Adam: A Method for Stochastic Optimization

Abstract

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method

Cited by in corpus (13757)

• Continuous control with deep reinforcement learning
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Learning Transferable Visual Models From Natural Language Supervision
• Attention U-Net: Learning Where to Look for the Pancreas
• Deep learning with convolutional neural networks for EEG decoding and visualization
• An Introduction to Variational Autoencoders
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Deep Learning using Rectified Linear Units (ReLU)
• ICLabel: An automated electroencephalographic independent component classifier, dataset, and website
• Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• DGM: A deep learning algorithm for solving partial differential equations
• Diffusion Models Beat GANs on Image Synthesis
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• KGAT: Knowledge Graph Attention Network for Recommendation
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network
• Prioritized Experience Replay
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• A Survey of Deep Learning Techniques for Autonomous Driving
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• MesoNet: a Compact Facial Video Forgery Detection Network
• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• AutoML: A Survey of the State-of-the-Art
• Graph Convolutional Networks for Hyperspectral Image Classification
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Asynchronous Methods for Deep Reinforcement Learning
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Over the Air Deep Learning Based Radio Signal Classification
• Cross-lingual Language Model Pretraining
• Scaling Laws for Neural Language Models
• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• Modeling polypharmacy side effects with graph convolutional networks
• LSTM Fully Convolutional Networks for Time Series Classification
• Temporal Ensembling for Semi-Supervised Learning
• Improved Training of Wasserstein GANs
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
• Deep Joint Source-Channel Coding for Wireless Image Transmission
• Deep learning for universal linear embeddings of nonlinear dynamics
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
• NICE: Non-linear Independent Components Estimation
• End-to-end Optimized Image Compression
• The Medical Segmentation Decathlon
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• A Deep Reinforced Model for Abstractive Summarization
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Enhanced LSTM for Natural Language Inference
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
• Multivariate LSTM-FCNs for Time Series Classification
• Zero-Shot Text-to-Image Generation
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Deep learning to represent sub-grid processes in climate models
• Graph Convolutional Matrix Completion
• fPINNs: Fractional Physics-Informed Neural Networks
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• Graph Contrastive Learning with Adaptive Augmentation
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• The Variational Quantum Eigensolver: a review of methods and best practices
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• The Perception-Distortion Tradeoff
• Representation Learning on Graphs with Jumping Knowledge Networks
• DRAW: A Recurrent Neural Network For Image Generation
• Image Quality Assessment: Unifying Structure and Texture Similarity
• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Energy-based Generative Adversarial Network
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Deep Learning-Based Communication Over the Air
• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• Super-resolution reconstruction of turbulent flows with machine learning
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Deep Audio-Visual Speech Recognition
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Snorkel: Rapid Training Data Creation with Weak Supervision
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• VL-BERT: Pre-training of Generic Visual-Linguistic Representations
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Automated brain extraction of multi-sequence MRI using artificial neural networks
• End-to-End Multimodal Emotion Recognition using Deep Neural Networks
• CamemBERT: a Tasty French Language Model
• Trained Ternary Quantization
• Deep Image Prior
• TractSeg - Fast and accurate white matter tract segmentation
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences
• Density estimation using Real NVP
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• COVID-CT-Dataset: A CT Scan Dataset about COVID-19
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Learning-Based View Synthesis for Light Field Cameras
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• BACH: Grand Challenge on Breast Cancer Histology Images
• Applications of deep learning in stock market prediction: recent progress
• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
• PadChest: A large chest x-ray image dataset with multi-label annotated reports
• Deep Learning for Classification of Hyperspectral Data: A Comparative Review
• Neural Volumes: Learning Dynamic Renderable Volumes from Images
• Pose Guided Person Image Generation
• Attention-based Deep Multiple Instance Learning
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Adversarially Learned Inference
• PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Resnet in Resnet: Generalizing Residual Architectures
• What Makes for Good Views for Contrastive Learning?
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
• Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• RPM-Net: Robust Point Matching using Learned Features
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
• HDR image reconstruction from a single exposure using deep CNNs
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series
• Physics-informed learning of governing equations from scarce data
• Revisiting Distributed Synchronous SGD
• Reproducible scaling laws for contrastive language-image learning
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• DeePMD-kit v2: A software package for Deep Potential models
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
• Don't Decay the Learning Rate, Increase the Batch Size
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• Recent Advances in Recurrent Neural Networks
• Invertible Conditional GANs for image editing
• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• The relativistic discriminator: a key element missing from standard GAN
• Machine learning in acoustics: theory and applications
• Deep Learning Methods for Improved Decoding of Linear Codes
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images
• Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• Neural Ordinary Differential Equations
• Certified Defenses against Adversarial Examples
• Three scenarios for continual learning
• Painting a portrait of the Galactic disc with its stellar clusters
• Generalized Seismic Phase Detection with Deep Learning
• Deep Neural Networks as Gaussian Processes
• Quantum advantage in learning from experiments
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Denoising Prior Driven Deep Neural Network for Image Restoration
• MPNet: Masked and Permuted Pre-training for Language Understanding
• Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
• Neural networks for post-processing ensemble weather forecasts
• DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning
• Deep image mining for diabetic retinopathy screening
• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• Seismic Signal Denoising and Decomposition Using Deep Neural Networks
• Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver
• DeepMind Control Suite
• Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
• P-wave arrival picking and first-motion polarity determination with deep learning
• On Using Monolingual Corpora in Neural Machine Translation
• Learning to Detect
• Multimodal Fusion Transformer for Remote Sensing Image Classification
• Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution
• Large Batch Training of Convolutional Networks
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• Dynamic Coattention Networks For Question Answering
• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• Attention is not Explanation
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Distributed Prioritized Experience Replay
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Data Augmentation using Random Image Cropping and Patching for Deep CNNs
• Physics-informed neural networks for solving Reynolds-averaged Navier$\unicode{x2013}$Stokes equations
• The Microsoft 2017 Conversational Speech Recognition System
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Group Sparse Regularization for Deep Neural Networks
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Dynamic Filter Networks
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification
• Quantum Natural Gradient
• Pre-Processing-Free Gear Fault Diagnosis Using Small Datasets with Deep Convolutional Neural Network-Based Transfer Learning
• A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
• End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
• Attributed Social Network Embedding
• Regularizing and Optimizing LSTM Language Models
• MolGAN: An implicit generative model for small molecular graphs
• HDLTex: Hierarchical Deep Learning for Text Classification
• DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Dynamic Graph Convolutional Networks
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
• Improved Image Captioning via Policy Gradient optimization of SPIDEr
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• Learning to Simulate Complex Physics with Graph Networks
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
• Causal Intervention for Leveraging Popularity Bias in Recommendation
• Countering Adversarial Images using Input Transformations
• DeBERTa: Decoding-enhanced BERT with Disentangled Attention
• Deep Reinforcement Learning for Multi-objective Optimization
• Learning Deep Generative Models of Graphs
• From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
• Improving performance of CNN to predict likelihood of COVID-19 using chest X-ray images with preprocessing algorithms
• Gated Graph Sequence Neural Networks
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• End-to-end Deep Learning of Optical Fiber Communications
• Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• Transfer learning in hybrid classical-quantum neural networks
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representation
• Light Gated Recurrent Units for Speech Recognition
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• Inferring transportation modes from GPS trajectories using a convolutional neural network
• Improved Denoising Diffusion Probabilistic Models
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Artificial neural networks for neuroscientists: A primer
• A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
• Gradient-based Hyperparameter Optimization through Reversible Learning
• DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
• Train longer, generalize better: closing the generalization gap in large batch training of neural networks
• Deep Anomaly Detection Using Geometric Transformations
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Deep Voice: Real-time Neural Text-to-Speech
• ATLAS $b$-jet identification performance and efficiency measurement with $t\bar{t}$ events in $pp$ collisions at $\sqrt{s}=13$ TeV
• Fine-Tuning Language Models from Human Preferences
• Perceptual Adversarial Networks for Image-to-Image Transformation
• Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport
• Deep Networks for Direction-of-Arrival Estimation in Low SNR
• Self-supervised ECG Representation Learning for Emotion Recognition
• Training-image based geostatistical inversion using a spatial generative adversarial neural network
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Filter-enhanced MLP is All You Need for Sequential Recommendation
• Conformer: Convolution-augmented Transformer for Speech Recognition
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection
• Deep-Learning Inversion of Seismic Data
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network
• Conditional Time Series Forecasting with Convolutional Neural Networks
• Scaling Graph Neural Networks with Approximate PageRank
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• Wave Physics as an Analog Recurrent Neural Network
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Optimization Problems for Machine Learning: A Survey
• Lookahead Optimizer: k steps forward, 1 step back
• NVAE: A Deep Hierarchical Variational Autoencoder
• Machine learning quantum phases of matter beyond the fermion sign problem
• Neural Network Detection of Data Sequences in Communication Systems
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Self-attention for raw optical Satellite Time Series Classification
• Multispectral and Hyperspectral Image Fusion Using a 3-D-Convolutional Neural Network
• Deep learning for determining a near-optimal topological design without any iteration
• InfoVAE: Information Maximizing Variational Autoencoders
• Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
• Generative Adversarial Imitation Learning
• Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
• MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
• Adaptive Computation Time for Recurrent Neural Networks
• Mining Latent Structures for Multimedia Recommendation
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification
• Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Deep Neural Networks for Data-Driven Turbulence Models
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Learning to Generate Reviews and Discovering Sentiment
• Adversarial Reciprocal Points Learning for Open Set Recognition
• SentEval: An Evaluation Toolkit for Universal Sentence Representations
• Passage Re-ranking with BERT
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• Evaluation of Session-based Recommendation Algorithms
• DyNet: The Dynamic Neural Network Toolkit
• Med3D: Transfer Learning for 3D Medical Image Analysis
• Layerwise learning for quantum neural networks
• Hello Edge: Keyword Spotting on Microcontrollers
• Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Hindsight Experience Replay
• A Comprehensive Analysis of Deep Regression
• Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning
• Data Augmentation by Pairing Samples for Images Classification
• An application of cascaded 3D fully convolutional networks for medical image segmentation
• Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning
• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
• Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks
• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Models Genesis
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Quasi-Recurrent Neural Networks
• Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals
• Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling
• Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
• Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion
• TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
• Boundary-Guided Camouflaged Object Detection
• Non-local Attention Optimized Deep Image Compression
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Learning the MMSE Channel Estimator
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
• Community Interaction and Conflict on the Web
• NPA: Neural News Recommendation with Personalized Attention
• Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Early Stage Malware Prediction Using Recurrent Neural Networks
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Compute Trends Across Three Eras of Machine Learning
• Anomaly Detection with Density Estimation
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
• Efficient representation and approximation of model predictive control laws via deep learning
• NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
• Recursive Cascaded Networks for Unsupervised Medical Image Registration
• Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey
• Deep Appearance Models for Face Rendering
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere
• Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition
• Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis
• MetaFormer Baselines for Vision
• Deep learning electromagnetic inversion with convolutional neural networks
• Classification without labels: Learning from mixed samples in high energy physics
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles
• An Iterative BP-CNN Architecture for Channel Decoding
• RSVQA: Visual Question Answering for Remote Sensing Data
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• Denoising Implicit Feedback for Recommendation
• DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
• TransNets: Learning to Transform for Recommendation
• Selective Encoding for Abstractive Sentence Summarization
• Grid Long Short-Term Memory
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
• Broadband DOA estimation using Convolutional neural networks trained with noise signals
• Ask the GRU: Multi-Task Learning for Deep Text Recommendations
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Sensitivity and Generalization in Neural Networks: an Empirical Study
• Neural Granger Causality
• Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
• Speaker-independent Speech Separation with Deep Attractor Network
• Improved training of end-to-end attention models for speech recognition
• Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes
• What do Neural Machine Translation Models Learn about Morphology?
• Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
• Transfer learning for time series classification
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging
• ChemTS: An Efficient Python Library for de novo Molecular Generation
• XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
• A Physics Informed Neural Network for Time-Dependent Nonlinear and Higher Order Partial Differential Equations
• Hardware-oriented Approximation of Convolutional Neural Networks
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Learning Optimal Resource Allocations in Wireless Systems
• Safe Exploration in Continuous Action Spaces
• Neural Natural Language Inference Models Enhanced with External Knowledge
• Single Image Portrait Relighting
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems
• Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
• Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
• Convergence Analysis of Two-layer Neural Networks with ReLU Activation
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• CANet: An Unsupervised Intrusion Detection System for High Dimensional CAN Bus Data
• Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising
• Compact Convolutional Neural Networks for Classification of Asynchronous Steady-state Visual Evoked Potentials
• MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video
• Learning Dexterous In-Hand Manipulation
• Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• Evaluation of deep learning models for multi-step ahead time series prediction
• Character Controllers Using Motion VAEs
• DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks
• Model-Ensemble Trust-Region Policy Optimization
• Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
• Transformer-based Acoustic Modeling for Hybrid Speech Recognition
• Unsupervised Generative Modeling Using Matrix Product States
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions
• Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• One Model To Learn Them All
• Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks
• Auxiliary Deep Generative Models
• Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRI
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• Deep Vessel Segmentation By Learning Graphical Connectivity
• Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
• FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• Identifying Corresponding Patches in SAR and Optical Images with a Pseudo-Siamese CNN
• Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease
• Adding Gradient Noise Improves Learning for Very Deep Networks
• CodeBERT: A Pre-Trained Model for Programming and Natural Languages
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
• Logic Tensor Networks
• Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
• Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
• AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Image De-raining Using a Conditional Generative Adversarial Network
• Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning
• DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks
• Hierarchical Multiscale Recurrent Neural Networks
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Ladder Variational Autoencoders
• Residual Dense Network for Image Super-Resolution
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• Detecting Offensive Language in Tweets Using Deep Learning
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Intra- and Inter-epoch Temporal Context Network (IITNet) Using Sub-epoch Features for Automatic Sleep Scoring on Raw Single-channel EEG
• Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
• Data-Driven Collective Variables for Enhanced Sampling
• Learning Open Set Network with Discriminative Reciprocal Points
• CMA-ES for Hyperparameter Optimization of Deep Neural Networks
• MDFEND: Multi-domain Fake News Detection
• Solving the acoustic VTI wave equation using physics-informed neural networks
• Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning
• A deep potential model with long-range electrostatic interactions
• Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction
• Learning to Remember Rare Events
• Learned Point Cloud Geometry Compression
• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
• Trainable ISTA for Sparse Signal Recovery
• Attentional Encoder Network for Targeted Sentiment Classification
• A deep learning-based remaining useful life prediction approach for bearings
• Lunar Crater Identification via Deep Learning
• Machine-Learning-Based Diagnostics of EEG Pathology
• SoundNet: Learning Sound Representations from Unlabeled Video
• Generating Adversarial Examples with Adversarial Networks
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks
• Source localization in an ocean waveguide using supervised machine learning
• Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations
• CLEAR: Contrastive Learning for Sentence Representation
• Benchmarking Graph Neural Networks
• Contextual Encoder-Decoder Network for Visual Saliency Prediction
• Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Phrase-Based & Neural Unsupervised Machine Translation
• A Survey of Privacy Attacks in Machine Learning
• Use What You Have: Video Retrieval Using Representations From Collaborative Experts
• EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion
• Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
• One-Shot Imitation Learning
• On the Reconstruction of Face Images from Deep Face Templates
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• Deep Residual Learning in Spiking Neural Networks
• Topology optimization of 2D structures with nonlinearities using deep learning
• Triple Generative Adversarial Nets
• Neural GPUs Learn Algorithms
• Automatic tagging using deep convolutional neural networks
• Video Compression With Rate-Distortion Autoencoders
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
• Multi-Modal Self-Supervised Learning for Recommendation
• Deep Pictorial Gaze Estimation
• Neural Collaborative Filtering
• Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
• An Application of Deep Reinforcement Learning to Algorithmic Trading
• Multi-Task Deep Neural Networks for Natural Language Understanding
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Joint Activity Recognition and Indoor Localization with WiFi Fingerprints
• On Breast Cancer Detection: An Application of Machine Learning Algorithms on the Wisconsin Diagnostic Dataset
• Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
• A Comparison of Optimization Algorithms for Deep Learning
• Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
• Jet Flavour Classification Using DeepJet
• Dynamical heating across the Milky Way disc using APOGEE and $Gaia$
• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Learning to Predict the Cosmological Structure Formation
• Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Analog forecasting of extreme-causing weather patterns using deep learning
• Unsupervised Learning of Depth and Ego-Motion from Video
• Drug Repurposing for COVID-19 via Knowledge Graph Completion
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
• Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
• Anomaly Detection using Autoencoders in High Performance Computing Systems
• Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
• Capsules for Object Segmentation
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• Revisiting Few-sample BERT Fine-tuning
• GSA-DenseNet121-COVID-19: a Hybrid Deep Learning Architecture for the Diagnosis of COVID-19 Disease based on Gravitational Search Optimization Algorithm
• Revisiting Anchor Mechanisms for Temporal Action Localization
• Which picker fits my data? A quantitative evaluation of deep learning based seismic pickers
• Country-wide high-resolution vegetation height mapping with Sentinel-2
• Memory-based control with recurrent neural networks
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
• Deep Voice 2: Multi-Speaker Neural Text-to-Speech
• Dual Cross-Attention for Medical Image Segmentation
• Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement
• Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier
• TNT: Target-driveN Trajectory Prediction
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
• One-Shot Neural Architecture Search via Self-Evaluated Template Network
• FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• Unsupervised Scale-consistent Depth Learning from Video
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
• Early-detection and classification of live bacteria using time-lapse coherent imaging and deep learning
• Structure optimization for parameterized quantum circuits
• Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
• ETA Prediction with Graph Neural Networks in Google Maps
• CrackGAN: Pavement Crack Detection Using Partially Accurate Ground Truths Based on Generative Adversarial Learning
• Controlling Fairness and Bias in Dynamic Learning-to-Rank
• Deep-learning-enabled geometric constraints and phase unwrapping for single-shot absolute 3D shape measurement
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• A Scalable Deep Neural Network Architecture for Multi-Building and Multi-Floor Indoor Localization Based on Wi-Fi Fingerprinting
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• L2 Regularization versus Batch and Weight Normalization
• Few-Shot Adversarial Domain Adaptation
• Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
• Deep Unsupervised Cardinality Estimation
• FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems
• Dual Encoding for Video Retrieval by Text
• Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
• An Explainable 3D Residual Self-Attention Deep Neural Network FOR Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI
• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
• Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• Deep Neural Networks for Multiple Speaker Detection and Localization
• ECG arrhythmia classification using a 2-D convolutional neural network
• Gradient Sparsification for Communication-Efficient Distributed Optimization
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• Deep Learning for Post-Processing Ensemble Weather Forecasts
• Federated Neural Collaborative Filtering
• A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
• Multi-Stage Document Ranking with BERT
• An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
• MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
• Intelligent Power Control for Spectrum Sharing in Cognitive Radios: A Deep Reinforcement Learning Approach
• Disentangled Representation Learning in Cardiac Image Analysis
• The BACCO Simulation Project: Exploiting the full power of large-scale structure for cosmology
• Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
• Differentiable MPC for End-to-end Planning and Control
• Simulation of multi-species flow and heat transfer using physics-informed neural networks
• Learning to Compose and Reason with Language Tree Structures for Visual Grounding
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC
• Gated Graph Recurrent Neural Networks
• Simultaneous Corn and Soybean Yield Prediction from Remote Sensing Data Using Deep Transfer Learning
• HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline
• Non-Stationary Texture Synthesis by Adversarial Expansion
• Sensor-based Gait Parameter Extraction with Deep Convolutional Neural Networks
• Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
• Removal of Batch Effects using Distribution-Matching Residual Networks
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Deep Reinforcement Learning for Electric Vehicle Routing Problem with Time Windows
• SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
• Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-Resolution
• Solving nonlinear differential equations with differentiable quantum circuits
• Unsupervised Machine Translation Using Monolingual Corpora Only
• Towards Sparse Hierarchical Graph Classifiers
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Deep Hough Transform for Semantic Line Detection
• Sequence to Sequence -- Video to Text
• Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
• A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series
• Deep learning at the shallow end: Malware classification for non-domain experts
• NetGAN: Generating Graphs via Random Walks
• PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
• DKN: Deep Knowledge-Aware Network for News Recommendation
• LipNet: End-to-End Sentence-level Lipreading
• Thinking Fast and Slow with Deep Learning and Tree Search
• Fairness in Credit Scoring: Assessment, Implementation and Profit Implications
• Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
• Wasserstein Auto-Encoders
• Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
• A new prediction method of unsteady wake flow by the hybrid deep neural network
• Classification of EEG-Based Brain Connectivity Networks in Schizophrenia Using a Multi-Domain Connectome Convolutional Neural Network
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
• Human Activity Recognition using Recurrent Neural Networks
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Harmonious Attention Network for Person Re-Identification
• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies
• How2: A Large-scale Dataset for Multimodal Language Understanding
• Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images
• Variational Encoding of Complex Dynamics
• Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks
• Missing Data Imputation with Adversarially-trained Graph Convolutional Networks
• Combined tract segmentation and orientation mapping for bundle-specific tractography
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Successor Features for Transfer in Reinforcement Learning
• An Interpretable Probabilistic Model for Short-Term Solar Power Forecasting Using Natural Gradient Boosting
• Learning a SAT Solver from Single-Bit Supervision
• LibriMix: An Open-Source Dataset for Generalizable Speech Separation
• Learning a Driving Simulator
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
• A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification
• Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach
• Deep Multimodal Subspace Clustering Networks
• Residual-based attention in physics-informed neural networks
• RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification
• On the prediction of critical heat flux using a physics-informed machine learning-aided framework
• Emerging quantum computing algorithms for quantum chemistry
• Generative replay with feedback connections as a general strategy for continual learning
• Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Nuclei instance segmentation and classification in histopathology images with StarDist
• Molecular graph generation with Graph Neural Networks
• Sentence Similarity Learning by Lexical Decomposition and Composition
• From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques
• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
• A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards
• Enhanced CNN for image denoising
• Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• A Berkeley View of Systems Challenges for AI
• Deformable 3D Convolution for Video Super-Resolution
• AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Tiny Machine Learning: Progress and Futures
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• Are Labels Required for Improving Adversarial Robustness?
• Deep Flare Net (DeFN) model for solar flare prediction
• Extrapolated full waveform inversion with deep learning
• Generalized Byzantine-tolerant SGD
• Semi-supervised Sequence Modeling for Elastic Impedance Inversion
• A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
• Robust Audio Adversarial Example for a Physical Attack
• Improving Variational Inference with Inverse Autoregressive Flow
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition
• Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy
• Differentiable Learning of Logical Rules for Knowledge Base Reasoning
• Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera
• OmniFold: A Method to Simultaneously Unfold All Observables
• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• MR image reconstruction using deep density priors
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• Wireless Interference Identification with Convolutional Neural Networks
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• Representation Learning by Rotating Your Faces
• A Review-aware Graph Contrastive Learning Framework for Recommendation
• Dynamical Variational Autoencoders: A Comprehensive Review
• Simultaneous calibration of spectro-photometric distances and the Gaia DR2 parallax zero-point offset with deep learning
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Leveraging Procedural Generation to Benchmark Reinforcement Learning
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
• Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Causal Contextual Prediction for Learned Image Compression
• A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations
• Online Batch Selection for Faster Training of Neural Networks
• Deep Complex Networks
• Deep learning observables in computational fluid dynamics
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
• Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings
• Applying deep reinforcement learning to active flow control in turbulent conditions
• Detection of phase transition via convolutional neural network
• RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Dynamic Word Embeddings
• Scaling description of generalization with number of parameters in deep learning
• Quantum generative adversarial network for generating discrete distribution
• A Neural Autoregressive Approach to Collaborative Filtering
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Variational Recurrent Auto-Encoders
• Supervised Multimodal Bitransformers for Classifying Images and Text
• Computational ghost imaging using deep learning
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
• A Minimalist Approach to Offline Reinforcement Learning
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• Towards Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-based Convolutional Encoders
• SAINT+: Integrating Temporal Features for EdNet Correctness Prediction
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Simple random search provides a competitive approach to reinforcement learning
• Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing
• Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• Learned Cardinalities: Estimating Correlated Joins with Deep Learning
• Pythia v0.1: the Winning Entry to the VQA Challenge 2018
• SpinalNet: Deep Neural Network with Gradual Input
• Improving detection of protein-ligand binding sites with 3D segmentation
• TCLR: Temporal Contrastive Learning for Video Representation
• Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning
• Benchmarking Batch Deep Reinforcement Learning Algorithms
• Stiff Neural Ordinary Differential Equations
• Invertible Residual Networks
• Neural Transfer Learning for Repairing Security Vulnerabilities in C Code
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
• GHRS: Graph-based Hybrid Recommendation System with Application to Movie Recommendation
• Deep Learning and Model Predictive Control for Self-Tuning Mode-Locked Lasers
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network
• Simulator-based training of generative models for the inverse design of metasurfaces
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
• OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
• All-Optical Information Processing Capacity of Diffractive Surfaces
• Context-Aware Visual Policy Network for Fine-Grained Image Captioning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• HDMI: High-order Deep Multiplex Infomax
• Bayesian Model-Agnostic Meta-Learning
• SMOTified-GAN for class imbalanced pattern classification problems
• Beyond Parity: Fairness Objectives for Collaborative Filtering
• Using machine learning to correct model error in data assimilation and forecast applications
• DeepSurf: A surface-based deep learning approach for the prediction of ligand binding sites on proteins
• POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS)
• A Label Attention Model for ICD Coding from Clinical Text
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Least Squares Generative Adversarial Networks
• Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach
• Analyzing Input and Output Representations for Speech-Driven Gesture Generation
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• The Strong Gravitational Lens Finding Challenge
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• An Overview of Machine Learning Techniques for Radiowave Propagation Modeling
• Disentangled Contrastive Collaborative Filtering
• Semantic Segmentation of Pathological Lung Tissue with Dilated Fully Convolutional Networks
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
• Simulation Assisted Likelihood-free Anomaly Detection
• UR-FUNNY: A Multimodal Language Dataset for Understanding Humor
• Generating Handwritten Chinese Characters using CycleGAN
• Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation
• Temporal Difference Models: Model-Free Deep RL for Model-Based Control
• Enhancing Discrete Choice Models with Representation Learning
• DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles
• Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Locating earthquakes with a network of seismic stations via a deep learning method
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Forecasting Future Humphrey Visual Fields Using Deep Learning
• Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
• Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections
• A Probabilistic U-Net for Segmentation of Ambiguous Images
• What is the Machine Learning?
• Path-Level Network Transformation for Efficient Architecture Search
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• A Multi-task Approach for Named Entity Recognition in Social Media Data
• Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Label Refinery: Improving ImageNet Classification through Label Progression
• Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology
• Deep Learning for Portfolio Optimization
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physics
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
• Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers
• BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification
• Super Resolution Convolutional Neural Network Models for Enhancing Resolution of Rock Micro-CT Images
• Learning Sparse Neural Networks through $L_0$ Regularization
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• XNLI: Evaluating Cross-lingual Sentence Representations
• The Neural Particle Method -- An Updated Lagrangian Physics Informed Neural Network for Computational Fluid Dynamics
• Dense Dilated Convolutions Merging Network for Land Cover Classification
• WINNet: Wavelet-inspired Invertible Network for Image Denoising
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
• Neural Network Renormalization Group
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Unfolding the Alternating Optimization for Blind Super Resolution
• Deep Learning in fNIRS: A review
• Deep Reinforcement Learning for Process Control: A Primer for Beginners
• Multimodal Generative Models for Scalable Weakly-Supervised Learning
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• CornerNet: Detecting Objects as Paired Keypoints
• Toward Controlled Generation of Text
• Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
• Where are we now? A large benchmark study of recent symbolic regression methods
• Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis
• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
• Deep Learning How to Fit an Intravoxel Incoherent Motion Model to Diffusion-Weighted MRI
• Supporting Very Large Models using Automatic Dataflow Graph Partitioning
• Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
• StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction
• Adversarial Video Generation on Complex Datasets
• Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Learning for Video Compression
• BS-Net: learning COVID-19 pneumonia severity on a large Chest X-Ray dataset
• Dense 3D Object Reconstruction from a Single Depth View
• Learning to Detect Objects with a 1 Megapixel Event Camera
• Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
• CNN-based Segmentation of Medical Imaging Data
• Emergent Complexity via Multi-Agent Competition
• Predictive Entropy Search for Multi-objective Bayesian Optimization
• An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification
• Artificial Neural Network with Physical Dynamic Metasurface Layer for Optimal Sensing
• RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
• Physics-informed neural networks for the shallow-water equations on the sphere
• Towards a Neural Statistician
• Palmprint Recognition in Uncontrolled and Uncooperative Environment
• FETCH: A deep-learning based classifier for fast transient classification
• Bayesian Recurrent Neural Networks
• A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEG
• TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
• HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
• Deep Identity-aware Transfer of Facial Attributes
• Deep Deterministic Policy Gradient for Urban Traffic Light Control
• A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
• Physics-Informed Neural Nets for Control of Dynamical Systems
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Deep Learning Based MIMO Communications
• Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training
• Graph Enhanced Representation Learning for News Recommendation
• Real-Time Radar-Based Gesture Detection and Recognition Built in an Edge-Computing Platform
• Pre-training of Graph Neural Network for Modeling Effects of Mutations on Protein-Protein Binding Affinity
• Self-supervised Learning for ECG-based Emotion Recognition
• AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
• Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Personalized Counterfactual Fairness in Recommendation
• LSTM-Based Zero-Velocity Detection for Robust Inertial Navigation
• Deep Learning for Tumor Classification in Imaging Mass Spectrometry
• ML-Net: multi-label classification of biomedical texts with deep neural networks
• Memory-Guided Multi-View Multi-Domain Fake News Detection
• Hierarchical Scene Coordinate Classification and Regression for Visual Localization
• Data Augmentation using Pre-trained Transformer Models
• When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?
• Convergence of the Deep BSDE Method for Coupled FBSDEs
• Spinal cord gray matter segmentation using deep dilated convolutions
• X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
• Revisiting Self-Training for Neural Sequence Generation
• Improved Techniques for Training Score-Based Generative Models
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Modeling Human Driving Behavior through Generative Adversarial Imitation Learning
• Deep Tone Mapping Operator for High Dynamic Range Images
• WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research
• Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
• Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
• Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
• OptNet: Differentiable Optimization as a Layer in Neural Networks
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving
• Soft-DTW: a Differentiable Loss Function for Time-Series
• Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
• Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
• Deep Kalman Filters
• Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning
• Composition-based Multi-Relational Graph Convolutional Networks
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• An Empirical Model of Large-Batch Training
• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
• End-to-end Learning of Multi-sensor 3D Tracking by Detection
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
• Deep splitting method for parabolic PDEs
• Dream to Control: Learning Behaviors by Latent Imagination
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists
• Data-Driven Modelling of the Reynolds Stress Tensor using Random Forests with Invariance
• The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
• Scalable Gradients for Stochastic Differential Equations
• Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
• Weighted Transformer Network for Machine Translation
• Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification
• Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
• Compression-aware Training of Deep Networks
• Meta-Reinforcement Learning Based Resource Allocation for Dynamic V2X Communications
• Meta-learning PINN loss functions
• Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
• DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
• TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
• Clinically Accurate Chest X-Ray Report Generation
• Learning the PE Header, Malware Detection with Minimal Domain Knowledge
• Learn to Combine Modalities in Multimodal Deep Learning
• Evolved Policy Gradients
• A deep learning approach to predict significant wave height using long short-term memory
• Representations of language in a model of visually grounded speech signal
• Optimization for deep learning: theory and algorithms
• Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
• Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
• From coarse wall measurements to turbulent velocity fields through deep learning
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Learned Convolutional Sparse Coding
• Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining
• DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm
• Learning to detect chest radiographs containing lung nodules using visual attention networks
• Estimating individual treatment effect: generalization bounds and algorithms
• Speech Emotion Recognition Using Multi-hop Attention Mechanism
• Recurrent Neural Networks: An Embedded Computing Perspective
• Offline Reinforcement Learning with Implicit Q-Learning
• FigureQA: An Annotated Figure Dataset for Visual Reasoning
• Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision
• Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Deep Convolutions for In-Depth Automated Rock Typing
• Milli-RIO: Ego-Motion Estimation with Low-Cost Millimetre-Wave Radar
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis
• Deep Learning-Based Model Predictive Control for Resonant Power Converters
• Knowledge Graph Reasoning with Relational Digraph
• AI Poincaré: Machine Learning Conservation Laws from Trajectories
• Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
• Taming the latency in multi-user VR 360${}^{\circ }$: A QoE-aware deep learning-aided multicast framework
• SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
• A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
• Non-convex Finite-Sum Optimization Via SCSG Methods
• Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images
• MINet: Multi-scale Interactive Network for Real-time Salient Object Detection of Strip Steel Surface Defects
• Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
• Compositional Attention Networks for Machine Reasoning
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• 3D Sketching using Multi-View Deep Volumetric Prediction
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
• Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
• A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams
• Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
• 3D Self-Supervised Methods for Medical Imaging
• Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Emotion Recognition From Speech With Recurrent Neural Networks
• Novel DeepONet architecture to predict stresses in elastoplastic structures with variable complex geometries and loads
• Battery-constrained Federated Edge Learning in UAV-enabled IoT for B5G/6G Networks
• Simulation of hyperelastic materials in real-time using Deep Learning
• On the Feasibility of Transfer-learning Code Smells using Deep Learning
• UrbanFM: Inferring Fine-Grained Urban Flows
• Neural Summarization by Extracting Sentences and Words
• Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
• A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction
• Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold
• High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning
• Transfer learning for music classification and regression tasks
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
• Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning
• State Predictive Information Bottleneck
• Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image
• Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks
• On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
• Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation
• Decentralized Power Allocation for MIMO-NOMA Vehicular Edge Computing Based on Deep Reinforcement Learning
• Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks
• Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction
• Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
• Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs
• Light Field Video Capture Using a Learning-Based Hybrid Imaging System
• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
• Delving into Deep Imbalanced Regression
• Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
• A neural attention model for speech command recognition
• Neural Interactive Collaborative Filtering
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Detection Algorithms for Communication Systems Using Deep Learning
• Multiphase flow prediction with deep neural networks
• Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications
• Dual Discriminator Generative Adversarial Nets
• Mixed-precision deep learning based on computational memory
• Attentive Aspect Modeling for Review-aware Recommendation
• When and why PINNs fail to train: A neural tangent kernel perspective
• GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
• Deep learning approach to description and classification of fungi microscopic images
• Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
• Neural Language Correction with Character-Based Attention
• RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking
• Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks
• Query2Label: A Simple Transformer Way to Multi-Label Classification
• Neural Additive Models: Interpretable Machine Learning with Neural Nets
• Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization
• Transforming Question Answering Datasets Into Natural Language Inference Datasets
• Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
• Context-Aware Visual Policy Network for Sequence-Level Image Captioning
• Evaluating surgical skills from kinematic data using convolutional neural networks
• Estimating Depth from RGB and Sparse Sensing
• Reinforced dynamics for enhanced sampling in large atomic and molecular systems
• Extreme events in dynamical systems and random walkers: A review
• Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads
• Structure-Preserving Image Super-Resolution
• Variational Autoencoders and Nonlinear ICA: A Unifying Framework
• Deep learning approach to describe and classify fungi microscopic images
• Look Before You Leap: Detecting Phishing Web Pages by Exploiting Raw URL And HTML Characteristics
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features
• PEPSI++: Fast and Lightweight Network for Image Inpainting
• Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures
• Robust sound event detection in bioacoustic sensor networks
• Land Cover Classification from Multi-temporal, Multi-spectral Remotely Sensed Imagery using Patch-Based Recurrent Neural Networks
• Learning to Protect Communications with Adversarial Neural Cryptography
• SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
• Disentangling Long and Short-Term Interests for Recommendation
• Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• Conditional Generation Net for Medication Recommendation
• A Novel Semi-Supervised Data-Driven Method for Chiller Fault Diagnosis with Unlabeled Data
• Deep learning of free boundary and Stefan problems
• Nuisance hardened data compression for fast likelihood-free inference
• Molecular representation learning with language models and domain-relevant auxiliary tasks
• XNOR-Net++: Improved Binary Neural Networks
• Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
• Pileup Mitigation with Machine Learning (PUMML)
• Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
• Pretrained Language Models for Sequential Sentence Classification
• A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture
• AI Safety Gridworlds
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Path-Restore: Learning Network Path Selection for Image Restoration
• End-to-End Object Detection with Adaptive Clustering Transformer
• Reinventing 2D Convolutions for 3D Images
• Adversarial Networks for the Detection of Aggressive Prostate Cancer
• Bilateral Multi-Perspective Matching for Natural Language Sentences
• Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
• Deep convolutional networks for quality assessment of protein folds
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Physics-informed neural networks of the Saint-Venant equations for downscaling a large-scale river model
• Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture
• Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• NeRF2: Neural Radio-Frequency Radiance Fields
• BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
• Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling
• EAST: An Efficient and Accurate Scene Text Detector
• Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
• A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels
• Message-passing neural networks for high-throughput polymer screening
• UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
• Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
• Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
• CNN+RNN Depth and Skeleton based Dynamic Hand Gesture Recognition
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
• Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models
• Towards Universal Paraphrastic Sentence Embeddings
• Self-Supervised Learning with Swin Transformers
• Privacy-Preserving Deep Learning via Weight Transmission
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network
• Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• Multi-Perspective Context Matching for Machine Comprehension
• Multiclass Wound Image Classification using an Ensemble Deep CNN-based Classifier
• User Diverse Preference Modeling by Multimodal Attentive Metric Learning
• Real-Time Adaptive Image Compression
• Multi-Objective CNN Based Algorithm for SAR Despeckling
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
• Blockchain-based Federated Learning with SMPC Model Verification Against Poisoning Attack for Healthcare Systems
• Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
• Multi-style Generative Network for Real-time Transfer
• Attenuation correction for brain PET imaging using deep neural network based on dixon and ZTE MR images
• MelNet: A Generative Model for Audio in the Frequency Domain
• TimeNet: Pre-trained deep recurrent neural network for time series classification
• Exploring the Role of Visual Content in Fake News Detection
• Identifying optimal cycles in quantum thermal machines with reinforcement-learning
• DeepMath - Deep Sequence Models for Premise Selection
• DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data
• Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
• BaitWatcher: A lightweight web interface for the detection of incongruent news headlines
• Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing
• EllSeg: An Ellipse Segmentation Framework for Robust Gaze Tracking
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Compressing Recurrent Neural Network with Tensor Train
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Black box variational inference for state space models
• Gravitational Wave Denoising of Binary Black Hole Mergers with Deep Learning
• Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
• Physics-Informed Neural Networks for Shell Structures
• Discover Your Social Identity from What You Tweet: a Content Based Approach
• Architectural Complexity Measures of Recurrent Neural Networks
• Contrastive Cross-Domain Sequential Recommendation
• MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks
• Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
• Unblind Your Apps: Predicting Natural-Language Labels for Mobile GUI Components by Deep Learning
• A Deep Learning Reconstruction Framework for Differential Phase-Contrast Computed Tomography with Incomplete Data
• Performance of top-quark and $W$-boson tagging with ATLAS in Run 2 of the LHC
• TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
• Discriminative Active Learning
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
• Towards Image Understanding from Deep Compression without Decoding
• Molecule Attention Transformer
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• Learning to Reason: End-to-End Module Networks for Visual Question Answering
• Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
• Wavelet Convolutional Neural Networks
• Improving prediction of the terrestrial water storage anomalies during the GRACE and GRACE-FO gap with Bayesian convolutional neural networks
• Maintaining cooperation in complex social dilemmas using deep reinforcement learning
• Deep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problems
• Learning to Classify from Impure Samples with High-Dimensional Data
• Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
• Review: Deep Learning in Electron Microscopy
• Reinforcement and Imitation Learning for Diverse Visuomotor Skills
• Texture Synthesis with Spatial Generative Adversarial Networks
• What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study
• i-flow: High-dimensional Integration and Sampling with Normalizing Flows
• Exploring the Limits of Out-of-Distribution Detection
• ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• Aligning where to see and what to tell: image caption with region-based attention and scene factorization
• A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images
• Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration
• Second-order Non-local Attention Networks for Person Re-identification
• Boundary-Seeking Generative Adversarial Networks
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• Root Mean Square Layer Normalization
• Unsupervised Learning of Object Keypoints for Perception and Control
• Graph neural networks for laminar flow prediction around random 2D shapes
• Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
• Quaternion Convolutional Neural Networks for Heterogeneous Image Processing
• HoloStain: Holographic virtual staining of individual biological cells
• FACMAC: Factored Multi-Agent Centralised Policy Gradients
• Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
• Learning to Generate Questions by Learning What not to Generate
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Local-Global Context Aware Transformer for Language-Guided Video Segmentation
• An Empirical Exploration of Curriculum Learning for Neural Machine Translation
• Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
• Changes to Captions: An Attentive Network for Remote Sensing Change Captioning
• Cell Segmentation and Tracking using CNN-Based Distance Predictions and a Graph-Based Matching Strategy
• Is it Time to Replace CNNs with Transformers for Medical Images?
• Detecting drug-drug interactions using artificial neural networks and classic graph similarity measures
• A mesh-free method for interface problems using the deep learning approach
• Fast Feature Fool: A data independent approach to universal adversarial perturbations
• Not All Samples Are Created Equal: Deep Learning with Importance Sampling
• Sharpness-Aware Minimization for Efficiently Improving Generalization
• IMF: Interactive Multimodal Fusion Model for Link Prediction
• FragNet: Writer Identification using Deep Fragment Networks
• Validating Hyperspectral Image Segmentation
• CCSNet: a deep learning modeling suite for CO${}_2$ storage
• CariGANs: Unpaired Photo-to-Caricature Translation
• Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
• Fixing Data Augmentation to Improve Adversarial Robustness
• Compositional Sequence Labeling Models for Error Detection in Learner Writing
• Adaptive Propagation Graph Convolutional Network
• Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering
• Decoding and mapping task states of the human brain via deep learning
• Data-Free Adversarial Distillation
• ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans
• An Empirical Study of Spatial Attention Mechanisms in Deep Networks
• A Rotation-Invariant Framework for Deep Point Cloud Analysis
• Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples
• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
• Data-Driven System Identification of 6-DoF Ship Motion in Waves with Neural Networks
• Deep Meta-Learning: Learning to Learn in the Concept Space
• A Comparison of Various Classical Optimizers for a Variational Quantum Linear Solver
• Evaluation of sentence embeddings in downstream and linguistic probing tasks
• Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Torchattacks: A PyTorch Repository for Adversarial Attacks
• Kernel Flows: from learning kernels from data into the abyss
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• End-to-End Differentiable Molecular Mechanics Force Field Construction
• PointConv: Deep Convolutional Networks on 3D Point Clouds
• The Static Local Field Correction of the Warm Dense Electron Gas: An ab Initio Path Integral Monte Carlo Study and Machine Learning Representation
• Adversarial Generation of Natural Language
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
• Learning and avoiding disorder in multimode fibers
• Male pelvic synthetic CT generation from T1-weighted MRI using 2D and 3D convolutional neural networks
• deSpeckNet: Generalizing Deep Learning Based SAR Image Despeckling
• Classification of Machine Learning Frameworks for Data-Driven Thermal Fluid Models
• Machine learning non-Markovian quantum dynamics
• Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
• Backprop KF: Learning Discriminative Deterministic State Estimators
• StarNet: Targeted Computation for Object Detection in Point Clouds
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Censoring Representations with an Adversary
• DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
• Conditional Variational Image Deraining
• What Do We Understand About Convolutional Networks?
• Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
• Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• Wavelet Convolutional Neural Networks for Texture Classification
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Fine-tuning wav2vec2 for speaker recognition
• Outlier Exposure with Confidence Control for Out-of-Distribution Detection
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Roundtrip: A Deep Generative Neural Density Estimator
• Benchmarking Adversarial Patch Against Aerial Detection
• When Gaussian Process Meets Big Data: A Review of Scalable GPs
• Updates to the DScribe Library: New Descriptors and Derivatives
• Deep Model Compression: Distilling Knowledge from Noisy Teachers
• Deep Modular Co-Attention Networks for Visual Question Answering
• A Transition-Based Directed Acyclic Graph Parser for UCCA
• Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms
• Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation
• Experimental velocity data estimation for imperfect particle images using machine learning
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
• Variational Quantum Boltzmann Machines
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
• Active learning of deep surrogates for PDEs: Application to metasurface design
• MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
• Pretrained Transformers as Universal Computation Engines
• Instance-Aware Domain Generalization for Face Anti-Spoofing
• A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection
• News Session-Based Recommendations using Deep Neural Networks
• Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
• End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Study of Different Deep Learning Approach with Explainable AI for Screening Patients with COVID-19 Symptoms: Using CT Scan and Chest X-ray Image Dataset
• Multi-Grained Named Entity Recognition
• FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements
• Improving Landslide Detection on SAR Data through Deep Learning
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• ABCNet: An attention-based method for particle tagging
• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
• Learning Deep Transformer Models for Machine Translation
• Learned Conjugate Gradient Descent Network for Massive MIMO Detection
• Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems
• Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
• Curriculum Learning for Speech Emotion Recognition from Crowdsourced Labels
• Unveiling phase transitions with machine learning
• ECAPA-TDNN Embeddings for Speaker Diarization
• Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
• Edge Contraction Pooling for Graph Neural Networks
• CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning
• SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs
• Deep Active Inference
• Deep Open Intent Classification with Adaptive Decision Boundary
• A BERT Baseline for the Natural Questions
• PrecoderNet: Hybrid Beamforming for Millimeter Wave Systems with Deep Reinforcement Learning
• Unsupervised Learning of 3D Structure from Images
• Physics and Equality Constrained Artificial Neural Networks: Application to Forward and Inverse Problems with Multi-fidelity Data Fusion
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• Deep learning of thermodynamics-aware reduced-order models from data
• Discovering state-parameter mappings in subsurface models using generative adversarial networks
• Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning
• SO-Net: Self-Organizing Network for Point Cloud Analysis
• Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
• Temperature Field Inversion of Heat-Source Systems via Physics-Informed Neural Networks
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
• Boosting Resolution and Recovering Texture of micro-CT Images with Deep Learning
• Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
• A simple yet effective baseline for 3d human pose estimation
• Generalization techniques of neural networks for fluid flow estimation
• A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
• Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
• Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease
• A Deep Learning Perspective on the Origin of Facial Expressions
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Deep-Learning based Inverse Modeling Approaches: A Subsurface Flow Example
• Automatic sleep stage classification with deep residual networks in a mixed-cohort setting
• On the Convergence Proof of AMSGrad and a New Version
• Capsule Networks against Medical Imaging Data Challenges
• Applying Deep Learning To Airbnb Search
• A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling
• TSA-Net: Tube Self-Attention Network for Action Quality Assessment
• Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
• Bayesian deep learning for error estimation in the analysis of anomalous diffusion
• Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking
• Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
• Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
• Second-Order Pooling for Graph Neural Networks
• Critic Regularized Regression
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
• A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation
• Handling Missing Data with Graph Representation Learning
• Reduced-order modeling with artificial neurons for gravitational-wave inference
• Emotional EEG Classification using Connectivity Features and Convolutional Neural Networks
• A Generative Model for Volume Rendering
• Neural Dual Contouring
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact
• Black-Box Attacks against RNN based Malware Detection Algorithms
• On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
• End-to-End ASR-free Keyword Search from Speech
• Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
• HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks
• Real-Time Deep Learning Approach to Visual Servo Control and Grasp Detection for Autonomous Robotic Manipulation
• Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
• CEM-RL: Combining evolutionary and gradient-based methods for policy search
• CENN: Conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries
• Deep 6-DOF Tracking
• Adaptive Universal Generalized PageRank Graph Neural Network
• Intelligent Meta-Imagers: From Compressed to Learned Sensing
• Machine Learning Holography for 3D Particle Field Imaging
• An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
• Time Series Forecasting Using LSTM Networks: A Symbolic Approach
• A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
• VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
• A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
• A Deep Learning Approach for Blind Drift Calibration of Sensor Networks
• SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling
• Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networks
• Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems
• DMRF-UNet: A Two-Stage Deep Learning Scheme for GPR Data Inversion under Heterogeneous Soil Conditions
• Microstructure synthesis using style-based generative adversarial network
• Where to put the Image in an Image Caption Generator
• Adversarial Training for Large Neural Language Models
• Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes
• WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations
• Multimodal Spatio-Temporal Deep Learning Approach for Neonatal Postoperative Pain Assessment
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• Supervised Learning of the Next-Best-View for 3D Object Reconstruction
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Diverse Trajectory Forecasting with Determinantal Point Processes
• Learning to design from humans: Imitating human designers through deep learning
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Data-driven vector localized waves and parameters discovery for Manakov system using deep learning approach
• Visual Reference Resolution using Attention Memory for Visual Dialog
• Heterogeneous Graph Representation Learning with Relation Awareness
• Natural Language Generation for Electronic Health Records
• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
• Deep Learning Based Sphere Decoding
• Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
• Structure-preserving neural networks
• CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
• Dissecting Neural ODEs
• Dynamic Routing Between Capsules
• On the Origin of Deep Learning
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Reading Wikipedia to Answer Open-Domain Questions
• Generalized Inner Loop Meta-Learning
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Self-Adaptive Training: beyond Empirical Risk Minimization
• Universal discriminative quantum neural networks
• Gromov-Wasserstein Learning for Graph Matching and Node Embedding
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Finding beans in burgers: Deep semantic-visual embedding with localization
• GP-GAN: Towards Realistic High-Resolution Image Blending
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery
• Neural Vector Spaces for Unsupervised Information Retrieval
• 3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels
• Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
• Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search
• Deep learning for galaxy surface brightness profile fitting
• DIVA: Domain Invariant Variational Autoencoders
• Identifying Galaxy Mergers in Observations and Simulations with Deep Learning
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
• Uncovering turbulent plasma dynamics via deep learning from partial observations
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Analysing Mathematical Reasoning Abilities of Neural Models
• Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
• Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks
• Robust Data-Driven Zero-Velocity Detection for Foot-Mounted Inertial Navigation
• DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
• A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat
• Hierarchical Object Detection with Deep Reinforcement Learning
• Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features
• Global Model Learning for Large Deformation Control of Elastic Deformable Linear Objects: An Efficient and Adaptive Approach
• Understanding and Improving Knowledge Distillation
• Exchanging Dual Encoder-Decoder: A New Strategy for Change Detection with Semantic Guidance and Spatial Localization
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• COCOA: Cross Modality Contrastive Learning for Sensor Data
• Micro Hand Gesture Recognition System Using Ultrasonic Active Sensing
• Learning hidden elasticity with deep neural networks
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Hybrid Robotic Grasping with a Soft Multimodal Gripper and a Deep Multistage Learning Scheme
• Early Detection of Myocardial Infarction in Low-Quality Echocardiography
• Neural Collaborative Reasoning
• A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
• Physics-informed neural networks for myocardial perfusion MRI quantification
• Functional Adversarial Attacks
• Unfolding with Generative Adversarial Networks
• GREEK-BERT: The Greeks visiting Sesame Street
• The Pitfalls of Simplicity Bias in Neural Networks
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
• Multiplicative LSTM for sequence modelling
• Super-Resolution with Deep Convolutional Sufficient Statistics
• A Unified Model for Opinion Target Extraction and Target Sentiment Prediction
• Deep Model Predictive Control with Online Learning for Complex Physical Systems
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• Noise Reduction in Gravitational-wave Data via Deep Learning
• FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
• Compositional generalization in a deep seq2seq model by separating syntax and semantics
• 2022 Review of Data-Driven Plasma Science
• A novel database of Children's Spontaneous Facial Expressions (LIRIS-CSE)
• SkinNet: A Deep Learning Framework for Skin Lesion Segmentation
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• SCOP: Scientific Control for Reliable Neural Network Pruning
• Sampling Matters in Deep Embedding Learning
• Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow
• Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
• Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
• Predicting Network Controllability Robustness: A Convolutional Neural Network Approach
• Controlling an Autonomous Vehicle with Deep Reinforcement Learning
• HTMLPhish: Enabling Phishing Web Page Detection by Applying Deep Learning Techniques on HTML Analysis
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• Attacking the Madry Defense Model with $L_1$-based Adversarial Examples
• Deep Networks as Approximators of Optimal Transfers Solutions in Multitarget Missions
• SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• Variational Graph Normalized Auto-Encoders
• Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Study
• An End-to-End Deep Learning Approach for Epileptic Seizure Prediction
• 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
• Generating Visually Aligned Sound from Videos
• A machine learning approach for efficient uncertainty quantification using multiscale methods
• Deep learning in biomedical optics
• DenseCap: Fully Convolutional Localization Networks for Dense Captioning
• Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
• A Study of MatchPyramid Models on Ad-hoc Retrieval
• Deep learning of contagion dynamics on complex networks
• Graph Convolution Machine for Context-aware Recommender System
• MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
• Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning
• Stochastic Conjugate Gradient Algorithm with Variance Reduction
• Modeling Relational Data with Graph Convolutional Networks
• Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
• A Joint Model for Question Answering and Question Generation
• Efficient Uncertainty Quantification for Dynamic Subsurface Flow with Surrogate by Theory-guided Neural Network
• Contrastive Collaborative Filtering for Cold-Start Item Recommendation
• An artificial neural network approach to bifurcating phenomena in computational fluid dynamics
• Super-resolution PET imaging using convolutional neural networks
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
• Self-Driving Car Steering Angle Prediction Based on Image Recognition
• Knowledge Transfer between Buildings for Seismic Damage Diagnosis through Adversarial Learning
• PhenoTagger: A Hybrid Method for Phenotype Concept Recognition using Human Phenotype Ontology
• Deformable Non-local Network for Video Super-Resolution
• Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech
• Deep Divergence-Based Approach to Clustering
• Change Point Detection in Time Series Data using Autoencoders with a Time-Invariant Representation
• Fast Object Learning and Dual-arm Coordination for Cluttered Stowing, Picking, and Packing
• Deep Learning of Quasar Spectra to Discover and Characterize Damped Lya Systems
• Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders
• Improving Variational Auto-Encoders using Householder Flow
• Weakly Labelled AudioSet Tagging with Attention Neural Networks
• A Method of Rapid Quantification of Patient-Specific Organ Dose for CT Using Coupled Deep-Learning based Multi-Organ Segmentation and GPU-accelerated Monte Carlo Dose Computing
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• Split Learning for collaborative deep learning in healthcare
• Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction
• Solving inverse problems using conditional invertible neural networks
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• Quantifying Translation-Invariance in Convolutional Neural Networks
• Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
• Lightweight Image Super-Resolution with Adaptive Weighted Learning Network
• Emotional Speech-Driven Animation with Content-Emotion Disentanglement
• Performance of the Quantum Approximate Optimization Algorithm on the Maximum Cut Problem
• Heterogeneous Multilayer Generalized Operational Perceptron
• Deep Retinal Image Segmentation with Regularization Under Geometric Priors
• Neural Reverse Engineering of Stripped Binaries using Augmented Control Flow Graphs
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Ground state energy functional with Hartree-Fock efficiency and chemical accuracy
• MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
• Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network
• Deep Polynomial Neural Networks
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• Not all bytes are equal: Neural byte sieve for fuzzing
• Unsupervised machine learning of topological phase transitions from experimental data
• Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
• A novel meta-learning initialization method for physics-informed neural networks
• Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media
• Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Ensemble Conformalized Quantile Regression for Probabilistic Time Series Forecasting
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate
• Stochastic Hyperparameter Optimization through Hypernetworks
• DepressionNet: A Novel Summarization Boosted Deep Framework for Depression Detection on Social Media
• A Closer Look at Accuracy vs. Robustness
• Self-supervised deep convolutional neural network for chest X-ray classification
• A deep learning framework for solution and discovery in solid mechanics
• ESCM${}^2$: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation
• Detecting motorcycle helmet use with deep learning
• Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
• Rain Streak Removal for Single Image via Kernel Guided CNN
• Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolution
• Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks
• Characterising optical fibre transmission matrices using metasurface reflector stacks for lensless imaging without distal access
• Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket
• Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction
• SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
• CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imaging
• Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Putting An End to End-to-End: Gradient-Isolated Learning of Representations
• Continuous-time system identification with neural networks: Model structures and fitting criteria
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
• Feature-map-level Online Adversarial Knowledge Distillation
• ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks
• Deep Bayesian Inversion
• Machine Learning-based Urban Canyon Path Loss Prediction using 28 GHz Manhattan Measurements
• SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning
• Predicting novel superconducting hydrides using machine learning approaches
• Nonlinear Approximation via Compositions
• TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
• Inference Suboptimality in Variational Autoencoders
• Deeply Sub-Wavelength Localization with Reverberation-Coded-Aperture
• Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
• An FE-DMN method for the multiscale analysis of fiber reinforced plastic components
• Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• Supervised Compression for Resource-Constrained Edge Computing Systems
• Autoregressive Transformer Neural Network for Simulating Open Quantum Systems via a Probabilistic Formulation
• T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
• 3DSSD: Point-based 3D Single Stage Object Detector
• 3D Bayesian Variational Full Waveform Inversion
• Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction
• Knowledge Query Network: How Knowledge Interacts with Skills
• Learning model-based planning from scratch
• Practical Approaches Towards Deep-Learning Based Cross-Device Power Side Channel Attack
• Learning to Optimize Neural Nets
• Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning
• Confusing Image Quality Assessment: Towards Better Augmented Reality Experience
• Preserving Semantic Relations for Zero-Shot Learning
• Neural-Network Decoders for Quantum Error Correction using Surface Codes:A Space Exploration of the Hardware Cost-Performance Trade-Offs
• StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow
• Robust Ultra-wideband Range Error Mitigation with Deep Learning at the Edge
• Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
• Detection of Inferior Myocardial Infarction using Shallow Convolutional Neural Networks
• Attacking Recommender Systems with Augmented User Profiles
• Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
• Fully Neural Network based Model for General Temporal Point Processes
• Probabilistic Deep Learning for Real-Time Large Deformation Simulations
• RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
• A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learning
• Hierarchical Convolutional-Deconvolutional Neural Networks for Automatic Liver and Tumor Segmentation
• Learning Dense and Continuous Optical Flow from an Event Camera
• Solving inverse-PDE problems with physics-aware neural networks
• DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
• Neural Memory Networks for Seizure Type Classification
• Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening
• Parameter-Efficient Person Re-identification in the 3D Space
• Intelligent optical performance monitor using multi-task learning based artificial neural network
• Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion
• Automated Conformance Testing for JavaScript Engines via Deep Compiler Fuzzing
• 4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds
• Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging utilizing Deep Learning
• MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification
• Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning
• Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis
• GDPNet: Refining Latent Multi-View Graph for Relation Extraction
• Application of generative autoencoder in de novo molecular design
• Towards Adversarial Retinal Image Synthesis
• Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
• Quantum computing of the ${}^6$Li nucleus via ordered unitary coupled clusters
• Non-rigid image registration using fully convolutional networks with deep self-supervision
• Ground truth force distribution for learning-based tactile sensing: a finite element approach
• A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
• MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
• Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation
• Consistent 3D Hand Reconstruction in Video via self-supervised Learning
• Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Likelihood-free inference with emulator networks
• ISIC 2017 - Skin Lesion Analysis Towards Melanoma Detection
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Deep neural network improves the estimation of polygenic risk scores for breast cancer
• Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
• Joint Implicit Image Function for Guided Depth Super-Resolution
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• Revisiting Adversarially Learned Injection Attacks Against Recommender Systems
• Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks
• A perspective on physical reservoir computing with nanomagnetic devices
• Learning Graph Representations with Embedding Propagation
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
• A Generalization of Convolutional Neural Networks to Graph-Structured Data
• Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Unpaired image denoising using a generative adversarial network in X-ray CT
• A-NICE-MC: Adversarial Training for MCMC
• Improving Universal Sound Separation Using Sound Classification
• Sound source detection, localization and classification using consecutive ensemble of CRNN models
• DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
• Distilled One-Shot Federated Learning
• GAP-net for Snapshot Compressive Imaging
• Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine (SVM) for Malware Classification
• Deep Rectangling for Image Stitching: A Learning Baseline
• Curriculum semi-supervised segmentation
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Zero-shot Text Classification With Generative Language Models
• Machine Learning for Optimal Parameter Prediction in Quantum Key Distribution
• Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
• SkillNER: Mining and Mapping Soft Skills from any Text
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction
• Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems
• Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19
• Machine Learning Implicit Solvation for Molecular Dynamics
• Adversarial Perturbations Against Real-Time Video Classification Systems
• Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
• Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
• Perceptually Optimized Image Rendering
• Theory-guided Auto-Encoder for Surrogate Construction and Inverse Modeling
• Distributed Deep Neural Networks over the Cloud, the Edge and End Devices
• Reinforcement Learning for Integer Programming: Learning to Cut
• PU-Net: Point Cloud Upsampling Network
• Learning physical properties of liquid crystals with deep convolutional neural networks
• Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks
• A Tutorial on Deep Learning for Music Information Retrieval
• Magnetostatics and micromagnetics with physics informed neural networks
• Lightweight Multi-Branch Network for Person Re-Identification
• 3D G-CNNs for Pulmonary Nodule Detection
• UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
• SPLATNet: Sparse Lattice Networks for Point Cloud Processing
• Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data
• Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
• When Do Neural Networks Outperform Kernel Methods?
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• Learning Generative Models with Sinkhorn Divergences
• On Self Modulation for Generative Adversarial Networks
• Attention Correctness in Neural Image Captioning
• Data-driven learning of robust nonlocal physics from high-fidelity synthetic data
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• Do Convolutional Networks need to be Deep for Text Classification ?
• Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• Earthquake Phase Association with Graph Neural Networks
• Developing an Unsupervised Real-time Anomaly Detection Scheme for Time Series with Multi-seasonality
• Computing Committor Functions for the Study of Rare Events Using Deep Learning
• Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
• Wideband Beamforming for RIS Assisted Near-Field Communications
• Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
• TDAN: Temporally Deformable Alignment Network for Video Super-Resolution
• HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
• Decoupled Neural Interfaces using Synthetic Gradients
• Remote estimation over a packet-drop channel with Markovian state
• Multilingual Neural Machine Translation with Task-Specific Attention
• Physics-informed neural networks for solving parametric magnetostatic problems
• ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
• Interpretation of Neural Networks is Fragile
• A Novel Graph based Trajectory Predictor with Pseudo Oracle
• Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning
• Video Frame Interpolation via Adaptive Separable Convolution
• Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Score
• Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach
• Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
• Future Frame Prediction for Anomaly Detection -- A New Baseline
• On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
• Gated-Dilated Networks for Lung Nodule Classification in CT scans
• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning
• Deep Learning Head Model for Real-time Estimation of Entire Brain Deformation in Concussion
• Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection
• Performance of a Deep Neural Network at Detecting North Atlantic Right Whale Upcalls
• Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• FontCode: Embedding Information in Text Documents using Glyph Perturbation
• UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
• Few-Shot Learning with Geometric Constraints
• Automatic Variational Inference in Stan
• A Generative Car-following Model Conditioned On Driving Styles
• ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features
• A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• An Extensive Study on Cross-Dataset Bias and Evaluation Metrics Interpretation for Machine Learning applied to Gastrointestinal Tract Abnormality Classification
• Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming
• Applications of Online Deep Learning for Crisis Response Using Social Media Information
• Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
• Dynamics-Aware Unsupervised Discovery of Skills
• Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• Collaborative Filtering with Recurrent Neural Networks
• Stabilizing GAN Training with Multiple Random Projections
• Building medical image classifiers with very limited data using segmentation networks
• 3DInvNet: A Deep Learning-Based 3D Ground-Penetrating Radar Data Inversion
• Machine learning non-local correlations
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Multilingual Image Description with Neural Sequence Models
• CoKE: Contextualized Knowledge Graph Embedding
• Vision Transformer based COVID-19 Detection using Chest X-rays
• Two-Step Sound Source Separation: Training on Learned Latent Targets
• Contrastive Learning of Structured World Models
• End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies
• Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation
• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
• Distance-based Self-Attention Network for Natural Language Inference
• Learning to Continually Learn
• Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
• Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
• PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images
• Super-resolution emulator of cosmological simulations using deep physical models
• Learned discretizations for passive scalar advection in a 2-D turbulent flow
• Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
• Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
• Drug-Drug Adverse Effect Prediction with Graph Co-Attention
• Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
• Contrastive Out-of-Distribution Detection for Pretrained Transformers
• Learning quantum data with the quantum Earth Mover's distance
• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting
• Learning to synthesise the ageing brain without longitudinal data
• SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion
• cellSTORM - Cost-effective Super-Resolution on a Cellphone using dSTORM
• Fine-grained Visual-textual Representation Learning
• A Machine Learning Approach to DoA Estimation and Model Order Selection for Antenna Arrays with Subarray Sampling
• Learning Heuristics over Large Graphs via Deep Reinforcement Learning
• Generative Networks for Precision Enthusiasts
• Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning
• Learning to Generalize from Sparse and Underspecified Rewards
• Int-Deep: A Deep Learning Initialized Iterative Method for Nonlinear Problems
• Discriminability objective for training descriptive captions
• Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion
• Inconsistent Matters: A Knowledge-guided Dual-consistency Network for Multi-modal Rumor Detection
• Neural Abstractive Text Summarization with Sequence-to-Sequence Models
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
• Performance characterization of a novel deep learning-based MR image reconstruction pipeline
• Symplectic Recurrent Neural Networks
• Cloud and Cloud Shadow Segmentation for Remote Sensing Imagery via Filtered Jaccard Loss Function and Parametric Augmentation
• Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations
• Anti-efficient encoding in emergent communication
• A robust anomaly finder based on autoencoders
• SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
• Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
• A Deep Convolutional Neural Network Model for improving WRF Forecasts
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• See, Hear, and Read: Deep Aligned Representations
• SelectNet: Self-paced Learning for High-dimensional Partial Differential Equations
• Convolutional Hierarchical Attention Network for Query-Focused Video Summarization
• Visually Grounded Neural Syntax Acquisition
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Machine Learning Approach to Model Order Reduction of Nonlinear Systems via Autoencoder and LSTM Networks
• CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
• 3D Simulation for Robot Arm Control with Deep Q-Learning
• End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-agent
• Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
• SPCANet: Stellar Parameters and Chemical Abundances Network for LAMOST-II Medium Resolution Survey
• Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
• Open Domain Event Extraction Using Neural Latent Variable Models
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• A Good Image Generator Is What You Need for High-Resolution Video Synthesis
• Deep Reinforcement Learning Control of Quantum Cartpoles
• Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts
• Actionable and Interpretable Fault Localization for Recurring Failures in Online Service Systems
• Convolutional Neural Network Ensemble Learning for Hyperspectral Imaging-based Blackberry Fruit Ripeness Detection in Uncontrolled Farm Environment
• Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Domain Generalization via Optimal Transport with Metric Similarity Learning
• Turbulent scalar flux in inclined jets in crossflow: counter gradient transport and deep learning modelling
• Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification
• XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
• Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network
• Theoretical Analysis of Auto Rate-Tuning by Batch Normalization
• Federated Multi-view Matrix Factorization for Personalized Recommendations
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• Co-training for Demographic Classification Using Deep Learning from Label Proportions
• FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
• Well-calibrated Confidence Measures for Multi-label Text Classification with a Large Number of Labels
• Bayesian Batch Active Learning as Sparse Subset Approximation
• On the Potential of Simple Framewise Approaches to Piano Transcription
• ECOVNet: An Ensemble of Deep Convolutional Neural Networks Based on EfficientNet to Detect COVID-19 From Chest X-rays
• Financial Markets Prediction with Deep Learning
• Contemporary machine learning: a guide for practitioners in the physical sciences
• Optimizing Rank-based Metrics with Blackbox Differentiation
• CEST MR fingerprinting (CEST-MRF) for Brain Tumor Quantification Using EPI Readout and Deep Learning Reconstruction
• Failures of Gradient-Based Deep Learning
• RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection
• Learning to Disentangle Scenes for Person Re-identification
• Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network
• Contracting Arbitrary Tensor Networks: General Approximate Algorithm and Applications in Graphical Models and Quantum Circuit Simulations
• FoodX-251: A Dataset for Fine-grained Food Classification
• CarDD: A New Dataset for Vision-based Car Damage Detection
• Probing stop pair production at the LHC with graph neural networks
• End-to-end neural relation extraction using deep biaffine attention
• Relational Fusion Networks: Graph Convolutional Networks for Road Networks
• Modeling Others using Oneself in Multi-Agent Reinforcement Learning
• GraphIE: A Graph-Based Framework for Information Extraction
• Linguistic Features for Readability Assessment
• The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares
• Assessing Transferability from Simulation to Reality for Reinforcement Learning
• Infrared and 3D skeleton feature fusion for RGB-D action recognition
• Few-Shot Learning Through an Information Retrieval Lens
• Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
• A Neural Network based Shock Detection and Localization Approach for Discontinuous Galerkin Methods
• What is the best RNN-cell structure to forecast each time series behavior?
• LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation
• Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting
• Fast differentiable DNA and protein sequence optimization for molecular design
• Explainable Activity Recognition for Smart Home Systems
• MODEL: Motif-based Deep Feature Learning for Link Prediction
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• A Computational Approach to Packet Classification
• Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth Extension
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography
• Risk-Aware Energy Scheduling for Edge Computing with Microgrid: A Multi-Agent Deep Reinforcement Learning Approach
• Deep Vectorization of Technical Drawings
• Detecting COVID-19 from Chest Computed Tomography Scans using AI-Driven Android Application
• Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
• Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
• Large Kernel Distillation Network for Efficient Single Image Super-Resolution
• Multi-Task Learning of Height and Semantics from Aerial Images
• Deep Neural Network Based Malware Detection Using Two Dimensional Binary Program Features
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
• Reactive Dynamics and Spectroscopy of Hydrogen Transfer from Neural Network-Based Reactive Potential Energy Surfaces
• SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN
• Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
• Recurrent Neural Networks for Semantic Instance Segmentation
• SLSNet: Skin lesion segmentation using a lightweight generative adversarial network
• Effective Quantization Methods for Recurrent Neural Networks
• Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
• Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
• Classical-to-quantum convolutional neural network transfer learning
• Unifying Map and Landmark Based Representations for Visual Navigation
• Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
• Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning
• Variational Autoencoders for Collaborative Filtering
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• Application of Gaussian process regression to plasma turbulent transport model validation via integrated modelling
• Cancer image classification based on DenseNet model
• Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving
• Expression Analysis Based on Face Regions in Read-world Conditions
• Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction
• Accelerating Flash Calculation through Deep Learning Methods
• Scene Recognition with Prototype-agnostic Scene Layout
• Automatic Rule Extraction from Long Short Term Memory Networks
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• Deep Signal Recovery with One-Bit Quantization
• ASAP: Architecture Search, Anneal and Prune
• Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction
• Variational Temporal Deep Generative Model for Radar HRRP Target Recognition
• Deep Learning for Passive Synthetic Aperture Radar
• EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
• KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
• Enabling large-scale viscoelastic calculations via neural network acceleration
• Unsupervised Domain Adversarial Self-Calibration for Electromyographic-based Gesture Recognition
• Variational Autoencoder with Arbitrary Conditioning
• Multi-level Attention Model for Weakly Supervised Audio Classification
• Lifelong Teacher-Student Network Learning
• GERE: Generative Evidence Retrieval for Fact Verification
• Graph Neural Networks Accelerated Molecular Dynamics
• Overparameterized Neural Networks Implement Associative Memory
• Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
• Physics-informed data based neural networks for two-dimensional turbulence
• Delay Aware Intelligent Transient Stability Assessment System
• OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
• On denoising autoencoders trained to minimise binary cross-entropy
• BASE Layers: Simplifying Training of Large, Sparse Models
• MegaDepth: Learning Single-View Depth Prediction from Internet Photos
• MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer
• Learning Natural Language Inference with LSTM
• Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM
• FPGA-accelerated machine learning inference as a service for particle physics computing
• Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning
• Privacy-preserving Federated Brain Tumour Segmentation
• Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning
• Unsupervised Translation of Programming Languages
• ABCDisCo: Automating the ABCD Method with Machine Learning
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
• Graph Neural Ordinary Differential Equations
• Decay Replay Mining to Predict Next Process Events
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate
• Neural Error Mitigation of Near-Term Quantum Simulations
• Visual Attention Network for Low Dose CT
• Greenhouse Gas Emission Prediction on Road Network using Deep Sequence Learning
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward
• SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks
• A deep Convolutional Neural Network for topology optimization with strong generalization ability
• Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRI
• Physically Interpretable Machine Learning for nuclear masses
• EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
• Statistical post-processing of wind speed forecasts using convolutional neural networks
• When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark
• User-Centric Conversational Recommendation with Multi-Aspect User Modeling
• C-VTON: Context-Driven Image-Based Virtual Try-On Network
• Deep learning for multimessenger core-collapse supernova detection
• Controlling Neural Level Sets
• Learning Deep Representations of Medical Images using Siamese CNNs with Application to Content-Based Image Retrieval
• Extracting full-field subpixel structural displacements from videos via deep learning
• Learning to Amend Facial Expression Representation via De-albino and Affinity
• Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics
• PDE-based Group Equivariant Convolutional Neural Networks
• Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
• PS1-STRM: Neural network source classification and photometric redshift catalogue for PS1 $3\pi$ DR1
• SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
• Three-dimensional Coherent X-ray Diffraction Imaging via Deep Convolutional Neural Networks
• TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
• Unsupervised Object Segmentation by Redrawing
• 6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning
• Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
• SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network
• Prediction of local elasto-plastic stress and strain fields in a two-phase composite microstructure using a deep convolutional neural network
• PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
• ZeRO-Offload: Democratizing Billion-Scale Model Training
• Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification
• FlauBERT: Unsupervised Language Model Pre-training for French
• Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus
• Supervised Learning with Projected Entangled Pair States
• Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
• PoNA: Pose-guided Non-local Attention for Human Pose Transfer
• Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs
• DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
• A Machine-learning framework for automatic reference-free quality assessment in MRI
• J-PLUS: Identification of low-metallicity stars with artificial neural networks using SPHINX
• Gated Fusion Network for Single Image Dehazing
• Feasibility Study of Neural ODE and DAE Modules for Power System Dynamic Component Modeling
• Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
• Improving Outfit Recommendation with Co-supervision of Fashion Generation
• Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version
• Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks
• A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
• Seabed classification using physics-based modeling and machine learning
• Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
• Deep Learning Prediction of Adverse Drug Reactions Using Open TG-GATEs and FAERS Databases
• Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes
• Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages
• A report on sound event detection with different binaural features
• On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation
• Learning the Multiple Traveling Salesmen Problem with Permutation Invariant Pooling Networks
• HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Towards the Limit of Network Quantization
• Online Service Migration in Mobile Edge with Incomplete System Information: A Deep Recurrent Actor-Critic Learning Approach
• Controllable Invariance through Adversarial Feature Learning
• Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
• PANNA: Properties from Artificial Neural Network Architectures
• A Convolutional Encoder Model for Neural Machine Translation
• Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization
• Local Spectral Graph Convolution for Point Set Feature Learning
• A Hybrid Model and Learning-Based Adaptive Navigation Filter
• Learning and Querying Fast Generative Models for Reinforcement Learning
• Quantum Graph Neural Networks
• Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
• Real-time Convolutional Neural Networks for Emotion and Gender Classification
• Queueing Network Controls via Deep Reinforcement Learning
• FIGR: Few-shot Image Generation with Reptile
• Dynamic Evaluation of Neural Sequence Models
• Quark-Gluon Tagging: Machine Learning vs Detector
• Detection and Parameter Estimation of Gravitational Waves from Binary Neutron-Star Mergers in Real LIGO Data using Deep Learning
• Convolutional Sketch Inversion
• Machine learning for music genre: multifaceted review and experimentation with audioset
• DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network
• SiFall: Practical Online Fall Detection with RF Sensing
• Data-driven topology design using a deep generative model
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• Flight Time Prediction for Fuel Loading Decisions with a Deep Learning Approach
• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization
• You Only Train Once: Learning a General Anomaly Enhancement Network with Random Masks for Hyperspectral Anomaly Detection
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
• Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference
• Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Fast and Accurate Single Image Super-Resolution via Information Distillation Network
• Learned Image Coding for Machines: A Content-Adaptive Approach
• Measuring the Intrinsic Dimension of Objective Landscapes
• EDITH :ECG biometrics aided by Deep learning for reliable Individual auTHentication
• A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM
• Dual Adversarial Auto-Encoders for Clustering
• Combining distribution-based neural networks to predict weather forecast probabilities
• You Only Learn Once: Universal Anatomical Landmark Detection
• Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
• Robust Grasp Planning Over Uncertain Shape Completions
• RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
• MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data
• Physics-informed deep generative models
• Deep Learning Approach for Building Detection in Satellite Multispectral Imagery
• MRzero -- Fully automated discovery of MRI sequences using supervised learning
• Unified Automatic Control of Vehicular Systems with Reinforcement Learning
• On Multiplicative Integration with Recurrent Neural Networks
• Conditional physics informed neural networks
• Improved Multiple-Image-Based Reflection Removal Algorithm Using Deep Neural Networks
• Deep Feature Space: A Geometrical Perspective
• Convolutional Recurrent Neural Networks for Music Classification
• AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabulary
• Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
• Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow
• Towards better decoding and language model integration in sequence to sequence models
• Memorize or generalize? Searching for a compositional RNN in a haystack
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• Excessive Invariance Causes Adversarial Vulnerability
• Bluff body uses deep-reinforcement-learning trained active flow control to achieve hydrodynamic stealth
• RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
• $\Delta$-PINNs: physics-informed neural networks on complex geometries
• Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation
• IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
• AutoMLP: Automated MLP for Sequential Recommendations
• Analysis and Optimization of Convolutional Neural Network Architectures
• GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression
• Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
• Machine Learning in NextG Networks via Generative Adversarial Networks
• Invariance-Preserving Localized Activation Functions for Graph Neural Networks
• The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
• Edge and Identity Preserving Network for Face Super-Resolution
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• A Progressive Batching L-BFGS Method for Machine Learning
• FRnet-DTI: Deep Convolutional Neural Networks with Evolutionary and Structural Features for Drug-Target Interaction
• Dynamical learning of dynamics
• Learning curves of generic features maps for realistic datasets with a teacher-student model
• Learning Detail-Structure Alternative Optimization for Blind Super-Resolution
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Towards vision-based robotic skins: a data-driven, multi-camera tactile sensor
• Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks
• Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
• Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments
• Operator Variational Inference
• Generative model benchmarks for superconducting qubits
• Multiple-Human Parsing in the Wild
• $\mathbf{\gamma }$-Net: Superresolving SAR Tomographic Inversion via Deep Learning
• DLBI: Deep learning guided Bayesian inference for structure reconstruction of super-resolution fluorescence microscopy
• BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing
• Fusion approaches for emotion recognition from speech using acoustic and text-based features
• Modeling the effect of the vaccination campaign on the Covid-19 pandemic
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
• Near-Optimal Sparse Allreduce for Distributed Deep Learning
• Deep Lattice Networks and Partial Monotonic Functions
• Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
• On Loss Functions for Deep Neural Networks in Classification
• The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification
• Multimodal Brain-Computer Interface for In-Vehicle Driver Cognitive Load Measurement: Dataset and Baselines
• Unseen Class Discovery in Open-world Classification
• Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
• Thermodynamics-informed graph neural networks
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
• Attack-Resistant Federated Learning with Residual-based Reweighting
• A Game Theoretic Framework for Model Based Reinforcement Learning
• VAE with a VampPrior
• One for Many: Transfer Learning for Building HVAC Control
• Task Agnostic Continual Learning via Meta Learning
• Edge Deep Learning for Neural Implants
• Quality-aware Selective Fusion Network for V-D-T Salient Object Detection
• Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
• Novel Deep Learning Architecture for Heart Disease Prediction using Convolutional Neural Network
• Code Search based on Context-aware Code Translation
• SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries
• Imposing Hard Constraints on Deep Networks: Promises and Limitations
• Search for pair production of heavy vector-like quarks decaying into hadronic final states in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• SRECG: ECG Signal Super-resolution Framework for Portable/Wearable Devices in Cardiac Arrhythmias Classification
• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• CNN-Based Deep Learning in Solar Wind Forecasting
• Digital holographic particle volume reconstruction using a deep neural network
• Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
• Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
• A deep neural network to search for new long-lived particles decaying to jets
• Learned Visual Navigation for Under-Canopy Agricultural Robots
• Accurate emulator for the redshift-space power spectrum of dark matter halos and its application to galaxy power spectrum
• Customer Lifetime Value in Video Games Using Deep Learning and Parametric Models
• AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
• A Joint Model for IT Operation Series Prediction and Anomaly Detection
• StructureFlow: Image Inpainting via Structure-aware Appearance Flow
• Detection of Face Recognition Adversarial Attacks
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units
• Evaluating machine learning techniques for predicting power spectra from reionization simulations
• Energy-based Graph Convolutional Networks for Scoring Protein Docking Models
• Optimizing Sparse RFI Prediction using Deep Learning
• Inference of the optical depth to reionization from low multipole temperature and polarisation Planck data
• Model-Parallel Fourier Neural Operators as Learned Surrogates for Large-Scale Parametric PDEs
• STD: Sparse-to-Dense 3D Object Detector for Point Cloud
• Estimating time-dependent entropy production from non-equilibrium trajectories
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• A Reinforcement Learning approach for Quantum State Engineering
• Dynamic Neural Program Embedding for Program Repair
• A Graph Autoencoder Approach to Causal Structure Learning
• TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation
• Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
• Deep Learning for Patient-Specific Kidney Graft Survival Analysis
• Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
• Advance Warning Methodologies for COVID-19 using Chest X-Ray Images
• Deep Semantic Segmentation in an AUV for Online Posidonia Oceanica Meadows identification
• Measurement of differential $\text{t}\overline{\text{t}}$ production cross sections in the full kinematic range using lepton+jets events from proton-proton collisions at $\sqrt{s}=$ 13 TeV
• S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Object-Centric Neural Scene Rendering
• Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• XNMT: The eXtensible Neural Machine Translation Toolkit
• PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
• View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
• Unsupervised Learning with Stein's Unbiased Risk Estimator
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
• Graph Communal Contrastive Learning
• Tensor-Train Recurrent Neural Networks for Video Classification
• WNGrad: Learn the Learning Rate in Gradient Descent
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• Recurrent Batch Normalization
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Reading Scene Text with Attention Convolutional Sequence Modeling
• Real-time System Identification Using Deep Learning for Linear Processes with Application to Unmanned Aerial Vehicles
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Uncertainty Aware Learning for High Energy Physics
• Transformer based Grapheme-to-Phoneme Conversion
• Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes
• Generalized Wasserstein Dice Score, Distributionally Robust Deep Learning, and Ranger for brain tumor segmentation: BraTS 2020 challenge
• Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
• Efficient texture-aware multi-GAN for image inpainting
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• A Memory-Network Based Solution for Multivariate Time-Series Forecasting
• Detecting hip fractures with radiologist-level performance using deep neural networks
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems
• Segmentation of histological images and fibrosis identification with a convolutional neural network
• Learning Generalized Spoof Cues for Face Anti-spoofing
• Multi-Stage Progressive Image Restoration
• On Learning Sets of Symmetric Elements
• Automated Pruning for Deep Neural Network Compression
• Learning What Data to Learn
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Theory and Experiments on Vector Quantized Autoencoders
• Physics-Informed Supervised Residual Learning for Electromagnetic Modeling
• Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery
• Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
• Latent-Graph Learning for Disease Prediction
• Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: simulations and experiments
• Learning by Association - A versatile semi-supervised training method for neural networks
• Predicting Yield Performance of Parents in Plant Breeding: A Neural Collaborative Filtering Approach
• Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
• Restricting the Flow: Information Bottlenecks for Attribution
• Learning With Context Feedback Loop for Robust Medical Image Segmentation
• Metrics for Deep Generative Models
• Global Sensitivity Analysis of Four Chamber Heart Hemodynamics Using Surrogate Models
• Linear Multiple Low-Rank Kernel Based Stationary Gaussian Processes Regression for Time Series
• Soft-Demapping for Short Reach Optical Communication: A Comparison of Deep Neural Networks and Volterra Series
• High Accuracy and High Fidelity Extraction of Neural Networks
• MoDL-MUSSELS: Model-Based Deep Learning for Multi-Shot Sensitivity Encoded Diffusion MRI
• Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations
• Predicting Temporal Sets with Deep Neural Networks
• A Spatio-Temporal Spot-Forecasting Framework for Urban Traffic Prediction
• Strong error analysis for stochastic gradient descent optimization algorithms
• Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
• SGM: Sequence Generation Model for Multi-label Classification
• Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
• Benchmarking of Different Optimizers in the Variational Quantum Algorithms for Applications in Quantum Chemistry
• DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning
• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media
• Deblending galaxy superpositions with branched generative adversarial networks
• Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
• Continuous sign language recognition from wearable IMUs using deep capsule networks and game theory
• PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
• Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• Dynamic Instance Domain Adaptation
• Multiple-Attribute Text Style Transfer
• Learning Algorithms for Active Learning
• Convolutional Radio Modulation Recognition Networks
• Real-time 3D Nanoscale Coherent Imaging via Physics-aware Deep Learning
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
• Natural Language Instructions for Intuitive Human Interaction with Robotic Assistants in Field Construction Work
• Forward and Reverse Gradient-Based Hyperparameter Optimization
• Neural Network Augmented Physics Models for Systems with Partially Unknown Dynamics: Application to Slider-Crank Mechanism
• Predicting atmospheric optical properties for radiative transfer computations using neural networks
• A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
• Pseudo-healthy synthesis with pathology disentanglement and adversarial learning
• Multi-Objective Bayesian Optimization for Accelerator Tuning
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• Intelligent real-time MEMS sensor fusion and calibration
• Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations
• Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI
• Fast and accurate waveform modeling of long-haul multi-channel optical fiber transmission using a hybrid model-data driven scheme
• Neural Expectation Maximization
• Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
• A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction
• EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
• Residual Policy Learning
• Digital rock reconstruction with user-defined properties using conditional generative adversarial networks
• Multi-Sample Dropout for Accelerated Training and Better Generalization
• Automatic registration with continuous pose updates for marker-less surgical navigation in spine surgery
• 3D Densely Convolutional Networks for Volumetric Segmentation
• Learning from synthetic photorealistic raindrop for single image raindrop removal
• Traffic Data Imputation using Deep Convolutional Neural Networks
• Compressed Domain Image Classification Using a Dynamic-Rate Neural Network
• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
• Shampoo: Preconditioned Stochastic Tensor Optimization
• Multi-Generator Generative Adversarial Nets
• Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
• Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
• SODFormer: Streaming Object Detection with Transformer Using Events and Frames
• FiNER: Financial Numeric Entity Recognition for XBRL Tagging
• A Context-aware Natural Language Generator for Dialogue Systems
• Colorization as a Proxy Task for Visual Understanding
• Contrastive Graph Pooling for Explainable Classification of Brain Networks
• The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
• Adaptive Attribute and Structure Subspace Clustering Network
• Binary MIMO Detection via Homotopy Optimization and Its Deep Adaptation
• SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
• DIODE: A Dense Indoor and Outdoor DEpth Dataset
• Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)
• autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients
• Deep Predictive Coding Network for Object Recognition
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Conformalized Quantile Regression
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Constrained Bayesian Optimization for Automatic Chemical Design
• Image quality assessment for machine learning tasks using meta-reinforcement learning
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• Unsupervised clustering for collider physics
• FISHING Net: Future Inference of Semantic Heatmaps In Grids
• Neural Network Reconstruction of Late-Time Cosmology and Null Tests
• Convolutional Neural Networks for Multispectral Image Cloud Masking
• A Physics-Informed Neural Network approach for compartmental epidemiological models
• Counting to Explore and Generalize in Text-based Games
• Gait recognition via deep learning of the center-of-pressure trajectory
• TBC-Net: A real-time detector for infrared small target detection using semantic constraint
• Forecasting Megaelectron-Volt Electrons inside Earth's Outer Radiation Belt: PreMevE 2.0 Based on Supervised Machine Learning Algorithms
• Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
• Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization
• Development and Evaluation of Recurrent Neural Network based Models for Hourly Traffic Volume and AADT Prediction
• Language learning using Speech to Image retrieval
• Adaptive deep density approximation for Fokker-Planck equations
• Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
• SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
• Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
• Deep reinforcement learning for quantum multiparameter estimation
• Scalable Neural Network Decoders for Higher Dimensional Quantum Codes
• Multi-fidelity modeling with different input domain definitions using Deep Gaussian Processes
• Learning macroscopic internal variables and history dependence from microscopic models
• DeepWarp: DNN-based Nonlinear Deformation
• Mean flow data assimilation based on physics-informed neural networks
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
• Deep Reinforcement Learning in Parameterized Action Space
• SVD Perspectives for Augmenting DeepONet Flexibility and Interpretability
• Stochastic Answer Networks for Natural Language Inference
• It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality
• Universal Domain Adaptation for Remote Sensing Image Scene Classification
• Generative Modeling of Turbulence
• Time2Vec: Learning a Vector Representation of Time
• Improvement of Performance in Freezing of Gait detection in Parkinsons Disease using Transformer networks and a single waist worn triaxial accelerometer
• Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
• Independently Controllable Factors
• Deferred Neural Rendering: Image Synthesis using Neural Textures
• Conditional Neural Processes
• Separable DeepONet: Breaking the Curse of Dimensionality in Physics-Informed Machine Learning
• Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation
• Online Learning With Adaptive Rebalancing in Nonstationary Environments
• A differentiable programming method for quantum control
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
• xQSM: Quantitative Susceptibility Mapping with Octave Convolutional and Noise Regularized Neural Networks
• Universal Effectiveness of High-Depth Circuits in Variational Eigenproblems
• Deep learning-based development of personalized human head model with non-uniform conductivity for brain stimulation
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses
• Learning to swim in potential flow
• Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation
• Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
• Skin cancer detection based on deep learning and entropy to detect outlier samples
• Joint Design of Measurement Matrix and Sparse Support Recovery Method via Deep Auto-encoder
• Automated detection of vulnerable plaque in intravascular ultrasound images
• Graph-MLP: Node Classification without Message Passing in Graph
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU
• Graph Partition Neural Networks for Semi-Supervised Classification
• Towards duration robust weakly supervised sound event detection
• SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images
• Video Swin Transformer
• Learning nonlocal constitutive models with neural networks
• RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
• NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
• Learning the Relationship between Galaxies Spectra and their Star Formation Histories using Convolutional Neural Networks and Cosmological Simulations
• Video Semantic Segmentation with Distortion-Aware Feature Correction
• What shapes feature representations? Exploring datasets, architectures, and training
• Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography
• Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
• Adversarial Dropout Regularization
• Generative Discovery of Novel Chemical Designs using Diffusion Modeling and Transformer Deep Neural Networks with Application to Deep Eutectic Solvents
• Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing
• Compressive Transformers for Long-Range Sequence Modelling
• CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference
• Head2Head++: Deep Facial Attributes Re-Targeting
• Performance Analysis and Dynamic Evolution of Deep Convolutional Neural Network for Nonlinear Inverse Scattering
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• A data-driven peridynamic continuum model for upscaling molecular dynamics
• The Photometric Metallicity and Carbon Distributions of the Milky Way's Halo and Solar Neighborhood from S-PLUS Observations of SDSS Stripe 82
• Deformation-Aware Robotic 3D Ultrasound
• Unsupervised Heterogeneous Coupling Learning for Categorical Representation
• Emergent Translation in Multi-Agent Communication
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• On the State of the Art of Evaluation in Neural Language Models
• Seeing with Humans: Gaze-Assisted Neural Image Captioning
• KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
• Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
• MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
• Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation
• Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
• StereoSpike: Depth Learning with a Spiking Neural Network
• Deep convolutional neural networks for multi-planar lung nodule detection: improvement in small nodule identification
• Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
• Recurrent Neural Networks With Limited Numerical Precision
• Learning text representation using recurrent convolutional neural network with highway layers
• Hermite-Gaussian Mode Detection via Convolution Neural Networks
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Limits of End-to-End Learning
• AutoEmbedder: A semi-supervised DNN embedding system for clustering
• Three Mechanisms of Weight Decay Regularization
• Continuous and Distribution-free Probabilistic Wind Power Forecasting: A Conditional Normalizing Flow Approach
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Complex-valued neural networks for machine learning on non-stationary physical data
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• "No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy
• Self-supervised Consensus Representation Learning for Attributed Graph
• Identifying Emotions from Walking using Affective and Deep Features
• Facial-Sketch Synthesis: A New Challenge
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics
• A Robust Comparison of the KDDCup99 and NSL-KDD IoT Network Intrusion Detection Datasets Through Various Machine Learning Algorithms
• Phasic Policy Gradient
• Prototype-Guided Memory Replay for Continual Learning
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Variational auto-encoding of protein sequences
• GRAINS: Generative Recursive Autoencoders for INdoor Scenes
• Deep Multi-Task Learning for Malware Image Classification
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Video Storytelling: Textual Summaries for Events
• Dealing with Sparse Rewards in Reinforcement Learning
• Classification of Point Cloud Scenes with Multiscale Voxel Deep Network
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Deep multi-survey classification of variable stars
• Neural system identification for large populations separating "what" and "where"
• Image-based material characterization of complex microarchitectured additively manufactured structures
• Cross-Market Product Recommendation
• Be Your Own Prada: Fashion Synthesis with Structural Coherence
• Relational Graph Attention Network for Aspect-based Sentiment Analysis
• An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
• Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
• Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
• Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Geometrically-Shaped Multi-Dimensional Modulation Formats in Coherent Optical Transmission Systems
• Explaining Latent Factor Models for Recommendation with Influence Functions
• Attribute Artifacts Removal for Geometry-based Point Cloud Compression
• Predicting the Mechanical Properties of Biopolymer Gels Using Neural Networks Trained on Discrete Fiber Network Data
• Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
• Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
• Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
• s-LWSR: Super Lightweight Super-Resolution Network
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• Neural Airport Ground Handling
• Deep Counterfactual Networks with Propensity-Dropout
• Hierarchical Memory Networks
• Neural Vocoder is All You Need for Speech Super-resolution
• Search for electroweak production of charginos and neutralinos in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale
• Multilingual Hierarchical Attention Networks for Document Classification
• Revisiting Efficient Multi-Step Nonlinearity Compensation with Machine Learning: An Experimental Demonstration
• Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT
• Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
• Deep Learning Based Packet Detection and Carrier Frequency Offset Estimation in IEEE 802.11ah
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks
• LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers
• STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
• Music Genre Classification using Machine Learning Techniques
• Emotional Speaker Identification using a Novel Capsule Nets Model
• Presenting Unbinned Differential Cross Section Results
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Hierarchical Convolutional Neural Network with Feature Preservation and Autotuned Thresholding for Crack Detection
• Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
• Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)
• Dynamic Prediction of ICU Mortality Risk Using Domain Adaptation
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Deep Learning for Symbolic Mathematics
• Adaptive network reliability analysis: Methodology and applications to power grid
• Diffractive deep neural network based adaptive optics scheme for vortex beam in oceanic turbulence
• A Multimodal Framework for the Detection of Hateful Memes
• Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques
• Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
• QKD: Quantization-aware Knowledge Distillation
• Quantum Machine Learning for Finance
• Two Stage Transformer Model for COVID-19 Fake News Detection and Fact Checking
• Training behavior of deep neural network in frequency domain
• Characterizing the Decision Boundary of Deep Neural Networks
• Advances in Quantum Deep Learning: An Overview
• Image Captioning at Will: A Versatile Scheme for Effectively Injecting Sentiments into Image Descriptions
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction
• Deep Learning for Channel Sensing and Hybrid Precoding in TDD Massive MIMO OFDM Systems
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• A Survey on State-of-the-art Deep Learning Applications and Challenges
• Deep embedded clustering of coral reef bioacoustics
• Adaptive Optics control using Model-Based Reinforcement Learning
• Computational Optics for Mobile Terminals in Mass Production
• Towards Semi-supervised Universal Graph Classification
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Equivariant Energy Flow Networks for Jet Tagging
• Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
• Compute and memory efficient universal sound source separation
• End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN
• GeniePath: Graph Neural Networks with Adaptive Receptive Paths
• A Hybrid Convolutional Variational Autoencoder for Text Generation
• Neural Networks Trained to Solve Differential Equations Learn General Representations
• Wide-Baseline Relative Camera Pose Estimation with Directional Learning
• Dynamic Occupancy Grid Mapping with Recurrent Neural Networks
• Low-temperature plasma simulation based on physics-informed neural networks: frameworks and preliminary applications
• Deep Reinforcement Learning for Sepsis Treatment
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation
• Computer-Aided Diagnosis of Label-Free 3-D Optical Coherence Microscopy Images of Human Cervical Tissue
• CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
• Neural networks in pulsed dipolar spectroscopy: a practical guide
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• Universal Neural Machine Translation for Extremely Low Resource Languages
• Deep Learning Stock Volatility with Google Domestic Trends
• ShapeWorld - A new test methodology for multimodal language understanding
• I-MAD: Interpretable Malware Detector Using Galaxy Transformer
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• Language Models with Transformers
• Model Selection in Bayesian Neural Networks via Horseshoe Priors
• Accelerating SGD with momentum for over-parameterized learning
• Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder
• deepMiRGene: Deep Neural Network based Precursor microRNA Prediction
• Prescribed Generative Adversarial Networks
• ShuffleSeg: Real-time Semantic Segmentation Network
• Neural Network aided quarantine control model estimation of global Covid-19 spread
• Identifying WIMP dark matter from particle and astroparticle data
• Cross-Lingual Machine Reading Comprehension
• Unsupervised Text Style Transfer using Language Models as Discriminators
• Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification
• ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users
• MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
• High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
• Deep learning-based statistical noise reduction for multidimensional spectral data
• Combined searches for the production of supersymmetric top quark partners in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Federated and Differentially Private Learning for Electronic Health Records
• Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
• Reweighted Proximal Pruning for Large-Scale Language Representation
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference
• Fast solver for J2-perturbed Lambert problem using deep neural network
• Principle-driven Fiber Transmission Model based on PINN Neural Network
• Missing Data Imputation using Optimal Transport
• Joint Embedding of Words and Labels for Text Classification
• Deep Learning-Guided Image Reconstruction from Incomplete Data
• Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
• Photonic convolutional neural networks using integrated diffractive optics
• Plug-and-Play Regulators for Image-Text Matching
• PoreNet: CNN-based Pore Descriptor for High-resolution Fingerprint Recognition
• NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles
• ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps
• DeepTrend: A Deep Hierarchical Neural Network for Traffic Flow Prediction
• Optimization of data-driven filterbank for automatic speaker verification
• Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems
• End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
• Early Diagnosis of Pneumonia with Deep Learning
• Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning
• Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition
• Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems
• Via Machinae: Searching for Stellar Streams using Unsupervised Machine Learning
• DNN driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation
• Industrial object, machine part and defect recognition towards fully automated industrial monitoring employing deep learning. The case of multilevel VGG19
• Attentional Graph Neural Network for Parking-slot Detection
• Learning Based User Scheduling in Reconfigurable Intelligent Surface Assisted Multiuser Downlink
• Learning-Based Real-Time Event Identification Using Rich Real PMU Data
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• Finite Element Network Analysis: A Machine Learning based Computational Framework for the Simulation of Physical Systems
• Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation
• FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
• Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• Lung Segmentation from Chest X-rays using Variational Data Imputation
• Semantic Segmentation Using Deep Learning to Extract Total Extraocular Muscles and Optic Nerve from Orbital Computed Tomography Images
• Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
• Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
• Sim2Real View Invariant Visual Servoing by Recurrent Control
• Machine-learning free-energy functionals using density profiles from simulations
• Contrastive Variational Autoencoder Enhances Salient Features
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
• NR-RRT: Neural Risk-Aware Near-Optimal Path Planning in Uncertain Nonconvex Environments
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
• Indoor environment data time-series reconstruction using autoencoder neural networks
• Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks
• The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
• Feedback alignment in deep convolutional networks
• Per-Object Systematics using Deep-Learned Calibration
• Bayesian Physics-Informed Neural Networks for the Subsurface Tomography based on the Eikonal Equation
• Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
• Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
• Super-resolution data assimilation
• Deep Slow Motion Video Reconstruction with Hybrid Imaging System
• Deep learning for thermal plasma simulation: solving 1-D arc model as an example
• Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
• Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networks
• Lesion Segmentation in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
• Phocas: dimensional Byzantine-resilient stochastic gradient descent
• MatFormer: A Generative Model for Procedural Materials
• Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge
• A Multi-view CNN-based Acoustic Classification System for Automatic Animal Species Identification
• SurvTRACE: Transformers for Survival Analysis with Competing Events
• Automatic Expert Selection for Multi-Scenario and Multi-Task Search
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Memory Augmented Neural Networks with Wormhole Connections
• Adorym: A multi-platform generic x-ray image reconstruction framework based on automatic differentiation
• Speech enhancement with variational autoencoders and alpha-stable distributions
• Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
• DNA-Level Splice Junction Prediction using Deep Recurrent Neural Networks
• Inverse design of plasma metamaterial devices for optical computing
• Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties
• Learning Approximate Inference Networks for Structured Prediction
• Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts
• CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator
• A Deep Reinforcement Learning Framework for Contention-Based Spectrum Sharing
• Attend and Diagnose: Clinical Time Series Analysis using Attention Models
• Learning Part Boundaries from 3D Point Clouds
• A Combined Machine-Learning / Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces
• A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Finding
• Privacy-Protective-GAN for Face De-identification
• Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
• Recommender systems based on graph embedding techniques: A comprehensive review
• Generating Multi-Categorical Samples with Generative Adversarial Networks
• Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces
• Underwater-Art: Expanding Information Perspectives With Text Templates For Underwater Acoustic Target Recognition
• HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
• A Geometric Analysis of Neural Collapse with Unconstrained Features
• Longitudinal Speech Biomarkers for Automated Alzheimer's Detection
• Heatmap Regression via Randomized Rounding
• Learning Neural Causal Models from Unknown Interventions
• Efficient Image Super-Resolution Using Pixel Attention
• The Mirage of Action-Dependent Baselines in Reinforcement Learning
• Deep Video Deblurring
• Dropout-based Active Learning for Regression
• Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks
• Detection of False Data Injection Attacks Using the Autoencoder Approach
• Probabilistic Binary Neural Networks
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
• Systematically Measuring Ultra-Diffuse Galaxies (SMUDGes). II. Expanded Survey Description and the Stripe 82 Catalog
• Fluctuation-dissipation relations for stochastic gradient descent
• Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
• Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
• What Makes Multi-modal Learning Better than Single (Provably)
• Conditional Variational Autoencoder for Neural Machine Translation
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Deep Robust Clustering by Contrastive Learning
• Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition
• Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer's Disease using structural MR and FDG-PET images
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
• Scale-Equivariant Steerable Networks
• ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
• Emergent Communication through Negotiation
• Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
• Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
• Code-Switching for Enhancing NMT with Pre-Specified Translation
• Onsets and Frames: Dual-Objective Piano Transcription
• CherryPicker: Semantic Skeletonization and Topological Reconstruction of Cherry Trees
• Precise Repositioning of Robotic Ultrasound: Improving Registration-based Motion Compensation using Ultrasound Confidence Optimization
• Charagram: Embedding Words and Sentences via Character n-grams
• Crowding Reveals Fundamental Differences in Local vs. Global Processing in Humans and Machines
• Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)
• An extended physics informed neural network for preliminary analysis of parametric optimal control problems
• Revisiting Video Saliency: A Large-scale Benchmark and a New Model
• Deep learning with self-supervision and uncertainty regularization to count fish in underwater images
• Gradient Starvation: A Learning Proclivity in Neural Networks
• Convolutional Neural Networks and a Transfer Learning Strategy to Classify Parkinson's Disease from Speech in Three Different Languages
• d3rlpy: An Offline Deep Reinforcement Learning Library
• Low-field magnetic resonance image enhancement via stochastic image quality transfer
• Self-supervised transfer learning of physiological representations from free-living wearable data
• End-to-end training of time domain audio separation and recognition
• Effective Strategies in Zero-Shot Neural Machine Translation
• Search for black hole hyperbolic encounters with gravitational wave detectors
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Whitening for Self-Supervised Representation Learning
• Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates
• Parallel Attention Network with Sequence Matching for Video Grounding
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
• ClearBuds: Wireless Binaural Earbuds for Learning-Based Speech Enhancement
• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• Convolutional neural networks that teach microscopes how to image
• Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
• MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection
• A Model-Agnostic Causal Learning Framework for Recommendation using Search Data
• Deep Iterative and Adaptive Learning for Graph Neural Networks
• DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection
• Deep Weighted Averaging Classifiers
• Massive MIMO Adaptive Modulation and Coding Using Online Deep Learning Algorithm
• Maximum Entropy Subspace Clustering Network
• Learning macroscopic parameters in nonlinear multiscale simulations using nonlocal multicontinua upscaling techniques
• A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
• Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
• Attention U-Net as a surrogate model for groundwater prediction
• Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language
• Unsupervised Speech Decomposition via Triple Information Bottleneck
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
• Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
• Estimation of groundwater storage from seismic data using deep learning
• Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
• Streaming end-to-end multi-talker speech recognition
• Fast-Slow Recurrent Neural Networks
• Action2Vec: A Crossmodal Embedding Approach to Action Learning
• Clue: Cross-modal Coherence Modeling for Caption Generation
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments
• Tackling Over-pruning in Variational Autoencoders
• Learning the Effect of Registration Hyperparameters with HyperMorph
• Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
• Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
• From Lost to Found: Discover Missing UI Design Semantics through Recovering Missing Tags
• FedMSE: Semi-supervised federated learning approach for IoT network intrusion detection
• Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-Network
• A simple and efficient architecture for trainable activation functions
• Denoising Autoencoders for Overgeneralization in Neural Networks
• METER: a mobile vision transformer architecture for monocular depth estimation
• Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• End-to-End Eye Movement Detection Using Convolutional Neural Networks
• Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches
• EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia
• Robust Training of Vector Quantized Bottleneck Models
• Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
• Watermarking Graph Neural Networks by Random Graphs
• Distortion-aware Monocular Depth Estimation for Omnidirectional Images
• MDA GAN: Adversarial-Learning-based 3-D Seismic Data Interpolation and Reconstruction for Complex Missing
• Using Deep Learning to Localize Gravitational Wave Sources
• Deep Learning Criminal Networks
• AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption
• Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
• Relative Entropy Regularized Policy Iteration
• Reinforcement Learning with Prototypical Representations
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• A Selective Overview of Deep Learning
• Deep Energy Estimator Networks
• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Joint Entity Extraction and Assertion Detection for Clinical Text
• Generating Multivariate Load States Using a Conditional Variational Autoencoder
• Temporal Consistency Learning of inter-frames for Video Super-Resolution
• Deep Learning with Functional Inputs
• Improving Social Awareness Through DANTE: A Deep Affinity Network for Clustering Conversational Interactants
• Clinical Concept Extraction with Contextual Word Embedding
• Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
• UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Quiver Mutations, Seiberg Duality and Machine Learning
• Speech Prediction using an Adaptive Recurrent Neural Network with Application to Packet Loss Concealment
• Adversarial Patch Attacks on Monocular Depth Estimation Networks
• Scenario-based Nonlinear Model Predictive Control for Building Heating Systems
• Accelerated Coronary MRI with sRAKI: A Database-Free Self-Consistent Neural Network k-space Reconstruction for Arbitrary Undersampling
• Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
• Learning perturbation sets for robust machine learning
• Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
• Graph Neural Networks for Graph Drawing
• An XAI framework for robust and transparent data-driven wind turbine power curve models
• Fast and Scalable Human Pose Estimation using mmWave Point Cloud
• Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles
• Annotating Object Instances with a Polygon-RNN
• Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network
• ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots
• DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
• Training machine-learning potentials for crystal structure prediction using disordered structures
• Multi-class quantum classifiers with tensor network circuits for quantum phase recognition
• Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
• Tree-structured multi-stage principal component analysis (TMPCA): theory and applications
• Inductive Bias of Deep Convolutional Networks through Pooling Geometry
• Acoustic Scene Classification with Squeeze-Excitation Residual Networks
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• PocketNet: A Smaller Neural Network for Medical Image Analysis
• Learning to Evolve Structural Ensembles of Unfolded and Disordered Proteins Using Experimental Solution Data
• Comparing machine learning techniques for predicting glassy dynamics
• No-Reference Image Quality Assessment by Hallucinating Pristine Features
• PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks
• Improved training of binary networks for human pose estimation and image recognition
• Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem
• Learning to Paint With Model-based Deep Reinforcement Learning
• Deep Learning-based Prediction of Key Performance Indicators for Electrical Machine
• Integrating production scheduling and process control using latent variable dynamic models
• Detecting Outliers with Foreign Patch Interpolation
• LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar
• Component Segmentation of Engineering Drawings Using Graph Convolutional Networks
• Bounding Box Tightness Prior for Weakly Supervised Image Segmentation
• BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis
• Complex dynamics on the one-dimensional quantum droplets via time piecewise PINNs
• Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction
• Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
• Generative Temporal Models with Memory
• FENet: A Frequency Extraction Network for Obstructive Sleep Apnea Detection
• Uncertainty Averse Pushing with Model Predictive Path Integral Control
• Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
• Distilling Knowledge from Reader to Retriever for Question Answering
• WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
• Extracting quantitative biological information from brightfield cell images using deep learning
• Deep Idempotent Network for Efficient Single Image Blind Deblurring
• Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition
• Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos
• List-Mode PET Image Reconstruction Using Deep Image Prior
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
• Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
• Extensible Structure-Informed Prediction of Formation Energy with Improved Accuracy and Usability employing Neural Networks
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference
• Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
• Equivariant Hamiltonian Flows
• Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
• Cross-head Supervision for Crowd Counting with Noisy Annotations
• Robustness Verification of Quantum Classifiers
• Deep modeling of quasar variability
• Concussion classification via deep learning using whole-brain white matter fiber strains
• Predictive Collective Variable Discovery with Deep Bayesian Models
• Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
• An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation
• Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization
• A Discussion on Solving Partial Differential Equations using Neural Networks
• Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data
• DiNNO: Distributed Neural Network Optimization for Multi-Robot Collaborative Learning
• Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
• Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• Relational Graph Convolutional Networks: A Closer Look
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design
• Knowledge Distillation approach towards Melanoma Detection
• CASCADE: Contextual Sarcasm Detection in Online Discussion Forums
• Nuclear binding energy predictions using neural networks: Application of the multilayer perceptron
• Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization
• A Framework for Automated Cellular Network Tuning with Reinforcement Learning
• Neural Probabilistic Model for Non-projective MST Parsing
• Discrete and Continuous Action Representation for Practical RL in Video Games
• A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
• Pyramid Medical Transformer for Medical Image Segmentation
• Learning Regional Attraction for Line Segment Detection
• Patch-Based Deep Autoencoder for Point Cloud Geometry Compression
• O-MedAL: Online Active Deep Learning for Medical Image Analysis
• Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code
• End-to-End Speech-Driven Facial Animation with Temporal GANs
• Multimodal and multicontrast image fusion via deep generative models
• Interaction-and-Aggregation Network for Person Re-identification
• A Convolutional Neural Network Approach to the Classification of Engineering Models
• Sensor-Independent Illumination Estimation for DNN Models
• Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
• Plasma Surrogate Modelling using Fourier Neural Operators
• Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
• HOOV: Hand Out-Of-View Tracking for Proprioceptive Interaction using Inertial Sensing
• A Neural Entity Coreference Resolution Review
• Long-term Pedestrian Trajectory Prediction using Mutable Intention Filter and Warp LSTM
• A Tungsten Deep Neural-Network Potential for Simulating Mechanical Property Degradation Under Fusion Service Environment
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• On the Effectiveness of Transfer Learning for Code Search
• QFlow lite dataset: A machine-learning approach to the charge states in quantum dot experiments
• On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
• SALSA-Lite: A Fast and Effective Feature for Polyphonic Sound Event Localization and Detection with Microphone Arrays
• Dynamical mass inference of galaxy clusters with neural flows
• ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
• Coherent Online Video Style Transfer
• Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• Adversarial T-shirt! Evading Person Detectors in A Physical World
• $\text{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• Constrained Attractor Selection Using Deep Reinforcement Learning
• Single-shot 3D multi-person pose estimation in complex images
• A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units
• Evaluating prose style transfer with the Bible
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning
• Image Compression with Encoder-Decoder Matched Semantic Segmentation
• Anomalous Jet Identification via Sequence Modeling
• Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
• The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
• DECAF: Deep Extreme Classification with Label Features
• Classification and reconstruction of spatially overlapping phase images using diffractive optical networks
• Joint Slot Filling and Intent Detection via Capsule Neural Networks
• Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
• Reward learning from human preferences and demonstrations in Atari
• Ensemble learning in CNN augmented with fully connected subnetworks
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Regularizing Black-box Models for Improved Interpretability
• Sentence-State LSTM for Text Representation
• RANC: Reconfigurable Architecture for Neuromorphic Computing
• Application of Deep Learning to Sphere Decoding for Large MIMO Systems
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• Heterogeneous graph neural network for power allocation in multicarrier-division duplex cell-free massive MIMO systems
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Automated Defect Recognition of Castings defects using Neural Networks
• Learning Permutations with Sinkhorn Policy Gradient
• Scene-Aware Audio Rendering via Deep Acoustic Analysis
• CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
• DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
• Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube
• Proactive Autoscaling for Edge Computing Systems with Kubernetes
• BourGAN: Generative Networks with Metric Embeddings
• Structure-Preserving Super Resolution with Gradient Guidance
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• Joint Transmission Map Estimation and Dehazing using Deep Networks
• Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings
• A Convex Duality Framework for GANs
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging
• $\mathcal{X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing
• Batch Optimization of Frequency-Modulated Pulses for Robust Two-qubit Gates in Ion Chains
• Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement
• Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
• PyXtal FF: a Python Library for Automated Force Field Generation
• Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
• Graph Transformer for Graph-to-Sequence Learning
• SPP-Net: Deep Absolute Pose Regression with Synthetic Views
• Local minima in training of neural networks
• Data-aided Underwater Acoustic Ray Propagation Modeling
• End-to-end Alternating Optimization for Real-World Blind Super Resolution
• Learning to Learn from Weak Supervision by Full Supervision
• Time-series machine-learning error models for approximate solutions to parameterized dynamical systems
• An Alternative View: When Does SGD Escape Local Minima?
• Improving Efficiency in Convolutional Neural Network with Multilinear Filters
• Prompt-based Ingredient-Oriented All-in-One Image Restoration
• Identifying Generalization Properties in Neural Networks
• A Sensorless Control System for an Implantable Heart Pump using a Real-time Deep Convolutional Neural Network
• State estimation with limited sensors -- A deep learning based approach
• MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising
• Learning to Extend Molecular Scaffolds with Structural Motifs
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
• Learning to Inpaint for Image Compression
• Shortcut-Stacked Sentence Encoders for Multi-Domain Inference
• Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
• Recognizing Abnormal Heart Sounds Using Deep Learning
• Dimensionality Reduction using Similarity-induced Embeddings
• Sequence Modeling via Segmentations
• Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
• TasNet: time-domain audio separation network for real-time, single-channel speech separation
• Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Factorized Multimodal Transformer for Multimodal Sequential Learning
• Learning Lane Graph Representations for Motion Forecasting
• Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Understanding training and generalization in deep learning by Fourier analysis
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
• LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
• Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
• Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction
• Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks
• Latent Molecular Optimization for Targeted Therapeutic Design
• A Study of Neural Matching Models for Cross-lingual IR
• Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Forecasting Network-wide Traffic State with Missing Values
• Learning Depth with Convolutional Spatial Propagation Network
• U-Net: Machine Reading Comprehension with Unanswerable Questions
• NUBIA: NeUral Based Interchangeability Assessor for Text Generation
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
• Predicting the Time Until a Vehicle Changes the Lane Using LSTM-based Recurrent Neural Networks
• Photorealistic Style Transfer via Wavelet Transforms
• Pragmatic inference and visual abstraction enable contextual flexibility during visual communication
• CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation
• CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
• Multilinear Compressive Learning
• On the "steerability" of generative adversarial networks
• ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• Optimal transport mapping via input convex neural networks
• Exploiting Positional Information for Session-based Recommendation
• DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-based Robotic Grasping
• Watching the World Go By: Representation Learning from Unlabeled Videos
• Multimodal Attention for Neural Machine Translation
• Omnidirectional Video Super-Resolution using Deep Learning
• WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
• Ensemble Federated Learning: an approach for collaborative pneumonia diagnosis
• Continual Learning for Generative Retrieval over Dynamic Corpora
• Measurement of the radius dependence of charged-particle jet suppression in Pb-Pb collisions at $\sqrt{s_{\mathrm{NN}}}$ = 5.02 TeV
• 4D topology optimization: Integrated optimization of the structure and self-actuation of soft bodies for dynamic motions
• STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction
• Multi-scale Attentive Image De-raining Networks via Neural Architecture Search
• DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
• Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs
• Spatio-Temporal EEG Representation Learning on Riemannian Manifold and Euclidean Space
• Quarks and gluons in the Lund plane
• Learning to summarize from human feedback
• Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning
• Reinforcement learning-enhanced protocols for coherent population-transfer in three-level quantum systems
• Multi-Static UWB Radar-based Passive Human Tracking Using COTS Devices
• Exploring Overcomplete Representations for Single Image Deraining using CNNs
• F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement
• Deep Unsupervised Clustering Using Mixture of Autoencoders
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles
• Efficient and Modular Implicit Differentiation
• Multi-Label Contrastive Learning for Abstract Visual Reasoning
• DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
• Deep learning jet modifications in heavy-ion collisions
• Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement
• Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
• Reducing the complexity of chemical networks via interpretable autoencoders
• A Population-based Hybrid Approach to Hyperparameter Optimization for Neural Networks
• On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
• What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo
• IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
• Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
• TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
• PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel
• Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation
• Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
• MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction
• Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise
• Few-shot Domain Adaptation by Causal Mechanism Transfer
• GLYFE: Review and Benchmark of Personalized Glucose Predictive Models in Type-1 Diabetes
• Low-Memory Neural Network Training: A Technical Report
• Application of a variational hybrid quantum-classical algorithm to heat conduction equation
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• On-device Training: A First Overview on Existing Systems
• Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks
• Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?
• MSED: a multi-modal sleep event detection model for clinical sleep analysis
• Quantum Approximate Optimization Algorithm with Adaptive Bias Fields
• Two-stage 2D-to-3D reconstruction of realistic microstructures: Implementation and numerical validation by effective properties
• Learning to Generate Corrective Patches using Neural Machine Translation
• Learning Pair Potentials using Differentiable Simulations
• PyPose: A Library for Robot Learning with Physics-based Optimization
• Portraying Double Higgs at the Large Hadron Collider
• Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects
• Improving Massive MIMO Belief Propagation Detector with Deep Neural Network
• Crowd Counting with Deep Structured Scale Integration Network
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• An empirical analysis of the optimization of deep network loss surfaces
• Hierarchical Pointer Net Parsing
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
• Multi-Hop Knowledge Graph Reasoning with Reward Shaping
• Hindsight policy gradients
• XPipe: Efficient Pipeline Model Parallelism for Multi-GPU DNN Training
• Predicting waves in fluids with deep neural network
• CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling
• Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
• Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
• Subject-Independent Drowsiness Recognition from Single-Channel EEG with an Interpretable CNN-LSTM model
• A Comparison of Machine Learning Algorithms for the Surveillance of Autism Spectrum Disorder
• Attribute Recognition by Joint Recurrent Learning of Context and Correlation
• Scene Text Recognition from Two-Dimensional Perspective
• A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO Detection
• Interpreting neural network models of residual scalar flux
• End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
• Trivializations for Gradient-Based Optimization on Manifolds
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
• Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Network
• Gaussian Material Synthesis
• Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
• Machine Learning Calabi-Yau Four-folds
• Numeral Understanding in Financial Tweets for Fine-grained Crowd-based Forecasting
• Incorporating Discrete Translation Lexicons into Neural Machine Translation
• System-reliability based multi-ensemble of GAN and one-class joint Gaussian distributions for unsupervised real-time structural health monitoring
• Learning Accurate Entropy Model with Global Reference for Image Compression
• Towards High Performance Video Object Detection for Mobiles
• Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning
• A Low-Cost, Flexible and Portable Volumetric Capturing System
• MaxiMask and MaxiTrack: two new tools for identifying contaminants in astronomical images using convolutional neural networks
• Deep speech inpainting of time-frequency masks
• Ballistocardiogram artifact reduction in simultaneous EEG-fMRI using deep learning
• Liver Segmentation from Multimodal Images using HED-Mask R-CNN
• AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
• Using Convolutional Neural Networks to Develop Starting Models for 2D Full Waveform Inversion
• Spatially and Temporally Efficient Non-local Attention Network for Video-based Person Re-Identification
• Latent Attention For If-Then Program Synthesis
• Objects detection for remote sensing images based on polar coordinates
• Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents
• Facial Action Unit Detection via Adaptive Attention and Relation
• A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition
• Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
• Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control
• Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
• Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning
• Knowledge-refined Denoising Network for Robust Recommendation
• Universal Multimodal Representation for Language Understanding
• Deconfounding Reinforcement Learning in Observational Settings
• Efficient Quality Control of Whole Slide Pathology Images with Human-in-the-loop Training
• Camera Style Adaptation for Person Re-identification
• Learning Human-Object Interaction Detection using Interaction Points
• Transfer learning-based method for automated ewaste recycling in smart cities
• Few-Shot Goal Inference for Visuomotor Learning and Planning
• Crowd Counting using Deep Recurrent Spatial-Aware Network
• Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
• Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
• Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT
• Experiment-informed finite-strain inverse design of spinodal metamaterials
• Learning Hierarchical Discourse-level Structure for Fake News Detection
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese
• SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers
• PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
• Bayesian neural networks via MCMC: a Python-based tutorial
• A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Machine learning-based inversion of nuclear responses
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• Detail-revealing Deep Video Super-resolution
• Measurement of the $CP$-violating phase ${\varphi }_{\mathrm{s}}$ in the B${}_{\mathrm{s}}^0$ $\to$ J$/\psi \varphi$(1020) $\to$ ${\mu }^{+}{\mu }^{-}$K${}^{+}$K${}^{-}$ channel in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• An attention-based multi-resolution model for prostate whole slide imageclassification and localization
• Learning to Estimate 3D Human Pose from Point Cloud
• Domain Adaptation for Robust Workload Level Alignment Between Sessions and Subjects using fNIRS
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• Path integral contour deformations for observables in $SU(N)$ gauge theory
• Machine Learning on Sequential Data Using a Recurrent Weighted Average
• Raw Waveform-based Speech Enhancement by Fully Convolutional Networks
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Task-Oriented Dialogue System as Natural Language Generation
• Learning Hierarchical Features from Generative Models
• A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• Temporally smooth online action detection using cycle-consistent future anticipation
• Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions
• A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions
• Audio Transformers
• Machine Learning for MU-MIMO Receive Processing in OFDM Systems
• Learning from Noisy Labels for Entity-Centric Information Extraction
• Improving constraints on the reionization parameters using 21-cm bispectrum
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Variational Bayes survival analysis for unemployment modelling
• Neural Network Decoders for Large-Distance 2D Toric Codes
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset
• Iterative PET Image Reconstruction Using Convolutional Neural Network Representation
• Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework
• Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models
• Consensus Attention-based Neural Networks for Chinese Reading Comprehension
• CNN-Based Ultrasound Image Reconstruction for Ultrafast Displacement Tracking
• Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces
• OctNet: Learning Deep 3D Representations at High Resolutions
• STDAN: Deformable Attention Network for Space-Time Video Super-Resolution
• Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models
• DeepGestalt - Identifying Rare Genetic Syndromes Using Deep Learning
• Dual Branch Neural Network for Sea Fog Detection in Geostationary Ocean Color Imager
• Stacked Convolutional Neural Network for Diagnosis of COVID-19 Disease from X-ray Images
• Neural News Recommendation with Attentive Multi-View Learning
• WarpPINN: Cine-MR image registration with physics-informed neural networks
• PCN: Point Completion Network
• Hierarchical Transformers for Multi-Document Summarization
• On the Use of Neural Networks for Full Waveform Inversion
• Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data
• Meta-learning of Sequential Strategies
• Search Engine Guided Non-Parametric Neural Machine Translation
• Physics-Informed Neural Networks for Parametric Compressible Euler Equations
• GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencoder
• Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection
• Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
• Analyzing γ-rays of the Galactic Center with Deep Learning
• AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage
• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• Transformer based time series prediction of the maximum power point for solar photovoltaic cells
• Stochastic Answer Networks for Machine Reading Comprehension
• Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
• Dropout Feature Ranking for Deep Learning Models
• Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
• End-to-end semantic segmentation of personalized deep brain structures for non-invasive brain stimulation
• Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems
• Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
• Gradient-based Optimization for Regression in the Functional Tensor-Train Format
• Predicting star formation properties of galaxies using deep learning
• Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos
• Multi-Graph Transformer for Free-Hand Sketch Recognition
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• Learning a Latent Space of Multitrack Measures
• What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning
• RNN-T For Latency Controlled ASR With Improved Beam Search
• Robust and interpretable blind image denoising via bias-free convolutional neural networks
• Mimic and Fool: A Task Agnostic Adversarial Attack
• Multimodal Unified Attention Networks for Vision-and-Language Interactions
• Multi-modality Latent Interaction Network for Visual Question Answering
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
• State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG
• Generative Adversarial Networks (GAN) for compact beam source modelling in Monte Carlo simulations
• Deep Gamblers: Learning to Abstain with Portfolio Theory
• RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning
• Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network
• Analyzing the Real-World Applicability of DGA Classifiers
• Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
• Training Variational Networks with Multi-Domain Simulations: Speed-of-Sound Image Reconstruction
• Multiobjective optimization of the dynamic aperture for SLS 2.0 using surrogate models based on artificial neural networks
• Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
• Search for a heavy Higgs boson decaying into two lighter Higgs bosons in the $\tau \tau$bb final state at 13 TeV
• Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
• Variational Inference based on Robust Divergences
• Capse.jl: efficient and auto-differentiable CMB power spectra emulation
• Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• Workpiece Image-based Tool Wear Classification in Blanking Processes Using Deep Convolutional Neural Networks
• A Multi-task Ensemble Framework for Emotion, Sentiment and Intensity Prediction
• Blending Diverse Physical Priors with Neural Networks
• Joint embedding of structure and features via graph convolutional networks
• Electromagnetic Showers Beyond Shower Shapes
• Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation using Wi-Fi Fingerprinting Based on Deep Neural Networks
• A Cautionary Tale of Decorrelating Theory Uncertainties
• Robust Medical Instrument Segmentation Challenge 2019
• Aspect Category Detection via Topic-Attention Network
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
• ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
• Video Frame Interpolation via Adaptive Convolution
• Is Transfer Learning Necessary for Protein Landscape Prediction?
• Sales Forecast in E-commerce using Convolutional Neural Network
• E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles
• Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding
• Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
• Controlling the Output Length of Neural Machine Translation
• Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge
• Neural Style Transfer for Audio Spectograms
• Physics informed deep learning for computational elastodynamics without labeled data
• The NN-Stacking: Feature weighted linear stacking through neural networks
• BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
• Markov Decision Process Based Design of SWIPT Systems: Non-linear EH Circuits, Memory, and Impedance Mismatch
• The Practicality of Stochastic Optimization in Imaging Inverse Problems
• Considerations When Learning Additive Explanations for Black-Box Models
• Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
• Audeo: Audio Generation for a Silent Performance Video
• Phase Aberration Correction for in vivo Ultrasound Localization Microscopy Using a Spatiotemporal Complex-Valued Neural Network
• KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
• Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation
• Deep Deterministic Policy Gradient to Minimize the Age of Information in Cellular V2X Communications
• Deep Hybrid Scattering Image Learning
• Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI
• Multivariate Time Series Classification using Dilated Convolutional Neural Network
• Neural Text Generation: A Practical Guide
• Deep Sketch-guided Cartoon Video Inbetweening
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning
• Preserving Symmetries for Variational Quantum Eigensolvers in the Presence of Noise
• Learning Continuous Image Representation with Local Implicit Image Function
• Target Transformed Regression for Accurate Tracking
• Graph Collaborative Reasoning
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
• Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
• Semantic-Forward Relaying: A Novel Framework Towards 6G Cooperative Communications
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
• Finding Competitive Network Architectures Within a Day Using UCT
• Z-Forcing: Training Stochastic Recurrent Networks
• Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images
• Design by adaptive sampling
• Federated Learning With Quantized Global Model Updates
• Adversarial Multi-Criteria Learning for Chinese Word Segmentation
• Policy Gradient based Quantum Approximate Optimization Algorithm
• Imitation and Mirror Systems in Robots through Deep Modality Blending Networks
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction
• DeepWay: a Deep Learning Waypoint Estimator for Global Path Generation
• A Theoretical Framework for Target Propagation
• Context-self contrastive pretraining for crop type semantic segmentation
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• TBI Contusion Segmentation from MRI using Convolutional Neural Networks
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
• Quantum readout error mitigation via deep learning
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification
• IMU Based Deep Stride Length Estimation With Self-Supervised Learning
• Products-10K: A Large-scale Product Recognition Dataset
• On Distinctive Image Captioning via Comparing and Reweighting
• One model Packs Thousands of Items with Recurrent Conditional Query Learning
• DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation
• Physics-informed reinforcement learning for sample-efficient optimization of freeform nanophotonic devices
• Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
• Energy-based Detection of Adverse Weather Effects in LiDAR Data
• Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations
• AGL: a Scalable System for Industrial-purpose Graph Machine Learning
• Deep Triplet Ranking Networks for One-Shot Recognition
• Towards Explainable Personalized Recommendations by Learning from Users' Photos
• MatFuse: Controllable Material Generation with Diffusion Models
• Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction
• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
• Detecting multiple chirality centers in chiral molecules with high harmonic generation
• Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety
• Redirection Controller Using Reinforcement Learning
• Efficient nonlinear manifold reduced order model
• ADMM-Net for Communication Interference Removal in Stepped-Frequency Radar
• The analysis of VERITAS muon images using convolutional neural networks
• PhotoMat: A Material Generator Learned from Single Flash Photos
• CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization
• Adaptive Scheduling for Multi-Task Learning
• Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filtering
• Diagnosis of Schizophrenia: A comprehensive evaluation
• Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
• Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
• Eval all, trust a few, do wrong to none: Comparing sentence generation models
• Improved Training of Physics-Informed Neural Networks with Model Ensembles
• Visual Attribute Transfer through Deep Image Analogy
• Teaching Machines to Describe Images via Natural Language Feedback
• HTLM: Hyper-Text Pre-Training and Prompting of Language Models
• Accelerating multimodal gravitational waveforms from precessing compact binaries with artificial neural networks
• Understanding the Limitations of Variational Mutual Information Estimators
• Adversarial-Prediction Guided Multi-task Adaptation for Semantic Segmentation of Electron Microscopy Images
• Concurrent Activity Recognition with Multimodal CNN-LSTM Structure
• PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
• Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
• Investigating Object Compositionality in Generative Adversarial Networks
• Physics Informed Data Driven model for Flood Prediction: Application of Deep Learning in prediction of urban flood development
• Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks
• The Functional Neural Process
• Structural inpainting
• Unsupervised Monocular Depth Estimation with Left-Right Consistency
• Motion Generation Using Bilateral Control-Based Imitation Learning with Autoregressive Learning
• Predicting drag on rough surfaces by transfer learning of empirical correlations
• Meta-Transfer Learning for Few-Shot Learning
• PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
• Few-Shot Keyword Spotting With Prototypical Networks
• Deep Reinforcement Learning for Six Degree-of-Freedom Planetary Powered Descent and Landing
• IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
• Prediction of laminar vortex shedding over a cylinder using deep learning
• Hash Embeddings for Efficient Word Representations
• Downstream Model Design of Pre-trained Language Model for Relation Extraction Task
• Learning Long Term Dependencies via Fourier Recurrent Units
• $\mathrm{S}\mathrm{IM}\mathrm{BIG}$: Mock Challenge for a Forward Modeling Approach to Galaxy Clustering
• Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
• Coordination for Connected and Automated Vehicles at Non-signalized Intersections: A Value Decomposition-based Multiagent Deep Reinforcement Learning Approach
• Establishing Baselines for Text Classification in Low-Resource Languages
• Improving Broad-Coverage Medical Entity Linking with Semantic Type Prediction and Large-Scale Datasets
• Understanding Knowledge Distillation in Non-autoregressive Machine Translation
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Multiview Deep Learning for Predicting Twitter Users' Location
• Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition
• Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
• DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning
• Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery
• Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
• Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation
• Monotonic Chunkwise Attention
• Are generative deep models for novelty detection truly better?
• Modular meta-learning
• Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networks
• DSConv: Efficient Convolution Operator
• Cognitive simulation models for inertial confinement fusion: Combining simulation and experimental data
• PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAM
• Bilevel methods for image reconstruction
• TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
• A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals
• Training Competitive Binary Neural Networks from Scratch
• MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and Better
• Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
• Manifold embedding data-driven mechanics
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction
• CADeSH: Collaborative Anomaly Detection for Smart Homes
• Bypassing Feature Squeezing by Increasing Adversary Strength
• Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data
• Edge-based sequential graph generation with recurrent neural networks
• Rapid tissue oxygenation mapping from snapshot structured-light images with adversarial deep learning
• Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric
• K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways
• Unsupervised Degradation Learning for Single Image Super-Resolution
• Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning
• Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependencies
• A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation
• Leveraging Machine Learning to Alleviate Hubbard Model Sign Problems
• Deep Reinforcement Learning from Policy-Dependent Human Feedback
• Multi-Objective De Novo Drug Design with Conditional Graph Generative Model
• Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEs
• Learning for Disparity Estimation through Feature Constancy
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• Learning Adaptive Sampling and Reconstruction for Volume Visualization
• LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
• A Multi-Modal Chinese Poetry Generation Model
• Description Based Text Classification with Reinforcement Learning
• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance
• Applications of Scientific Machine Learning for the Analysis of Functionally Graded Porous Beams
• Anomaly Detection in Gravitational Waves data using Convolutional AutoEncoders
• Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation
• An AI-Assisted Design Method for Topology Optimization Without Pre-Optimized Training Data
• Binary Neutron Stars Gravitational Wave Detection Based on Wavelet Packet Analysis And Convolutional Neural Networks
• Width Provably Matters in Optimization for Deep Linear Neural Networks
• Deep Character-Level Click-Through Rate Prediction for Sponsored Search
• Text to Image Synthesis Using Generative Adversarial Networks
• Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections
• IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
• DCASE 2018 Challenge Surrey Cross-Task convolutional neural network baseline
• sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI
• MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
• Aggressive Deep Driving: Model Predictive Control with a CNN Cost Model
• DeepMVS: Learning Multi-view Stereopsis
• Using BERT for Word Sense Disambiguation
• Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing
• Spherical Message Passing for 3D Graph Networks
• DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Symplectic Learning for Hamiltonian Neural Networks
• VarNet: Variational Neural Networks for the Solution of Partial Differential Equations
• Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations
• Characterizing soot in TEM images using a convolutional neural network
• Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression
• Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation
• Regularizing Deep Multi-Task Networks using Orthogonal Gradients
• Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks
• Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies
• NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• A cross-corpus study on speech emotion recognition
• Improving Variational Encoder-Decoders in Dialogue Generation
• Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• Efficient Neural Implicit Representation for 3D Human Reconstruction
• Enhancing Medical Image Registration via Appearance Adjustment Networks
• Tensor Normalization and Full Distribution Training
• OpenDPD: An Open-Source End-to-End Learning & Benchmarking Framework for Wideband Power Amplifier Modeling and Digital Pre-Distortion
• Robust deformable image registration using cycle-consistent implicit representations
• Gaussian process regression + deep neural network autoencoder for probabilistic surrogate modeling in nonlinear mechanics of solids
• FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equations
• Unsupervised Learning of Long-Term Motion Dynamics for Videos
• CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
• Few-shot Natural Language Generation for Task-Oriented Dialog
• CASI: A Convolutional Neural Network Approach for Shell Identification
• On the application of generative adversarial networks for nonlinear modal analysis
• Inductive Matrix Completion Based on Graph Neural Networks
• Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks
• BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
• Deep Reinforcement Learning for Intelligent Transportation Systems
• Unsupervised Deep Contrast Enhancement with Power Constraint for OLED Displays
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution
• End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient
• Are we pretraining it right? Digging deeper into visio-linguistic pretraining
• Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
• Hypergraph-based Multi-View Action Recognition using Event Cameras
• Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials
• Implementation of Fruits Recognition Classifier using Convolutional Neural Network Algorithm for Observation of Accuracies for Various Hidden Layers
• Burst Denoising with Kernel Prediction Networks
• When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
• Revisiting Fine-tuning for Few-shot Learning
• DeProCams: Simultaneous Relighting, Compensation and Shape Reconstruction for Projector-Camera Systems
• Short text classification with machine learning in the social sciences: The case of climate change on Twitter
• Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting
• KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset
• Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
• Smartphone Sensor-based Human Activity Recognition Robust to Different Sampling Rates
• Model-free Deep Reinforcement Learning for Urban Autonomous Driving
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• AANet: Adaptive Aggregation Network for Efficient Stereo Matching
• Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning
• CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer
• Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications
• Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions
• PPFS: Predictive Permutation Feature Selection
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Exposure Trajectory Recovery from Motion Blur
• Semantic segmentation of mFISH images using convolutional networks
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks
• Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators
• Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
• When is invariance useful in an Out-of-Distribution Generalization problem ?
• Real or Fake? Learning to Discriminate Machine from Human Generated Text
• Improving the Gating Mechanism of Recurrent Neural Networks
• Nemesyst: A Hybrid Parallelism Deep Learning-Based Framework Applied for Internet of Things Enabled Food Retailing Refrigeration Systems
• Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
• Machine Learning Approaches to Learn HyChem Models
• FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
• Self-Supervised VQ-VAE for One-Shot Music Style Transfer
• Bayesian Stokes inversion with Normalizing flows
• Robust Tumor Localization with Pyramid Grad-CAM
• Spatiotemporal Transformer for Video-based Person Re-identification
• Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• Context-aware Synthesis for Video Frame Interpolation
• A Probabilistic Framework for Estimating the Risk of Pedestrian-Vehicle Conflicts at Intersections
• 'In-Between' Uncertainty in Bayesian Neural Networks
• Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions
• Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• Automated Identification of Cell Populations in Flow Cytometry Data with Transformers
• Dielectric constant of supercritical water in a large pressure-temperature range
• Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
• Densely connected neural networks for nonlinear regression
• A physics-aware deep learning model for energy localization in multiscale shock-to-detonation simulations of heterogeneous energetic materials
• Convolutional Sequence to Sequence Model for Human Dynamics
• CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows
• Blood Oxygen Saturation Estimation from Facial Video via DC and AC components of Spatio-temporal Map
• Physics-Consistent Data-driven Waveform Inversion with Adaptive Data Augmentation
• Conditional Adversarial Synthesis of 3D Facial Action Units
• Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
• JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
• Non-autoregressive Transformer by Position Learning
• GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
• Multimodal Transformer with Multi-View Visual Representation for Image Captioning
• Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images
• An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification
• A Comparative Study of Word Embeddings for Reading Comprehension
• Task-Oriented Query Reformulation with Reinforcement Learning
• Optimal control of families of quantum gates
• Educating Text Autoencoders: Latent Representation Guidance via Denoising
• 3D Axial-Attention for Lung Nodule Classification
• Reliable Probability Forecast of Solar Flares: Deep Flare Net-Reliable (DeFN-R)
• Noise2Context: Context-assisted Learning 3D Thin-layer Low Dose CT Without Clean Data
• DR-Unet104 for Multimodal MRI brain tumor segmentation
• Amobee at SemEval-2018 Task 1: GRU Neural Network with a CNN Attention Mechanism for Sentiment Classification
• VIO-DualProNet: Visual-Inertial Odometry with Learning Based Process Noise Covariance
• Embedding Model Based Fast Meta Learning for Downlink Beamforming Adaptation
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Towards contrast-agnostic soft segmentation of the spinal cord
• A Graph-to-Sequence Model for AMR-to-Text Generation
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• A Variational Information Bottleneck Approach to Multi-Omics Data Integration
• Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation
• Q-Learning in enormous action spaces via amortized approximate maximization
• Dynamic Conditional Imitation Learning for Autonomous Driving
• ViTOR: Learning to Rank Webpages Based on Visual Features
• Deep Convolutional Autoencoders as Generic Feature Extractors in Seismological Applications
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• VD-BERT: A Unified Vision and Dialog Transformer with BERT
• Short-term daily precipitation forecasting with seasonally-integrated autoencoder
• Predicting Future Lane Changes of Other Highway Vehicles using RNN-based Deep Models
• Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
• Cost-aware Bayesian Optimization
• R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
• Graph CNN for Moving Object Detection in Complex Environments from Unseen Videos
• Extracting Urban Sound Information for Residential Areas in Smart Cities Using an End-to-End IoT System
• CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
• Learning to Defend by Learning to Attack
• DAPPLE: A Pipelined Data Parallel Approach for Training Large Models
• Physics-constrained Deep Learning for Robust Inverse ECG Modeling
• On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters
• Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
• Pair-Level Supervised Contrastive Learning for Natural Language Inference
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
• Multi-Task Handwritten Document Layout Analysis
• Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learning
• TheanoLM - An Extensible Toolkit for Neural Network Language Modeling
• Word Embeddings and Their Use In Sentence Classification Tasks
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• A Conditional Variational Framework for Dialog Generation
• SEOpinion: Summarization and Exploration Opinion of E-Commerce Websites
• Thermal experiments for fractured rock characterization: theoretical analysis and inverse modeling
• Convolutional Generation of Textured 3D Meshes
• SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
• Perspective Projection-Based 3D CT Reconstruction from Biplanar X-rays
• Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
• Multiple shooting for training neural differential equations on time series
• Learning in Wireless Control Systems over Non-Stationary Channels
• Relation-Based Associative Joint Location for Human Pose Estimation in Videos
• Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network
• Improving Entity Linking by Modeling Latent Relations between Mentions
• An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
• Model reconstruction from temporal data for coupled oscillator networks
• ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
• Deep Learning-Guided Surface Characterization for Autonomous Hydrogen Lithography
• QGOpt: Riemannian optimization for quantum technologies
• Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition
• DSAM: A Deep Learning Framework for Analyzing Temporal and Spatial Dynamics in Brain Networks
• Opening the black box of neural nets: case studies in stop/top discrimination
• Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
• ViSTRA2: Video Coding using Spatial Resolution and Effective Bit Depth Adaptation
• DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
• Mask-aware Photorealistic Face Attribute Manipulation
• TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow
• A Flow-Based Neural Network for Time Domain Speech Enhancement
• Rain O'er Me: Synthesizing real rain to derain with data distillation
• Simple yet Effective Way for Improving the Performance of GAN
• High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks
• Non-Local Video Denoising by CNN
• RES: A Robust Framework for Guiding Visual Explanation
• Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
• High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning
• Efficient Exact Verification of Binarized Neural Networks
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• QUOTIENT: Two-Party Secure Neural Network Training and Prediction
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Continual Learning with Gated Incremental Memories for sequential data processing
• On Learning Intrinsic Rewards for Policy Gradient Methods
• Efficient sampling of constrained high-dimensional theoretical spaces with machine learning
• Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection
• Deep Contextual Bandit and Reinforcement Learning for IRS-Assisted MU-MIMO Systems
• Single-exposure absorption imaging of ultracold atoms using deep learning
• FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
• Solar Power Time Series Forecasting Utilising Wavelet Coefficients
• Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows
• On the Benefit of Adversarial Training for Monocular Depth Estimation
• Transferable Adversarial Attacks for Image and Video Object Detection
• AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks
• Synthesis of Realistic ECG using Generative Adversarial Networks
• Earthquake Location and Magnitude Estimation with Graph Neural Networks
• Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines
• Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
• Learning Discriminative Representations and Decision Boundaries for Open Intent Detection
• Cramér-Rao bound-informed training of neural networks for quantitative MRI
• Make Skeleton-based Action Recognition Model Smaller, Faster and Better
• What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties
• Shallow reading with Deep Learning: Predicting popularity of online content using only its title
• Bayesian model and dimension reduction for uncertainty propagation: applications in random media
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• Search for charged-lepton-flavour violation in $Z$-boson decays with the ATLAS detector
• End-to-End Self-Debiasing Framework for Robust NLU Training
• Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision
• Pose is all you need: The pose only group activity recognition system (POGARS)
• Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
• Multi-Task Deep Residual Echo Suppression with Echo-aware Loss
• Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
• A Study of the Generalizability of Self-Supervised Representations
• Deep Learning based Channel Estimation for Massive MIMO with Hybrid Transceivers
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
• Full-pulse Tomographic Reconstruction with Deep Neural Networks
• Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
• Style2Vec: Representation Learning for Fashion Items from Style Sets
• DeepMTL Pro: Deep Learning Based MultipleTransmitter Localization and Power Estimation
• ASMCNN: An Efficient Brain Extraction Using Active Shape Model and Convolutional Neural Networks
• Guided parallelized stochastic gradient descent for delay compensation
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification
• WD3: Taming the Estimation Bias in Deep Reinforcement Learning
• Single-Shot Motion Completion with Transformer
• Alleviating the transit timing variation bias in transit surveys. I. RIVERS: Method and detection of a pair of resonant super-Earths around Kepler-1705
• Convolutional Neural Network-Bagged Decision Tree: A hybrid approach to reduce electric vehicle's driver's range anxiety by estimating energy consumption in real-time
• Compressing Word Embeddings via Deep Compositional Code Learning
• Active Learning for Graph Neural Networks via Node Feature Propagation
• FloWaveNet : A Generative Flow for Raw Audio
• Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learning
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
• Meta-Learning for Low-Resource Neural Machine Translation
• Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
• Numerical Approximation of Partial Differential Equations by a Variable Projection Method with Artificial Neural Networks
• Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
• Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces
• ZM-Net: Real-time Zero-shot Image Manipulation Network
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
• Counterfactual Explanation Based on Gradual Construction for Deep Networks
• Developing Bug-Free Machine Learning Systems With Formal Mathematics
• Spatio-temporal analysis of chromospheric heating in a plage region
• Hyperparameter Optimization: A Spectral Approach
• Text as Neural Operator: Image Manipulation by Text Instruction
• Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
• Neural Network Reconstruction of $H^{\prime }(z)$ and its application in Teleparallel Gravity
• Amortized Variational Inference: A Systematic Review
• Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Deep Convolutional Neural Network for Identifying Seam-Carving Forgery
• ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
• End-to-end Optimization of Constellation Shaping for Wiener Phase Noise Channels with a Differentiable Blind Phase Search
• HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
• Comparing Neural- and N-Gram-Based Language Models for Word Segmentation
• Dynamic Adversarial Patch for Evading Object Detection Models
• Exploiting Neural Query Translation into Cross Lingual Information Retrieval
• Hybrid RIS-Assisted MIMO Dual-Function Radar-Communication System
• Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hulls
• Bayesian Deep Ensembles via the Neural Tangent Kernel
• Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks
• Transforming Visual Scene Graphs to Image Captions
• Understanding Synthetic Gradients and Decoupled Neural Interfaces
• In-air Knotting of Rope using Dual-Arm Robot based on Deep Learning
• Signed Distance-based Deep Memory Recommender
• HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methods
• RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music
• Leakage of Dataset Properties in Multi-Party Machine Learning
• High Perceptual Quality Wireless Image Delivery with Denoising Diffusion Models
• Sketch-Guided Scenery Image Outpainting
• They, Them, Theirs: Rewriting with Gender-Neutral English
• Deep learning with 4D spatio-temporal data representations for OCT-based force estimation
• Negative Sampling Improves Hypernymy Extraction Based on Projection Learning
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
• Consistent machine learning for topology optimization with microstructure-dependent neural network material models
• LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
• Musculoskeletal AutoEncoder: A Unified Online Acquisition Method of Intersensory Networks for State Estimation, Control, and Simulation of Musculoskeletal Humanoids
• Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
• Search for flavour-changing neutral currents in processes with one top quark and a photon using 81 fb${}^{-1}$ of $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS experiment
• Rethinking Weight Decay For Efficient Neural Network Pruning
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Machine Learning aided 3D-position reconstruction in large LaCl${}_3$ crystals
• FibAR: Embedding Optical Fibers in 3D Printed Objects for Active Markers in Dynamic Projection Mapping
• Better Compression with Deep Pre-Editing
• AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods
• Virtual staining of defocused autofluorescence images of unlabeled tissue using deep neural networks
• Velocity Reconstruction in Puffing Pool Fires with Physics-Informed Neural Networks
• One-shot Face Reenactment
• Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application
• Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
• Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
• Single Image Reflection Removal Using Deep Encoder-Decoder Network
• Can Graph Neural Networks Count Substructures?
• Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization
• Machine Learning Emulation of Urban Land Surface Processes
• Large-Scale Generative Data-Free Distillation
• Informed Multi-context Entity Alignment
• Laplacian Smoothing Gradient Descent
• Physical deep learning based on optimal control of dynamical systems
• DeepFake Detection Based on the Discrepancy Between the Face and its Context
• DeepSignals: Predicting Intent of Drivers Through Visual Signals
• 3D Human Pose Estimation with Relational Networks
• Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoders
• Deep Learning Aided Packet Routing in Aeronautical Ad-Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multi-Objective Optimization
• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
• Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
• CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters
• Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation
• PECOS: Prediction for Enormous and Correlated Output Spaces
• Mean-field theory of graph neural networks in graph partitioning
• FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
• Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• Deep learning approach for breast cancer diagnosis
• Explaining deep learning of galaxy morphology with saliency mapping
• Uncertainty Quantification in Three Dimensional Natural Convection using Polynomial Chaos Expansion and Deep Neural Networks
• EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• Development of accurate human head models for personalized electromagnetic dosimetry using deep learning
• A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming
• Seeking Subjectivity in Visual Emotion Distribution Learning
• Accelerating Quantitative Susceptibility Mapping using Compressed Sensing and Deep Neural Network
• Hamiltonian Generative Networks
• CVR-Net: A deep convolutional neural network for coronavirus recognition from chest radiography images
• Efficient Implementation of Non-linear Flow Law Using Neural Network into the Abaqus Explicit FEM code
• DeepLO: Geometry-Aware Deep LiDAR Odometry
• Wire-Cell 3D Pattern Recognition Techniques for Neutrino Event Reconstruction in Large LArTPCs: Algorithm Description and Quantitative Evaluation with MicroBooNE Simulation
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• Quasar microlensing light curve analysis using deep machine learning
• Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
• TRAT: Tracking by Attention Using Spatio-Temporal Features
• Unseen Target Stance Detection with Adversarial Domain Generalization
• A Differentiable Model of the Assembly of Individual and Populations of Dark Matter Halos
• Tighter Variational Bounds are Not Necessarily Better
• Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
• Neural Extractive Text Summarization with Syntactic Compression
• Language-Conditioned Graph Networks for Relational Reasoning
• Deep encoder-decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling
• Regularizing RNNs by Stabilizing Activations
• Evaluation of convolutional neural networks using a large multi-subject P300 dataset
• Approximate Bayesian Uncertainties on Deep Learning Dynamical Mass Estimates of Galaxy Clusters
• Computational synthesis of locomotive soft robots by topology optimization
• Similarity Learning based Few Shot Learning for ECG Time Series Classification
• Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
• Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network
• A neural network system for transformation of regional cuisine style
• AdaSwarm: Augmenting Gradient-Based optimizers in Deep Learning with Swarm Intelligence
• A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
• Representation, learning, and planning algorithms for geometric task and motion planning
• Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
• A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
• Towards a Neural Network Approach to Abstractive Multi-Document Summarization
• Autonomous Air Traffic Controller: A Deep Multi-Agent Reinforcement Learning Approach
• DF-VO: What Should Be Learnt for Visual Odometry?
• Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
• Wide Compression: Tensor Ring Nets
• RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
• SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
• CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
• An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients
• BusTr: Predicting Bus Travel Times from Real-Time Traffic
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams
• Successive Point-of-Interest Recommendation with Local Differential Privacy
• Deep Reinforcement Learning based Resource Allocation for V2V Communications
• Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word
• S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning
• Decoding Imagined Speech and Computer Control using Brain Waves
• Spin Parity of Spiral Galaxies II: A catalogue of 80k spiral galaxies using big data from the Subaru Hyper Suprime-Cam Survey and deep learning
• Single-frame far-field diffractive imaging with randomized illumination
• Bidirectional Tree-Structured LSTM with Head Lexicalization
• Variational quantum one-class classifier
• Learning-based estimation of dielectric properties and tissue density in head models for personalized radio-frequency dosimetry
• Detecting Photoshopped Faces by Scripting Photoshop
• Universal programmable photonic architecture for quantum information processing
• Subject-independent trajectory prediction using pre-movement EEG during grasp and lift task
• Beyond Heart Murmur Detection: Automatic Murmur Grading from Phonocardiogram
• Human activity recognition based on time series analysis using U-Net
• Neural Networks for Extreme Quantile Regression with an Application to Forecasting of Flood Risk
• URANUS: Radio Frequency Tracking, Classification and Identification of Unmanned Aircraft Vehicles
• Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
• Learning to Prune Filters in Convolutional Neural Networks
• A Deep Learning Based 6 Degree-of-Freedom Localization Method for Endoscopic Capsule Robots
• Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets
• On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
• Model-Based Reinforcement Learning for Sepsis Treatment
• Neural Canonical Transformation with Symplectic Flows
• Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
• Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
• On Feature Normalization and Data Augmentation
• Learning Efficient Algorithms with Hierarchical Attentive Memory
• A Benchmark for Lease Contract Review
• Video Propagation Networks
• Extraction of the Muon Signals Recorded with the Surface Detector of the Pierre Auger Observatory Using Recurrent Neural Networks
• Restricted Minimum Error Entropy Criterion for Robust Classification
• Counterfactual Phenotyping with Censored Time-to-Events
• Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• On the Powerball Method for Optimization
• Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis
• Multimodal Compact Bilinear Pooling for Multimodal Neural Machine Translation
• EM-driven unsupervised learning for efficient motion segmentation
• An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior
• Learning Sparse Low-Precision Neural Networks With Learnable Regularization
• Unsupervised learning of anomalous diffusion data
• Multivariate Realized Volatility Forecasting with Graph Neural Network
• Learning Dense Correspondence via 3D-guided Cycle Consistency
• Many-Body Quantum States with Exact Conservation of Non-Abelian and Lattice Symmetries through Variational Monte Carlo
• Meta-Consolidation for Continual Learning
• DVQA: Understanding Data Visualizations via Question Answering
• Composite Motion Learning with Task Control
• AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
• Relational recurrent neural networks
• Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling
• Multimodal Speech Emotion Recognition using Cross Attention with Aligned Audio and Text
• Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
• Embedding Words as Distributions with a Bayesian Skip-gram Model
• ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks
• FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
• Continuous-in-Depth Neural Networks
• An Adversarial Super-Resolution Remedy for Radar Design Trade-offs
• A Deep Multi-Agent Reinforcement Learning Approach to Autonomous Separation Assurance
• Identifying viruses from metagenomic data by deep learning
• Revisiting the Plastic Surgery Hypothesis via Large Language Models
• Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
• Sampling Agnostic Feature Representation for Long-Term Person Re-identification
• Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval
• Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognition
• Low-Resource Text Classification using Domain-Adversarial Learning
• Convolutions on Spherical Images
• OctNetFusion: Learning Depth Fusion from Data
• Wiener-Hammerstein model and its learning for nonlinear digital pre-distortion of optical transmitters
• Generative machine learning methods for multivariate ensemble post-processing
• Learning Guided Convolutional Network for Depth Completion
• Exploring Differential Geometry in Neural Implicits
• Generative Modeling with Conditional Autoencoders: Building an Integrated Cell
• SPIGAN: Privileged Adversarial Learning from Simulation
• AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization
• Constructing Parsimonious Analytic Models for Dynamic Systems via Symbolic Regression
• Auto-Encoding Scene Graphs for Image Captioning
• How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change
• View Synthesis by Appearance Flow
• GlobeNet: Convolutional Neural Networks for Typhoon Eye Tracking from Remote Sensing Imagery
• Inception Neural Network for Complete Intersection Calabi-Yau 3-folds
• Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding
• Unified Abstract Syntax Tree Representation Learning for Cross-Language Program Classification
• ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• Robust Deep Reinforcement Learning for Extractive Legal Summarization
• Scaling Laws for Transfer
• Predicting fluid-structure interaction with graph neural networks
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
• Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
• Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention
• A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
• Latency-Aware Differentiable Neural Architecture Search
• Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
• EVIL: Exploiting Software via Natural Language
• Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video
• Assaying Out-Of-Distribution Generalization in Transfer Learning
• Learning to Reuse Distractors to support Multiple Choice Question Generation in Education
• Deep Neural Networks for Marine Debris Detection in Sonar Images
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• Sentence Pair Scoring: Towards Unified Framework for Text Comprehension
• Graph Neural Networks for Surfactant Multi-Property Prediction
• Arbitrage of Energy Storage in Electricity Markets with Deep Reinforcement Learning
• Solving time dependent Fokker-Planck equations via temporal normalizing flow
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
• Deep reinforcement learning in World-Earth system models to discover sustainable management strategies
• Deep active inference agents using Monte-Carlo methods
• Evolving Context-Aware Recommender Systems With Users in Mind
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• Less Is More: Picking Informative Frames for Video Captioning
• Motion Switching with Sensory and Instruction Signals by designing Dynamical Systems using Deep Neural Network
• AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
• Transcribing Content from Structural Images with Spotlight Mechanism
• Magnetic Field Prediction Using Generative Adversarial Networks
• A Contrastive Variational Graph Auto-Encoder for Node Clustering
• Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring
• Camera-based vehicle velocity estimation from monocular video
• EFTofLSS meets simulation-based inference: ${\sigma }_8$ from biased tracers
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping
• Normalized and Geometry-Aware Self-Attention Network for Image Captioning
• Automatic Design of Artificial Neural Networks for Gamma-Ray Detection
• Multi Modal Convolutional Neural Networks for Brain Tumor Segmentation
• Simple vs complex temporal recurrences for video saliency prediction
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification
• Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
• Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks
• Neural network representability of fully ionized plasma fluid model closures
• Connecting Weighted Automata and Recurrent Neural Networks through Spectral Learning
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition
• View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
• BlinkML: Efficient Maximum Likelihood Estimation with Probabilistic Guarantees
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• DCVSMNet: Double Cost Volume Stereo Matching Network
• High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
• Ball 3D Localization From A Single Calibrated Image
• Flowfield prediction of airfoil off-design conditions based on a modified variational autoencoder
• Self-Explaining Structures Improve NLP Models
• Theory-Inspired Path-Regularized Differential Network Architecture Search
• Discovering Signals from Web Sources to Predict Cyber Attacks
• Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims
• Modeling Vocabulary for Big Code Machine Learning
• Online Learning for Neural Machine Translation Post-editing
• Local Label Point Correction for Edge Detection of Overlapping Cervical Cells
• Large-Scale Plant Classification with Deep Neural Networks
• SUPPNet: Neural network for stellar spectrum normalisation
• On Demand Solid Texture Synthesis Using Deep 3D Networks
• 3D Dense Face Alignment via Graph Convolution Networks
• Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia
• AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance
• Network slicing for vehicular communications: a multi-agent deep reinforcement learning approach
• SemantIC: Semantic Interference Cancellation Towards 6G Wireless Communications
• Differentially Private Federated Learning on Heterogeneous Data
• Meta-Learning Representations for Continual Learning
• Direction Concentration Learning: Enhancing Congruency in Machine Learning
• TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• Attention over Parameters for Dialogue Systems
• Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• Data-Enhanced Variational Monte Carlo Simulations for Rydberg Atom Arrays
• A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor
• Facial Landmark Detection with Tweaked Convolutional Neural Networks
• GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
• Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
• MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining
• Unveiling new disease, pathway, and gene associations via multi-scale neural networks
• Sequence-Based Extractive Summarisation for Scientific Articles
• Learning Intrinsic Image Decomposition from Watching the World
• Accelerated variational algorithms for digital quantum simulation of many-body ground states
• An Adaptive Clipping Approach for Proximal Policy Optimization
• Reducing the Model Variance of a Rectal Cancer Segmentation Network
• Where is Your App Frustrating Users?
• A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content
• Neural ensemble decoding for topological quantum error-correcting codes
• Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
• Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
• Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos
• Mapping Dark Matter in the Milky Way using Normalizing Flows and Gaia DR3
• RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
• Robust Collaborative Filtering to Popularity Distribution Shift
• Neural Networks with Recurrent Generative Feedback
• Fast Image Caption Generation with Position Alignment
• Automatic Analysis of Sewer Pipes Based on Unrolled Monocular Fisheye Images
• 3D Shape Reconstruction from Vision and Touch
• Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces
• Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
• e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
• MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation
• Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
• DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering
• Online Video Deblurring via Dynamic Temporal Blending Network
• Learning to solve inverse problems using Wasserstein loss
• A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
• Offline Reinforcement Learning with Fisher Divergence Critic Regularization
• Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Active anomaly detection based on deep one-class classification
• Unweighting multijet event generation using factorisation-aware neural networks
• deepTarget: End-to-end Learning Framework for microRNA Target Prediction using Deep Recurrent Neural Networks
• Robust Dynamic Bus Control: A Distributional Multi-agent Reinforcement Learning Approach
• Double RIS-Assisted MIMO Systems Over Spatially Correlated Rician Fading Channels and Finite Scatterers
• Masked Non-Autoregressive Image Captioning
• S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction
• Noisy Natural Gradient as Variational Inference
• Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalising neural network
• Improving Multi-Modal Learning with Uni-Modal Teachers
• Deep Koopman Learning of Nonlinear Time-Varying Systems
• Emerging Cross-lingual Structure in Pretrained Language Models
• Dynamic Feature Acquisition Using Denoising Autoencoders
• DeepFlow: History Matching in the Space of Deep Generative Models
• Personalized Dialogue Generation with Persona-Adaptive Attention
• New Benchmarks for Learning on Non-Homophilous Graphs
• A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
• VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation
• Mitigating Smart Jammers in Multi-User MIMO
• Defense against Universal Adversarial Perturbations
• Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• Improving the Neural GPU Architecture for Algorithm Learning
• An Ensemble Model with Attention Based Mechanism for Image Captioning
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• Two Routes to Scalable Credit Assignment without Weight Symmetry
• GANs May Have No Nash Equilibria
• A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• End to End Video Segmentation for Driving : Lane Detection For Autonomous Car
• DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps
• Searching for broadband pulsed beacons from 1883 stars using neural networks
• Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
• Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
• A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
• Talking Head from Speech Audio using a Pre-trained Image Generator
• LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection
• MaskDGA: A Black-box Evasion Technique Against DGA Classifiers and Adversarial Defenses
• Developmentally motivated emergence of compositional communication via template transfer
• Sub-Band Knowledge Distillation Framework for Speech Enhancement
• Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond
• Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles
• Image-Conditioned Graph Generation for Road Network Extraction
• V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation
• Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution
• Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition
• Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning
• Double Deep Q-Learning-based Path Selection and Service Placement for Latency-Sensitive Beyond 5G Applications
• Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
• Stress-Testing Neural Models of Natural Language Inference with Multiply-Quantified Sentences
• Cross-domain Correspondence Learning for Exemplar-based Image Translation
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
• The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
• PENet: Towards Precise and Efficient Image Guided Depth Completion
• VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels
• Estimating 6D Pose From Localizing Designated Surface Keypoints
• RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data
• NUVA: A Naming Utterance Verifier for Aphasia Treatment
• Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Explanation as a Defense of Recommendation
• Inverse design of broadband and lossless topological photonic crystal waveguide modes
• HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
• Contextual Slot Carryover for Disparate Schemas
• On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement
• EmotionX-KU: BERT-Max based Contextual Emotion Classifier
• Neural parameters estimation for brain tumor growth modeling
• Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering
• NORESQA: A Framework for Speech Quality Assessment using Non-Matching References
• Unsupervised Doodling and Painting with Improved SPIRAL
• Distance Map Loss Penalty Term for Semantic Segmentation
• Random Error Sampling-based Recurrent Neural Network Architecture Optimization
• The LSST-DESC 3x2pt Tomography Optimization Challenge
• FaceShop: Deep Sketch-based Face Image Editing
• DDRprog: A CLEVR Differentiable Dynamic Reasoning Programmer
• Hierarchically modelling Kepler dwarfs and subgiants to improve inference of stellar properties with asteroseismology
• Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss
• DSGN: Deep Stereo Geometry Network for 3D Object Detection
• An Attention-based Graph Neural Network for Heterogeneous Structural Learning
• DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary Supervision
• Inference skipping for more efficient real-time speech enhancement with parallel RNNs
• Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
• Optimizing User Interface Layouts via Gradient Descent
• Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
• A GNN Approach for Cell-Free Massive MIMO
• HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• VITON: An Image-based Virtual Try-on Network
• Teacher-Student chain for efficient semi-supervised histology image classification
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
• Deep Learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with Data Gaps
• Context-Aware Learning to Rank with Self-Attention
• Parallelizing Linear Recurrent Neural Nets Over Sequence Length
• Holophrasm: a neural Automated Theorem Prover for higher-order logic
• Online Monaural Speech Enhancement Using Delayed Subband LSTM
• Potential for optimizing Higgs boson CP measurement in H to tau tau decay at LHC and ML techniques
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers
• Depth-aware Blending of Smoothed Images for Bokeh Effect Generation
• GradAug: A New Regularization Method for Deep Neural Networks
• Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
• A Unified Multi-Phase CT Synthesis and Classification Framework for Kidney Cancer Diagnosis with Incomplete Data
• Graph Policy Network for Transferable Active Learning on Graphs
• Knowledge Distillation Based Semantic Communications For Multiple Users
• Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
• Physics-informed neural networks for unsteady incompressible flows with time-dependent moving boundaries
• Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• Variational Bayesian experimental design for geophysical applications: seismic source location, amplitude versus offset inversion, and estimating CO2 saturations in a subsurface reservoir
• Taming Resource Heterogeneity In Distributed ML Training With Dynamic Batching
• X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks
• Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
• Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities
• ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold
• Physics-informed neural networks for gravity currents reconstruction from limited data
• Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions
• RetroGraph: Retrosynthetic Planning with Graph Search
• Predicting Auction Price of Vehicle License Plate with Deep Recurrent Neural Network
• Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty
• Jet-Parton Assignment in ttH Events using Deep Learning
• A hybrid data driven-physics constrained Gaussian process regression framework with deep kernel for uncertainty quantification
• Autoencoder-based holographic image restoration
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
• FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
• Graph-based Algorithm Unfolding for Energy-aware Power Allocation in Wireless Networks
• A community-powered search of machine learning strategy space to find NMR property prediction models
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• A Reinforcement Learning Approach for the Continuous Electricity Market of Germany: Trading from the Perspective of a Wind Park Operator
• Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks
• Convolution by Evolution: Differentiable Pattern Producing Networks
• Improving colonoscopy lesion classification using semi-supervised deep learning
• Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties
• Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
• Graph-Guided Network for Irregularly Sampled Multivariate Time Series
• PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
• Investigation of nonlocal data-driven methods for subgrid-scale stress modelling in large eddy simulation
• Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
• CSC-Unet: A Novel Convolutional Sparse Coding Strategy Based Neural Network for Semantic Segmentation
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Meta-learning Based Beamforming Design for MISO Downlink
• A modular U-Net for automated segmentation of X-ray tomography images in composite materials
• GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
• The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation
• Automatically Differentiable Quantum Circuit for Many-qubit State Preparation
• Bayesian graph convolutional neural networks via tempered MCMC
• A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
• SNIascore: Deep Learning Classification of Low-Resolution Supernova Spectra
• Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches
• An Approach for Improving Automatic Mouth Emotion Recognition
• Families In Wild Multimedia: A Multimodal Database for Recognizing Kinship
• Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks
• Prediction of numerical homogenization using deep learning for the Richards equation
• Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
• FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
• Deep learning-based denoising for fast time-resolved flame emission spectroscopy in high-pressure combustion environment
• Manipulation of Granular Materials by Learning Particle Interactions
• Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
• Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder
• Visual Anomaly Detection in Event Sequence Data
• Latent-Domain Predictive Neural Speech Coding
• Redshift requirements for cosmic shear with intrinsic alignment
• Content-Aware Unsupervised Deep Homography Estimation
• High-resolution Multi-spectral Imaging with Diffractive Lenses and Learned Reconstruction
• Toward Degree Bias in Embedding-Based Knowledge Graph Completion
• A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series
• Inferring electrochemical performance and parameters of Li-ion batteries based on deep operator networks
• Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks
• Dr.VAE: Drug Response Variational Autoencoder
• EA-LSTM: Evolutionary Attention-based LSTM for Time Series Prediction
• Learning-Based Framework for Camera Calibration with Distortion Correction and High Precision Feature Detection
• Perfect is the enemy of test oracle
• Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network
• Learning the Enigma with Recurrent Neural Networks
• Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
• Deep learning: Technical introduction
• Cooperative Multi-Agent Reinforcement Learning for Low-Level Wireless Communication
• BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis
• An Expandable Machine Learning-Optimization Framework to Sequential Decision-Making
• Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron
• Video action detection by learning graph-based spatio-temporal interactions
• Knowledge Representation Learning: A Quantitative Review
• Generalisation of structural knowledge in the hippocampal-entorhinal system
• Graph Signal Restoration Using Nested Deep Algorithm Unrolling
• GCNv2: Efficient Correspondence Prediction for Real-Time SLAM
• Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
• Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
• FedCM: Federated Learning with Client-level Momentum
• Self-Binarizing Networks
• A Survey of Deep Learning Video Super-Resolution
• Multi-Features Guidance Network for partial-to-partial point cloud registration
• Explainable artificial intelligence model to predict acute critical illness from electronic health records
• Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction
• Can We Generate Shellcodes via Natural Language? An Empirical Study
• Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
• Teaching Categories to Human Learners with Visual Explanations
• A Survey of Black-Box Adversarial Attacks on Computer Vision Models
• Classical and quantum regression analysis for the optoelectronic performance of NTCDA/p-Si UV photodiode
• Automatic Identification of MHD Modes in Magnetic Fluctuations Spectrograms using Deep Learning Techniques
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• Wave Function Engineering for Spectrally-Uncorrelated Biphotons in the Telecommunication Band based on a Machine-Learning Framework
• Temporal Convolutional Networks for Action Segmentation and Detection
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• Physics-Informed Machine Learning for Grade Prediction in Froth Flotation
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• A Deep Q-Network for the Beer Game: A Deep Reinforcement Learning algorithm to Solve Inventory Optimization Problems
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Self-Supervised Deep Pose Corrections for Robust Visual Odometry
• A Convolutional Neural Network For Cosmic String Detection in CMB Temperature Maps
• Revisiting Bayesian Autoencoders with MCMC
• Black-Box Optimization with Local Generative Surrogates
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• Purifying electron spectra from noisy pulses with machine learning using synthetic Hamilton matrices
• Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring
• Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
• Continuous Gesture Recognition from sEMG Sensor Data with Recurrent Neural Networks and Adversarial Domain Adaptation
• Quantitative Phase Imaging and Artificial Intelligence: A Review
• Behavioral decision-making for urban autonomous driving in the presence of pedestrians using Deep Recurrent Q-Network
• Real time evolution with neural-network quantum states
• An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
• Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking
• Real-time Streaming Video Denoising with Bidirectional Buffers
• Machine Learning with Membership Privacy using Adversarial Regularization
• Automatic Differentiable Monte Carlo: Theory and Application
• Motion-Appearance Co-Memory Networks for Video Question Answering
• End-to-End Supermask Pruning: Learning to Prune Image Captioning Models
• Cervical Optical Coherence Tomography Image Classification Based on Contrastive Self-Supervised Texture Learning
• Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks
• Point Cloud Registration using Representative Overlapping Points
• BlockCNN: A Deep Network for Artifact Removal and Image Compression
• A Light Dual-Task Neural Network for Haze Removal
• Multimodal Polynomial Fusion for Detecting Driver Distraction
• Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering
• Offensive Language and Hate Speech Detection for Danish
• Deep Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement
• Stochastic learning control of inhomogeneous quantum ensembles
• ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
• Reservoirs learn to learn
• Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• Bayesian Neural Architecture Search using A Training-Free Performance Metric
• UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
• StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
• Stochastic Domain Wall-Magnetic Tunnel Junction Artificial Neurons for Noise-Resilient Spiking Neural Networks
• Learning Texture Manifolds with the Periodic Spatial GAN
• ElegansNet: a brief scientific report and initial experiments
• On-the-fly Table Generation
• No More Discrimination: Cross City Adaptation of Road Scene Segmenters
• Effects of spatiotemporal correlations in wind data on neural network-based wind predictions
• Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
• Deep Learning Analysis of Deeply Virtual Exclusive Photoproduction
• Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
• Blind Super-Resolution With Iterative Kernel Correction
• Image Inpainting with Learnable Bidirectional Attention Maps
• Meta-Learning Symmetries by Reparameterization
• NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
• ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation
• Sentence Embeddings in NLI with Iterative Refinement Encoders
• Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
• A deep learning model for burn depth classification using ultrasound imaging
• Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
• Giving Commands to a Self-Driving Car: How to Deal with Uncertain Situations?
• Autoencoders for music sound modeling: a comparison of linear, shallow, deep, recurrent and variational models
• Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
• Conducting Credit Assignment by Aligning Local Representations
• EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching
• Learning Representations from Audio-Visual Spatial Alignment
• Synthetic Elastography using B-mode Ultrasound through a Deep Fully-Convolutional Neural Network
• Learning Intrusion Prevention Policies through Optimal Stopping
• Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
• Encoders Help You Disambiguate Word Senses in Neural Machine Translation
• A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
• World Model as a Graph: Learning Latent Landmarks for Planning
• Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
• Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction
• Learning to Sketch with Deep Q Networks and Demonstrated Strokes
• Pythia: Grammar-Based Fuzzing of REST APIs with Coverage-guided Feedback and Learning-based Mutations
• Abdominal synthetic CT reconstruction with intensity projection prior for MRI-only adaptive radiotherapy
• Low Dimensional Convolutional Neural Network For Solar Flares GOES Time Series Classification
• Cooking State Recognition from Images Using Inception Architecture
• DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
• Image inpainting using frequency domain priors
• Scalable Rule-Based Representation Learning for Interpretable Classification
• Deep Neural Network Architectures for Modulation Classification
• Improving Local Identifiability in Probabilistic Box Embeddings
• ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
• Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion
• Adversarial Text Generation Without Reinforcement Learning
• Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• Graph-based Solutions with Residuals for Intrusion Detection: the Modified E-GraphSAGE and E-ResGAT Algorithms
• Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks
• Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular Networks
• Robot in the mirror: toward an embodied computational model of mirror self-recognition
• Emergence of foveal image sampling from learning to attend in visual scenes
• Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
• SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame
• Robust Compressive Phase Retrieval via Deep Generative Priors
• Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
• Exact constraints and appropriate norms in machine learned exchange-correlation functionals
• Pseudo-Hamiltonian Neural Networks with State-Dependent External Forces
• A Baseline for Few-Shot Image Classification
• Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• Cover Detection using Dominant Melody Embeddings
• Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions
• StoryGAN: A Sequential Conditional GAN for Story Visualization
• Generative Adversarial Networks Applied to Synthetic Financial Scenarios Generation
• XNAS: Neural Architecture Search with Expert Advice
• Factor Augmented Sparse Throughput Deep ReLU Neural Networks for High Dimensional Regression
• Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis
• Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
• Pain level and pain-related behaviour classification using GRU-based sparsely-connected RNNs
• Practical Window Setting Optimization for Medical Image Deep Learning
• Improved uncertainty quantification for neural networks with Bayesian last layer
• Multi-Fidelity Bayesian Optimization via Deep Neural Networks
• Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
• Subregular Complexity and Deep Learning
• Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
• Guardians of the Deep Fog: Failure-Resilient DNN Inference from Edge to Cloud
• Agnostic Lane Detection
• Rethinking Closed-loop Training for Autonomous Driving
• D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization
• Application of machine learning to viscoplastic flow modeling
• Poincaré Wasserstein Autoencoder
• Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using Machine Learning techniques
• Learning Interpretable Rules for Scalable Data Representation and Classification
• The Deep Kernelized Autoencoder
• A Deep Learning Approach to Quasar Continuum Prediction
• Natural Backdoor Attack on Text Data
• Open Set Domain Adaptation by Backpropagation
• Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotion
• MeshSDF: Differentiable Iso-Surface Extraction
• Light-weight CNN-based VVC Inter Partitioning Acceleration
• Analyzing analytical methods: The case of phonology in neural models of spoken language
• Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction
• On the adequacy of untuned warmup for adaptive optimization
• Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
• Deep Learning with Gaussian Differential Privacy
• Understanding and Predicting the Memorability of Outdoor Natural Scenes
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• Comparative study of regression vs pairwise models for surrogate-based heuristic optimisation
• Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
• Causal Generative Neural Networks
• Leveraging the Mathematics of Shape for Solar Magnetic Eruption Prediction
• Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
• Robust Estimation of Hypernasality in Dysarthria with Acoustic Model Likelihood Features
• Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks
• Variational approach to rare event simulation using least-squares regression
• TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
• Graph-based Alignment and Uniformity for Recommendation
• QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers
• Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data
• Controllable Person Image Synthesis with Attribute-Decomposed GAN
• A Hybrid Retrieval-Generation Neural Conversation Model
• Mechanics-Aware Modeling of Cloth Appearance
• Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring
• Subword-augmented Embedding for Cloze Reading Comprehension
• Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
• Permutation Invariant Graph Generation via Score-Based Generative Modeling
• Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Neural Parametric Fokker-Planck Equations
• A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text
• DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer
• Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild
• Transformer Hawkes Process
• Global Encoding for Abstractive Summarization
• The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
• Continual Reinforcement Learning with Complex Synapses
• Deep learning for intensity mapping observations: Component extraction
• End-to-End Multi-Task Learning with Attention
• Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
• Autonomous Power Allocation based on Distributed Deep Learning for Device-to-Device Communication Underlaying Cellular Network
• Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
• Deep Gaussian Processes with Convolutional Kernels
• Dense Pixel-Labeling for Reverse-Transfer and Diagnostic Learning on Lung Ultrasound for COVID-19 and Pneumonia Detection
• Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
• HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• NewsPod: Automatic and Interactive News Podcasts
• Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
• Machine-learning assisted quantum control in random environment
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• On Learning Associations of Faces and Voices
• A deep learning approach for lower back-pain risk prediction during manual lifting
• Algorithmic Composition of Melodies with Deep Recurrent Neural Networks
• Weakly-supervised Visual Grounding of Phrases with Linguistic Structures
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training
• Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
• Graph Geometry Interaction Learning
• Probabilistic Dual Network Architecture Search on Graphs
• Deep learning techniques applied to the physics of extensive air showers
• Self-Supervised Variational Auto-Encoders
• Deep Online Correction for Monocular Visual Odometry
• Rotor Localization and Phase Mapping of Cardiac Excitation Waves using Deep Neural Networks
• Slum Segmentation and Change Detection : A Deep Learning Approach
• not-MIWAE: Deep Generative Modelling with Missing not at Random Data
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
• Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
• Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins
• Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM)
• CLDG: Contrastive Learning on Dynamic Graphs
• Learning Two-Branch Neural Networks for Image-Text Matching Tasks
• JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions
• DNN-Based Speech Presence Probability Estimation for Multi-Frame Single-Microphone Speech Enhancement
• Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs
• Towards Deep Cellular Phenotyping in Placental Histology
• Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
• Robot self/other distinction: active inference meets neural networks learning in a mirror
• Distilled Neural Networks for Efficient Learning to Rank
• Scheduling Dimension Reduction of LPV Models -- A Deep Neural Network Approach
• ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
• Real-Time Machine-Learning-Based Optimization Using Input Convex Long Short-Term Memory Network
• Countdown Regression: Sharp and Calibrated Survival Predictions
• Confidence Prediction for Lexicon-Free OCR
• Graph Neural Networks with Diverse Spectral Filtering
• Deep Residual Echo Suppression with A Tunable Tradeoff Between Signal Distortion and Echo Suppression
• Acceleration of Gradient-based Path Integral Method for Efficient Optimal and Inverse Optimal Control
• BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
• Face X-ray for More General Face Forgery Detection
• Malicious code detection in android: the role of sequence characteristics and disassembling methods
• DarkDeblur: Learning single-shot image deblurring in low-light condition
• No Padding Please: Efficient Neural Handwriting Recognition
• An Exploration of Word Embedding Initialization in Deep-Learning Tasks
• ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
• Feedback Control For Cassie With Deep Reinforcement Learning
• Deep Learning in Bioinformatics
• Deep Counterfactual Regret Minimization
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• Pre-train and Learn: Preserve Global Information for Graph Neural Networks
• LEGO: Learning Edge with Geometry all at Once by Watching Videos
• Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
• Solving Arithmetic Word Problems by Scoring Equations with Recursive Neural Networks
• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Constrained Learning with Non-Convex Losses
• Sample-Efficient Imitation Learning via Generative Adversarial Nets
• Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning
• Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
• PonderNet: Learning to Ponder
• Practical Block-wise Neural Network Architecture Generation
• MRI Cross-Modality NeuroImage-to-NeuroImage Translation
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Local Adaptivity in Federated Learning: Convergence and Consistency
• Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
• FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks
• SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
• Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
• The Atari Grand Challenge Dataset
• Automatic detection of microsleep episodes with deep learning
• Esophageal virtual disease landscape using mechanics-informed machine learning
• CoT: Cooperative Training for Generative Modeling of Discrete Data
• MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series
• Variational Inference for Gaussian Process Models with Linear Complexity
• Sentiment Classification in Swahili Language Using Multilingual BERT
• Learning Clustered Representation for Complex Free Energy Landscapes
• Deep Generative Modeling for Scene Synthesis via Hybrid Representations
• DeepLofargram: A Deep Learning based Fluctuating Dim Frequency Line Detection and Recovery
• Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
• Semi-Supervised Neural System for Tagging, Parsing and Lematization
• Embedding API Dependency Graph for Neural Code Generation
• Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
• FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction
• A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension
• End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation Detection using Wearables
• High-Resolution Multispectral Dataset for Semantic Segmentation
• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
• Towards causal generative scene models via competition of experts
• Fast Hierarchical Games for Image Explanations
• Unified Supervised-Unsupervised (SUPER) Learning for X-ray CT Image Reconstruction
• Learning Spatial Awareness to Improve Crowd Counting
• CoReFusion: Contrastive Regularized Fusion for Guided Thermal Super-Resolution
• Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
• Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis
• Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size
• New Fairness Metrics for Recommendation that Embrace Differences
• Achieving Equalized Odds by Resampling Sensitive Attributes
• BeamLearning: an end-to-end Deep Learning approach for the angular localization of sound sources using raw multichannel acoustic pressure data
• CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
• Learning Vehicle Trajectory Uncertainty
• Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
• CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality
• An End-to-End Network for Emotion-Cause Pair Extraction
• Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation
• A practical tutorial on Variational Bayes
• Counterfactual Zero-Shot and Open-Set Visual Recognition
• Sentence Centrality Revisited for Unsupervised Summarization
• A Critical Analysis of Biased Parsers in Unsupervised Parsing
• Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
• TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer
• Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
• The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge
• Controllable Video Captioning with an Exemplar Sentence
• Understanding and Modeling Passive-Negative Feedback for Short-video Sequential Recommendation
• Automated Self-Supervised Learning for Graphs
• PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
• Automating Privilege Escalation with Deep Reinforcement Learning
• A large-scale evaluation framework for EEG deep learning architectures
• BatMobility: Towards Flying Without Seeing for Autonomous Drones
• Asymmetric self-play for automatic goal discovery in robotic manipulation
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Modeling Electromagnetic Navigation Systems for Medical Applications using Random Forests and Artificial Neural Networks
• A Tour of Reinforcement Learning: The View from Continuous Control
• Content Adaptive Optimization for Neural Image Compression
• Neural Approximate Sufficient Statistics for Implicit Models
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• Robust Keystroke Biometric Anomaly Detection
• A Spectral Energy Distance for Parallel Speech Synthesis
• Part-Guided Attention Learning for Vehicle Instance Retrieval
• Deep Learning-enabled MCMC for Probabilistic State Estimation in District Heating Grids
• Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution
• Provably Efficient Imitation Learning from Observation Alone
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning
• Data Leakage and Evaluation Issues in Micro-Expression Analysis
• Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
• Self-supervised EEG Representation Learning for Automatic Sleep Staging
• Attacking Speaker Recognition With Deep Generative Models
• Learning from Multi-View Multi-Way Data via Structural Factorization Machines
• Neural network-based anomaly detection for high-resolution X-ray spectroscopy
• DeepOrigin: End-to-End Deep Learning for Detection of New Malware Families
• Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging
• A Neural Scaling Law from the Dimension of the Data Manifold
• Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
• Talking Face Generation by Conditional Recurrent Adversarial Network
• Read + Verify: Machine Reading Comprehension with Unanswerable Questions
• MIM: A deep mixed residual method for solving high-order partial differential equations
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
• Optical information transfer through random unknown diffusers using electronic encoding and diffractive decoding
• PCNN: A physics-constrained neural network for multiphase flows
• Learning Household Task Knowledge from WikiHow Descriptions
• Toward Semi-Automatic Misconception Discovery Using Code Embeddings
• Optical Flow Estimation using a Spatial Pyramid Network
• Extractive Summarization of EHR Discharge Notes
• Scale-recurrent Network for Deep Image Deblurring
• Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languages
• Bayesian Renormalization
• Multi-Robot Coordination and Layout Design for Automated Warehousing
• Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic Prediction
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Image Inpainting for Irregular Holes Using Partial Convolutions
• Basis Pursuit Denoising via Recurrent Neural Network Applied to Super-resolving SAR Tomography
• GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
• Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation
• Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution
• KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey
• Counterfactual Collaborative Reasoning
• Single Day Outdoor Photometric Stereo
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
• Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning
• YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
• A General Approach to Dropout in Quantum Neural Networks
• Deep Perceptual Compression
• Image Based Food Energy Estimation With Depth Domain Adaptation
• Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
• ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay
• Calibrated Reliable Regression using Maximum Mean Discrepancy
• Identification of point sources in gamma rays using U-shaped convolutional neural networks and a data challenge
• STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
• Regularizing Activation Distribution for Training Binarized Deep Networks
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• Accelerated Stochastic Power Iteration
• Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding
• Machine Learning for Observables: Reactant to Product State Distributions for Atom-Diatom Collisions
• A priori and a posteriori error estimates for the Deep Ritz method applied to the Laplace and Stokes problem
• Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation
• Learning Wake-Sleep Recurrent Attention Models
• End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks
• Toward Drug-Target Interaction Prediction via Ensemble Modeling and Transfer Learning
• Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
• Tackling the Curse of Dimensionality in Fractional and Tempered Fractional PDEs with Physics-Informed Neural Networks
• RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection
• DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting
• A Behavioral Approach to Visual Navigation with Graph Localization Networks
• ivis Dimensionality Reduction Framework for Biomacromolecular Simulations
• Domain Adaptive Dialog Generation via Meta Learning
• Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations
• Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models
• Low Resource Neural Machine Translation: A Benchmark for Five African Languages
• Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
• Sequential Recommendation with Graph Neural Networks
• Dynamic Fusion Networks for Machine Reading Comprehension
• DPDnet: A Robust People Detector using Deep Learning with an Overhead Depth Camera
• The Fraction of Broken Waves in Natural Surf Zones
• A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus
• The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
• Learning Domain-Independent Planning Heuristics with Hypergraph Networks
• An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation
• Variational Recurrent Models for Solving Partially Observable Control Tasks
• Hyperparameter tuning of optical neural network classifiers for high-order gaussian beams
• Label Efficient Semi-Supervised Learning via Graph Filtering
• DeepFlash: Turning a Flash Selfie into a Studio Portrait
• GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
• Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
• FedEval: A Holistic Evaluation Framework for Federated Learning
• End-to-End Learning for the Deep Multivariate Probit Model
• Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning
• MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
• Benchmarking deep inverse models over time, and the neural-adjoint method
• MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution
• Variational Memory Addressing in Generative Models
• Minimal Effort Back Propagation for Convolutional Neural Networks
• Meta Networks for Neural Style Transfer
• Combining Strategic Learning and Tactical Search in Real-Time Strategy Games
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation
• Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays
• PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
• Using machine learning to parametrize postmerger signals from binary neutron stars
• In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
• Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings
• Label Dependent Attention Model for Disease Risk Prediction Using Multimodal Electronic Health Records
• Dropout as a Low-Rank Regularizer for Matrix Factorization
• Transition Propagation Graph Neural Networks for Temporal Networks
• Position-aware Self-attention with Relative Positional Encodings for Slot Filling
• Fishing for Clickbaits in Social Images and Texts with Linguistically-Infused Neural Network Models
• Video Compression through Image Interpolation
• Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
• ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
• Remote Sensing Novel View Synthesis with Implicit Multiplane Representations
• A matrix-inverse-free implementation of the MU-MIMO WMMSE beamforming algorithm
• Combating Human Trafficking with Deep Multimodal Models
• Glancing Transformer for Non-Autoregressive Neural Machine Translation
• A deep learning method for the trajectory reconstruction of cosmic rays with the DAMPE mission
• Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions
• Alpha-Beta Divergence For Variational Inference
• Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations
• LSTM Benchmarks for Deep Learning Frameworks
• Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes
• Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
• xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
• Compatible and Diverse Fashion Image Inpainting
• Optimal Thermometers with Spin Networks
• Building a Neural Machine Translation System Using Only Synthetic Parallel Data
• HOList: An Environment for Machine Learning of Higher-Order Theorem Proving
• DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News
• Industrial Scale Privacy Preserving Deep Neural Network
• Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
• Malicious Code Detection: Run Trace Output Analysis by LSTM
• Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially-Aware Language Acquisition
• Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
• Fast Task Inference with Variational Intrinsic Successor Features
• Linear-Model-inspired Neural Network for Electromagnetic Inverse Scattering
• deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
• A Bayesian approach to tissue-fraction estimation for oncological PET segmentation
• Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data
• Investigating and Modeling the Dynamics of Long Ties
• Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks
• A Deep Generative Model of Speech Complex Spectrograms
• Early detection of sepsis utilizing deep learning on electronic health record event sequences
• Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization
• A Deep Double Ritz Method (D${}^2$RM) for solving Partial Differential Equations using Neural Networks
• Security Aspects of Quantum Machine Learning: Opportunities, Threats and Defenses
• NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators with 3D-Stacked-DRAM
• Deep-learning-based reconstruction of the neutrino direction and energy for in-ice radio detectors
• Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views
• TransEM:Residual Swin-Transformer based regularized PET image reconstruction
• From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts
• Multi-task convolutional neural network for image aesthetic assessment
• Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling
• Particle Identification In Camera Image Sensors Using Computer Vision
• Multitask Learning for Emotion and Personality Detection
• A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition
• Predicting Audience's Laughter Using Convolutional Neural Network
• Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework
• Microparticle cloud imaging and tracking for data-driven plasma science
• Detecting Compressed Cleartext Traffic from Consumer Internet of Things Devices
• GuessWhat?! Visual object discovery through multi-modal dialogue
• Weakly Supervised Change Detection Using Guided Anisotropic Difusion
• What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
• Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
• Comprehensive Mapping of Continuous/Switching Circuits in CCM and DCM to Machine Learning Domain using Homogeneous Graph Neural Networks
• Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture
• Multi-scale Deep Neural Networks for Solving High Dimensional PDEs
• Reducing Data Complexity using Autoencoders with Class-informed Loss Functions
• Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding
• Null Hypothesis Test for Anomaly Detection
• Revisiting Neural Retrieval on Accelerators
• Predicting Information Pathways Across Online Communities
• SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning
• Neural Segmental Hypergraphs for Overlapping Mention Recognition
• Semi-Supervised Visual Representation Learning for Fashion Compatibility
• LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis
• Understanding Unintended Memorization in Federated Learning
• Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss
• Meta-Adaptive Nonlinear Control: Theory and Algorithms
• A novel method for error analysis in radiation thermometry with application to industrial furnaces
• Deep Architectures for Modulation Recognition
• Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks using Deep Reinforcement Learning
• More light on Higgs flavor at the LHC: Higgs couplings to light quarks through $h+\gamma$ production
• Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning
• Multi-agent Trajectory Prediction with Fuzzy Query Attention
• Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
• Conditional Image-to-Image Translation
• Neural Predictor for Neural Architecture Search
• Deep learning classification of chest x-ray images
• Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads
• Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
• An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
• Performance Guaranteed Network Acceleration via High-Order Residual Quantization
• Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
• Fast and Accurate Modeling of Transient-State Gradient-Spoiled Sequences by Recurrent Neural Networks
• Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization
• Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions
• SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring
• prDeep: Robust Phase Retrieval with a Flexible Deep Network
• Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction
• Retinal Optic Disc Segmentation using Conditional Generative Adversarial Network
• A Connectome Based Hexagonal Lattice Convolutional Network Model of the Drosophila Visual System
• Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection
• Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
• Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
• Generative adversarial network for super-resolution imaging through a fiber
• Anticipating many futures: Online human motion prediction and synthesis for human-robot collaboration
• A Neural-Network Framework for the Design of Individualised Hearing-Loss Compensation
• Many-body calculations for periodic materials via quantum machine learning
• Inverse Renormalization Group based on Image Super-Resolution using Deep Convolutional Networks
• Learning thermoacoustic interactions in combustors using a physics-informed neural network
• A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks
• Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• Phase Retrieval and Design with Automatic Differentiation
• Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data
• Generalised gravitational burst generation with Generative Adversarial Networks
• A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
• Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes
• Gaussian Process Prior Variational Autoencoders
• SCAN: Sliding Convolutional Attention Network for Scene Text Recognition
• Transportation Density Reduction Caused by City Lockdowns Across the World during the COVID-19 Epidemic: From the View of High-resolution Remote Sensing Imagery
• Watch What You Just Said: Image Captioning with Text-Conditional Attention
• Detecting Hallucinated Content in Conditional Neural Sequence Generation
• A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
• Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
• Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
• Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual
• Human Satisfaction as the Ultimate Goal in Ridesharing
• Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
• On the Utility of Gradient Compression in Distributed Training Systems
• Learning Object Relation Graph and Tentative Policy for Visual Navigation
• IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary
• Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease
• 3D Photography using Context-aware Layered Depth Inpainting
• Learning by Semantic Similarity Makes Abstractive Summarization Better
• Learning Discriminative Features for Crowd Counting
• Cascaded Refinement Network for Point Cloud Completion
• Learning Convolutional Networks for Content-weighted Image Compression
• SafeCritic: Collision-Aware Trajectory Prediction
• MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation
• Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation
• Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images
• Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
• Efficient Computation in Adaptive Artificial Spiking Neural Networks
• Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
• DeepKey: An EEG and Gait Based Dual-Authentication System
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
• Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
• Grad DFT: a software library for machine learning enhanced density functional theory
• A shallow physics-informed neural network for solving partial differential equations on surfaces
• Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
• Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions
• Neurons on Amoebae
• Modeling Lost Information in Lossy Image Compression
• Neural Attribute Machines for Program Generation
• Building-road Collaborative Extraction from Remotely Sensed Images via Cross-Interaction
• Deep Learning-based galaxy image deconvolution
• ACDC: A Structured Efficient Linear Layer
• Transferring Cross-domain Knowledge for Video Sign Language Recognition
• LaFIn: Generative Landmark Guided Face Inpainting
• Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting
• Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
• Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
• Protein Secondary Structure Prediction Using Deep Multi-scale Convolutional Neural Networks and Next-Step Conditioning
• Adversarial Contrastive Estimation
• Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
• Stories for Images-in-Sequence by using Visual and Narrative Components
• Weakly-supervised Contextualization of Knowledge Graph Facts
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
• Getting To Know You: User Attribute Extraction from Dialogues
• FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold
• Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders
• Semantic Compositional Networks for Visual Captioning
• Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling
• Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Mixing ADAM and SGD: a Combined Optimization Method
• Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• STAR: Sparse Transformer-based Action Recognition
• Drug-Target Interaction Prediction with Graph Attention networks
• Quantile QT-Opt for Risk-Aware Vision-Based Robotic Grasping
• Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
• Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
• Model Order Selection in DoA Scenarios via Cross-Entropy based Machine Learning Techniques
• Deep Spatio-Temporal Forecasting of Electrical Vehicle Charging Demand
• Joint NN-Supported Multichannel Reduction of Acoustic Echo, Reverberation and Noise
• Rotation-Sensitive Regression for Oriented Scene Text Detection
• Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• SPI: Automated Identification of Security Patches via Commits
• Edge Representation Learning with Hypergraphs
• Training Agents using Upside-Down Reinforcement Learning
• Analytic Continued Fractions for Regression: A Memetic Algorithm Approach
• Bridging Knowledge Graphs to Generate Scene Graphs
• TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval
• GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters
• Learning Deep Analysis Dictionaries for Image Super-Resolution
• Adversarial Representation Active Learning
• Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation
• Learning to be a Statistician: Learned Estimator for Number of Distinct Values
• Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals
• Generative Latent Flow
• Detrending Exoplanetary Transit Light Curves with Long Short-Term Memory Networks
• A Geometric Approach to Obtain a Bird's Eye View from an Image
• Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains
• Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System
• Robust Lexical Features for Improved Neural Network Named-Entity Recognition
• Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty
• Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
• DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer
• $L_0$-ARM: Network Sparsification via Stochastic Binary Optimization
• Extending GCC-PHAT using Shift Equivariant Neural Networks
• Stein variational gradient descent with local approximations
• Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?
• Transformation Autoregressive Networks
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• Generalized Hindsight for Reinforcement Learning
• Cross-sectional Stock Price Prediction using Deep Learning for Actual Investment Management
• Supply-Power-Constrained Cable Capacity Maximization Using Multi-Layer Neural Networks
• Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
• Hybrid Loss for Learning Single-Image-based HDR Reconstruction
• Acoustic Leak Detection in Water Networks
• Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction
• Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
• Bottom-up Broadcast Neural Network For Music Genre Classification
• Contrastive Visual-Linguistic Pretraining
• Occlusion Aware Unsupervised Learning of Optical Flow
• Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Fault-tolerant quantum algorithms for quantum molecular systems: A survey
• Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems
• Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
• Topology-Informed Machine Learning for Efficient Prediction of Solid Oxide Fuel Cell Electrode Polarization
• Transfer Learning for Clinical Time Series Analysis using Recurrent Neural Networks
• Towards physics-informed neural networks for landslide prediction
• Self-supervised Representation Learning With Path Integral Clustering For Speaker Diarization
• Reduced-order modeling of unsteady fluid flow using neural network ensembles
• Pointer Graph Networks
• Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
• Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
• Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
• Learning Human Optical Flow
• Stroke-based sketched symbol reconstruction and segmentation
• RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering
• Learning to Collocate Neural Modules for Image Captioning
• Three dimensional blind image deconvolution for fluorescence microscopy using generative adversarial networks
• Characterizing and Improving Stability in Neural Style Transfer
• Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering
• DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
• Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
• Efficient nonparametric statistical inference on population feature importance using Shapley values
• Self-supervised Low Light Image Enhancement and Denoising
• Learning Robotic Manipulation through Visual Planning and Acting
• Quantum Generative Adversarial Networks For Anomaly Detection In High Energy Physics
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• A Pixel-Based Framework for Data-Driven Clothing
• Recommending Solution Paths for Solving Optimization Problems with Quantum Computing
• Deep Robust Kalman Filter
• Experience Replay with Likelihood-free Importance Weights
• Data-driven construction of stochastic reduced dynamics encoded with non-Markovian features
• Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
• End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks
• DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Hierarchical Interdisciplinary Topic Detection Model for Research Proposal Classification
• Bridge Damage Detection using a Single-Stage Detector and Field Inspection Images
• A flexible event reconstruction based on machine learning and likelihood principles
• Open video data sharing in developmental and behavioural science
• m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural Networks
• Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging
• Modeling the sea-surface $p$CO${}_2$ of the central Bay of Bengal region using machine learning algorithms
• An Introduction to Deep Learning for the Physical Layer
• SYMBA: Symbolic Computation of Squared Amplitudes in High Energy Physics with Machine Learning
• Search for flavour-changing neutral-current couplings between the top quark and the photon with the ATLAS detector at $\sqrt{s}=13$ TeV
• RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations
• White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks
• BlockQNN: Efficient Block-wise Neural Network Architecture Generation
• Real-time Pupil Tracking from Monocular Video for Digital Puppetry
• Shape Matters: Understanding the Implicit Bias of the Noise Covariance
• Quantum reinforcement learning in continuous action space
• Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization
• Solving Differential Equations Using Neural Network Solution Bundles
• Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
• RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
• Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
• improving partition-block-based acoustic echo canceler in under-modeling scenarios
• Identifying Flux Rope Signatures Using a Deep Neural Network
• Non-intrusive and semi-intrusive uncertainty quantification of a multiscale in-stent restenosis model
• 1-Dimensional polynomial neural networks for audio signal related problems
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Phase Conductor on Multi-layered Attentions for Machine Comprehension
• Replay and Synthetic Speech Detection with Res2net Architecture
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• Reply With: Proactive Recommendation of Email Attachments
• Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture
• Learning to Learn Variational Semantic Memory
• Deep4Air: A Novel Deep Learning Framework for Airport Airside Surveillance
• Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem
• Hyperparameter Learning via Distributional Transfer
• Enhancement Of Coded Speech Using a Mask-Based Post-Filter
• Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier
• Estimating and Improving Fairness with Adversarial Learning
• Stochastic Answer Networks for SQuAD 2.0
• Ensembling Low Precision Models for Binary Biomedical Image Segmentation
• Finding Better Topologies for Deep Convolutional Neural Networks by Evolution
• A Shallow Ritz Method for Elliptic Problems with Singular Sources
• Learning Sequence Encoders for Temporal Knowledge Graph Completion
• Neural networks for on-the-fly single-shot state classification
• Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation
• Visual Parser: Representing Part-whole Hierarchies with Transformers
• Evaluating uncertainties in electrochemical impedance spectra of solid oxide fuel cells
• Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms
• A Deep Learning Approach to Mapping Irrigation: IrrMapper-U-Net
• Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
• Consensus-based Sequence Training for Video Captioning
• Mimicry: Towards the Reproducibility of GAN Research
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Domain specific cues improve robustness of deep learning based segmentation of ct volumes
• Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks
• Classifier-agnostic saliency map extraction
• A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models
• Meta-Learning for Stochastic Gradient MCMC
• Estimation of moisture content distribution in porous foam using microwave tomography with neural networks
• Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds
• FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
• DDFlow: Learning Optical Flow with Unlabeled Data Distillation
• Voice Conversion with Conditional SampleRNN
• Image Deconvolution with Deep Image and Kernel Priors
• Towards Multi-pose Guided Virtual Try-on Network
• VIGAN: Missing View Imputation with Generative Adversarial Networks
• Graph Convolutional Networks for Classification with a Structured Label Space
• Towards Learning to Detect and Predict Contact Events on Vision-based Tactile Sensors
• Real-time Sub-milliwatt Epilepsy Detection Implemented on a Spiking Neural Network Edge Inference Processor
• Deep Task-Based Analog-to-Digital Conversion
• Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
• Inversion of Time-Lapse Surface Gravity Data for Detection of 3D CO${}_2$ Plumes via Deep Learning
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
• A Bayesian Deep Learning Approach to Near-Term Climate Prediction
• Interactive dimensionality reduction using similarity projections
• Is Deeper Better only when Shallow is Good?
• Bayesian Tensorized Neural Networks with Automatic Rank Selection
• Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
• Machine learning surrogates for efficient hydrologic modeling: Insights from stochastic simulations of managed aquifer recharge
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• An Adaptive Random Path Selection Approach for Incremental Learning
• Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
• MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters
• Using Artificial Tokens to Control Languages for Multilingual Image Caption Generation
• Stochastic Normalizing Flows
• Improved Optimization for the Neural-network Quantum States and Tests on the Chromium Dimer
• Robust partial Fourier reconstruction for diffusion-weighted imaging using a recurrent convolutional neural network
• Nonlinear Multiview Analysis: Identifiability and Neural Network-assisted Implementation
• Dynamics-aware Embeddings
• Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint
• GIKT: A Graph-based Interaction Model for Knowledge Tracing
• IGUANe: a 3D generalizable CycleGAN for multicenter harmonization of brain MR images
• Neural Networks for Cross-lingual Negation Scope Detection
• Learning Autoencoders with Relational Regularization
• Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
• MedAL: Deep Active Learning Sampling Method for Medical Image Analysis
• A Digital Twin for Reconfigurable Intelligent Surface Assisted Wireless Communication
• Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition
• Deep learning for solution and inversion of structural mechanics and vibrations
• The MultiBERTs: BERT Reproductions for Robustness Analysis
• DeepGMR: Learning Latent Gaussian Mixture Models for Registration
• Topological Semantic Mapping by Consolidation of Deep Visual Features
• Evaluating the Robustness of Self-Supervised Learning in Medical Imaging
• Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation
• DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation
• High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation
• Predicting cognitive scores with graph neural networks through sample selection learning
• Determination of the Semion Code Threshold using Neural Decoders
• An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Sequential convolutional network for behavioral pattern extraction in gait recognition
• Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation
• Interpreting Super-Resolution Networks with Local Attribution Maps
• Advancing GraphSAGE with A Data-Driven Node Sampling
• Unsupervised Person Image Generation with Semantic Parsing Transformation
• ConceptBeam: Concept Driven Target Speech Extraction
• Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
• Multimodal Estimation of End Point Force During Quasi-dynamic and Dynamic Muscle Contractions Using Deep Learning
• Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
• Riesz-Quincunx-UNet Variational Auto-Encoder for Satellite Image Denoising
• Behavior Self-Organization Supports Task Inference for Continual Robot Learning
• Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
• Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification
• Are All Languages Created Equal in Multilingual BERT?
• Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection
• Deep multi-task mining Calabi-Yau four-folds
• Multi-Label Learning from Medical Plain Text with Convolutional Residual Models
• Evaluation Of Hidden Markov Models Using Deep CNN Features In Isolated Sign Recognition
• xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks
• Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks
• MIC: Mining Interclass Characteristics for Improved Metric Learning
• Continuous Regularized Wasserstein Barycenters
• Deep Neural Network Inverse Design of Integrated Nanophotonic Devices
• NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach
• Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events
• Ancient-Modern Chinese Translation with a Large Training Dataset
• M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation
• Improving novelty detection with generative adversarial networks on hand gesture data
• Deep Learning Framework for Multi-Round Service Bundle Recommendation in Iterative Mashup Development
• Tinto: Multisensor Benchmark for 3D Hyperspectral Point Cloud Segmentation in the Geosciences
• Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Networks
• Using Artificial Neural Networks to extract the 21-cm Global Signal from the EDGES data
• RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
• A neural network classifier for electron identification on the DAMPE experiment
• Towards Interactive Image Inpainting via Sketch Refinement
• Spiking Neural Network Nonlinear Demapping on Neuromorphic Hardware for IM/DD Optical Communication
• BIRNet: Brain Image Registration Using Dual-Supervised Fully Convolutional Networks
• Positivity Bias in Customer Satisfaction Ratings
• DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• Deep Learning for Communication over Dispersive Nonlinear Channels: Performance and Comparison with Classical Digital Signal Processing
• On the Sample Complexity of Stability Constrained Imitation Learning
• Knowledge discovery from emergency ambulance dispatch during COVID-19: A case study of Nagoya City, Japan
• Multitask Balanced and Recalibrated Network for Medical Code Prediction
• Detecting COVID-19 from digitized ECG printouts using 1D convolutional neural networks
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• Deeptime: a Python library for machine learning dynamical models from time series data
• InterpNET: Neural Introspection for Interpretable Deep Learning
• An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
• UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons
• Deep learning enhanced noise spectroscopy of a spin qubit environment
• Discriminative Sentence Modeling for Story Ending Prediction
• Temporal Recurrent Networks for Online Action Detection
• DeepMovie: Using Optical Flow and Deep Neural Networks to Stylize Movies
• Multi-class Classification without Multi-class Labels
• SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
• Feature learning for efficient ASR-free keyword spotting in low-resource languages
• Learning by Abstraction: The Neural State Machine
• Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
• On the Benefits of Early Fusion in Multimodal Representation Learning
• GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction
• Link Prediction via Graph Attention Network
• A general framework for multi-step ahead adaptive conformal heteroscedastic time series forecasting
• Zero-Shot Dialog Generation with Cross-Domain Latent Actions
• Pollen Grain Microscopic Image Classification Using an Ensemble of Fine-Tuned Deep Convolutional Neural Networks
• Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering
• Crowd Counting via Hierarchical Scale Recalibration Network
• Stereoscopic Neural Style Transfer
• Light Field Synthesis by Training Deep Network in the Refocused Image Domain
• Language Modelling with Pixels
• Rapid Response Crop Maps in Data Sparse Regions
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• View-based Explanations for Graph Neural Networks
• Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
• Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
• MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weather
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Structure Probing Neural Network Deflation
• Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
• A Hybrid Model-based and Data-driven Approach to Spectrum Sharing in mmWave Cellular Networks
• Feature Re-Learning with Data Augmentation for Video Relevance Prediction
• Learning Blended, Precise Semantic Program Embeddings
• An Improved Normed-Deformable Convolution for Crowd Counting
• ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples
• Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
• Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables
• Adversarial attacks on Copyright Detection Systems
• Self-Supervised Reinforcement Learning for Recommender Systems
• Predicting Evacuation Decisions using Representations of Individuals' Pre-Disaster Web Search Behavior
• IQ of Neural Networks
• Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs
• Machine learning for metal additive manufacturing: Predicting temperature and melt pool fluid dynamics using physics-informed neural networks
• Transfer Learning of Artist Group Factors to Musical Genre Classification
• GraphAD: A Graph Neural Network for Entity-Wise Multivariate Time-Series Anomaly Detection
• Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
• Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds
• Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation
• A Synergistic Kalman- and Deep Postfiltering Approach to Acoustic Echo Cancellation
• Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES
• Learning to Interpret Satellite Images in Global Scale Using Wikipedia
• An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms
• Transfer learning of phase transitions in percolation and directed percolation
• Solving differential equations with unknown constitutive relations as recurrent neural networks
• VRSTC: Occlusion-Free Video Person Re-Identification
• Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method
• One-Shot Relational Learning for Knowledge Graphs
• SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud
• Dynamic imaging using Motion-Compensated SmooThness Regularization on Manifolds (MoCo-SToRM)
• Towards Speech Emotion Recognition "in the wild" using Aggregated Corpora and Deep Multi-Task Learning
• Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
• Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data
• CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism
• Multi-scale Time-stepping of Partial Differential Equations with Transformers
• A Hierarchical Latent Structure for Variational Conversation Modeling
• Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries
• Matrix Element Regression with Deep Neural Networks -- breaking the CPU barrier
• Harnessing Structures for Value-Based Planning and Reinforcement Learning
• VideoCapsuleNet: A Simplified Network for Action Detection
• A Weakly Supervised Approach for Estimating Spatial Density Functions from High-Resolution Satellite Imagery
• SCSS-Net: Solar Corona Structures Segmentation by Deep Learning
• Semi-Supervised Deep Metrics for Image Registration
• A scalable saliency-based Feature selection method with instance level information
• DRINet++: Efficient Voxel-as-point Point Cloud Segmentation
• Simulation and Optimisation of Air Conditioning Systems using Machine Learning
• Multi-task Learning for Voice Trigger Detection
• Soft-Root-Sign Activation Function
• TinyTurbo: Efficient Turbo Decoders on Edge
• Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information
• Hyper-Convolution Networks for Biomedical Image Segmentation
• Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
• Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
• Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network
• Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps
• Automatic Classification of Music Genre using Masked Conditional Neural Networks
• Segmentation of Liver Lesions with Reduced Complexity Deep Models
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• Overcoming limited battery data challenges: A coupled neural network approach
• Imaging Conductivity from Current Density Magnitude using Neural Networks
• Video Quality Assessment with Texture Information Fusion for Streaming Applications
• Machine Learning Statistical Gravity from Multi-Region Entanglement Entropy
• LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
• Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails
• Automatic Segmentation and Location Learning of Neonatal Cerebral Ventricles in 3D Ultrasound Data Combining CNN and CPPN
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
• Deep Policy Iteration with Integer Programming for Inventory Management
• Face Anti-Spoofing Via Disentangled Representation Learning
• Score and Lyrics-Free Singing Voice Generation
• Training Deeper Neural Machine Translation Models with Transparent Attention
• Do Neural Nets Learn Statistical Laws behind Natural Language?
• Deep Reinforcement Learning Radio Control and Signal Detection with KeRLym, a Gym RL Agent
• Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
• Certified Robustness to Adversarial Word Substitutions
• The Riemannian Geometry of Deep Generative Models
• Combining stochastic density functional theory with deep potential molecular dynamics to study warm dense matter
• On Hallucination and Predictive Uncertainty in Conditional Language Generation
• Deep Learning Architecture Based Approach For 2D-Simulation of Microwave Plasma Interaction
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory
• An Attempt towards Interpretable Audio-Visual Video Captioning
• Visual Attention Prompted Prediction and Learning
• GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs
• Neural Networks Potential from the Bispectrum Component: A Case Study on Crystalline Silicon
• Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
• Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface
• HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation
• Rigid Motion Invariant Statistical Shape Modeling based on Discrete Fundamental Forms
• GraFormer: Graph Convolution Transformer for 3D Pose Estimation
• Multimodal Imaging-based Material Mass Density Estimation for Proton Therapy Using Physics-Constrained Deep Learning
• Comprehension-guided referring expressions
• Memory-Attended Recurrent Network for Video Captioning
• Road Roughness Estimation Using Machine Learning
• Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments
• A Comparison of Residual-based Methods on Fault Detection
• Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
• Deep Relevance Ranking Using Enhanced Document-Query Interactions
• Probing effective field theory operators in the associated production of top quarks with a Z boson in multilepton final states at $\sqrt{s}=$ 13 TeV
• Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
• Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems
• Can Active Memory Replace Attention?
• Dissipation-induced collective advantage of a quantum thermal machine
• ADMM-DAD net: a deep unfolding network for analysis compressed sensing
• Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
• Extractive Summarization as Text Matching
• Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
• GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions
• Image Denoising using Attention-Residual Convolutional Neural Networks
• Generating Diverse and Meaningful Captions
• Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
• An End-to-end Deep Learning Approach for Landmark Detection and Matching in Medical Images
• Avoiding Echo-Responses in a Retrieval-Based Conversation System
• Text-Free Prosody-Aware Generative Spoken Language Modeling
• EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision
• Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• Machine learning methods for constructing probabilistic Fermi-LAT catalogs
• Synthesizing lesions using contextual GANs improves breast cancer classification on mammograms
• Neural Diffusion Model for Microscopic Cascade Prediction
• CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models
• Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
• Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
• Iteratively Training Look-Up Tables for Network Quantization
• DRL-Assisted Resource Allocation for NOMA-MEC Offloading with Hybrid SIC
• RDEC: Integrating Regularization into Deep Embedded Clustering for Imbalanced Datasets
• On the Effectiveness of Least Squares Generative Adversarial Networks
• Region Based Adversarial Synthesis of Facial Action Units
• Deep UL2DL: Channel Knowledge Transfer from Uplink to Downlink
• Hierarchical Discrete Distribution Decomposition for Match Density Estimation
• A near-autonomous and incremental intrusion detection system through active learning of known and unknown attacks
• A Deep Registration Method for Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis
• Deep Neural Network Framework Based on Backward Stochastic Differential Equations for Pricing and Hedging American Options in High Dimensions
• Back to the Formula -- LHC Edition
• Spatial Dual-Modality Graph Reasoning for Key Information Extraction
• Shaping Belief States with Generative Environment Models for RL
• PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving
• Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting
• Learning to Represent Words in Context with Multilingual Supervision
• CL4AC: A Contrastive Loss for Audio Captioning
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems
• Cramer-Wold AutoEncoder
• Relaxed Quantization for Discretized Neural Networks
• Will You Dance To The Challenge? Predicting User Participation of TikTok Challenges
• Set2Graph: Learning Graphs From Sets
• SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers
• Avoiding local minima in Variational Quantum Algorithms with Neural Networks
• Unsupervised learning of topological phase diagram using topological data analysis
• Early Classification for Agricultural Monitoring from Satellite Time Series
• DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
• LagNetViP: A Lagrangian Neural Network for Video Prediction
• Channel Agnostic End-to-End Learning based Communication Systems with Conditional GAN
• A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
• Conditional Born machine for Monte Carlo event generation
• Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis
• Phase Retrieval Under a Generative Prior
• Cooperative data-driven modeling
• Conditional Infilling GANs for Data Augmentation in Mammogram Classification
• SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
• Controllable Multi-Interest Framework for Recommendation
• Judging a Book By its Cover
• Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data
• Nonlinear Causal Discovery with Confounders
• CopyCAT: Taking Control of Neural Policies with Constant Attacks
• CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations
• CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
• Learning to Solve Vehicle Routing Problems with Time Windows through Joint Attention
• Transfer Learning for Sequence Labeling Using Source Model and Target Data
• Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
• Learned convex regularizers for inverse problems
• Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar
• Realtime Trajectory Smoothing with Neural Nets
• Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)
• Learning Backward Compatible Embeddings
• An Efficient Internet Traffic Classification System Using Deep Learning for IoT
• Neural Machine Translation with Monolingual Translation Memory
• Neural Program Search: Solving Programming Tasks from Description and Examples
• D${}^{\text{2}}$UF: Deep Coded Aperture Design and Unrolling Algorithm for Compressive Spectral Image Fusion
• A Trained Regularization Approach Based on Born Iterative Method for Electromagnetic Imaging
• Quantitative Comparison of Planar Coded Aperture Imaging Reconstruction Methods
• Content-Aware Detection of Temporal Metadata Manipulation
• Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processing
• Unsupervised Domain-Specific Deblurring via Disentangled Representations
• Learning models for visual 3D localization with implicit mapping
• Adapted Center and Scale Prediction: More Stable and More Accurate
• Blockwise Self-Attention for Long Document Understanding
• COVID-19Base: A knowledgebase to explore biomedical entities related to COVID-19
• A Generative Adversarial Network for AI-Aided Chair Design
• Repulsive Deep Ensembles are Bayesian
• Integral Human Pose Regression
• Aedes-AI: Neural Network Models of Mosquito Abundance
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• AIM 2020 Challenge on Learned Image Signal Processing Pipeline
• The Principle of Minimum Pressure Gradient: An Alternative Basis for Physics-Informed Learning of Incompressible Fluid Mechanics
• HUBERT Untangles BERT to Improve Transfer across NLP Tasks
• Deep Learning for Learning Graph Representations
• Combining Q-Learning and Search with Amortized Value Estimates
• TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking
• SSL-QALAS: Self-Supervised Learning for Rapid Multiparameter Estimation in Quantitative MRI Using 3D-QALAS
• Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
• Selfish Sparse RNN Training
• A Deep Learning Framework to Reconstruct Face under Mask
• Efficient yet Competitive Speech Translation: FBK@IWSLT2022
• NeuRec: On Nonlinear Transformation for Personalized Ranking
• Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction
• Deep Rotation Correction without Angle Prior
• Deep Gaussian Process-Based Bayesian Inference for Contaminant Source Localization
• Situational Fusion of Visual Representation for Visual Navigation
• Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations
• Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization
• Variational Preparation of the Sachdev-Ye-Kitaev Thermofield Double
• Learning Sparse Prototypes for Text Generation
• Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization
• Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
• Neural Network Optimal Feedback Control with Guaranteed Local Stability
• Semantic Single-Image Dehazing
• AI-enabled Sound Pattern Recognition on Asthma Medication Adherence: Evaluation with the RDA Benchmark Suite
• Overcoming Language Variation in Sentiment Analysis with Social Attention
• Reinforcement Learning for Learning Rate Control
• Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained Models
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• Time-dependent atomic magnetometry with a recurrent neural network
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Does CLIP Know My Face?
• An Outlier Exposure Approach to Improve Visual Anomaly Detection Performance for Mobile Robots
• Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Explaining and Generalizing Back-Translation through Wake-Sleep
• Joint Demosaicking and Denoising Benefits from a Two-stage Training Strategy
• Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems
• Interpretable Nonlinear Dynamic Modeling of Neural Trajectories
• Unifying local and non-local signal processing with graph CNNs
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
• Multi-scale Adaptive Task Attention Network for Few-Shot Learning
• Autoencoding Low-Resolution MRI for Semantically Smooth Interpolation of Anisotropic MRI
• Fast improvement of TEM image with low-dose electrons by deep learning
• Multi-center validation study of automated classification of pathological slowing in adult scalp electroencephalograms via frequency features
• ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies
• Learning to Optimize in Model Predictive Control
• Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
• Automated Thalamic Nuclei Segmentation Using Multi-Planar Cascaded Convolutional Neural Networks
• 3DEG: Data-Driven Descriptor Extraction for Global re-localization in subterranean environments
• Point Spread Function Estimation for Wide Field Small Aperture Telescopes with Deep Neural Networks and Calibration Data
• Data-Driven Control of the COVID-19 Outbreak via Non-Pharmaceutical Interventions: A Geometric Programming Approach
• Cosmological Parameter Estimation and Inference using Deep Summaries
• FlipDial: A Generative Model for Two-Way Visual Dialogue
• Identifying the Adoption or Rejection of Misinformation Targeting COVID-19 Vaccines in Twitter Discourse
• Generative causal explanations of black-box classifiers
• Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training
• A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision
• Multi-variable LSTM neural network for autoregressive exogenous model
• Estimation of discrete choice models with hybrid stochastic adaptive batch size algorithms
• Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
• Improved Explanatory Efficacy on Human Affect and Workload through Interactive Process in Artificial Intelligence
• Exploring Transformers for Large-Scale Speech Recognition
• How to Train Your Energy-Based Model for Regression
• Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders
• Disentangled speaker and nuisance attribute embedding for robust speaker verification
• Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
• Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time
• Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization
• A deep learning based solution for construction equipment detection: from development to deployment
• Recurrent Autoregressive Networks for Online Multi-Object Tracking
• Noise Adaptive Speech Enhancement using Domain Adversarial Training
• Enhancing Rumor Detection in Social Media Using Dynamic Propagation Structures
• Neural Machine Translation with Noisy Lexical Constraints
• Model Reduction with Memory and the Machine Learning of Dynamical Systems
• Pose-aware Attention Network for Flexible Motion Retargeting by Body Part
• Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet)
• GAN Based Medical Image Registration
• Heavy Ball Neural Ordinary Differential Equations
• 2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data
• A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction
• Unsupervised Domain Adaptation of Language Models for Reading Comprehension
• The Search for Sparse, Robust Neural Networks
• NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting
• Evidence Networks: simple losses for fast, amortized, neural Bayesian model comparison
• Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
• Sparse Adversarial Perturbations for Videos
• Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
• Data Dropout: Optimizing Training Data for Convolutional Neural Networks
• LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
• Dual-view Molecule Pre-training
• DropDim: A Regularization Method for Transformer Networks
• Predicting Model Failure using Saliency Maps in Autonomous Driving Systems
• Two-stage Deep Denoising with Self-guided Noise Attention for Multimodal Medical Images
• SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
• Named Entity Disambiguation using Deep Learning on Graphs
• Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
• Question Answering over Knowledge Base using Language Model Embeddings
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• Probabilistic dose prediction using mixture density networks for automated radiation therapy treatment planning
• Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
• Audio Cover Song Identification using Convolutional Neural Network
• Hardware/Software Co-Exploration of Neural Architectures
• Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
• TomOpt: Differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography
• Learning Free-Surface Flow with Physics-Informed Neural Networks
• Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
• Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning
• DeepCPG Policies for Robot Locomotion
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
• Dense Neural Network Based Arrhythmia Classification on Low-cost and Low-compute Micro-controller
• Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
• Zero-shot User Intent Detection via Capsule Neural Networks
• Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey
• Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression
• Adversarially Robust Training through Structured Gradient Regularization
• Learning to Sketch with Shortcut Cycle Consistency
• D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection
• Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
• A Flexible Selection Scheme for Minimum-Effort Transfer Learning
• Predicting human decision making in psychological tasks with recurrent neural networks
• SylNet: An Adaptable End-to-End Syllable Count Estimator for Speech
• One Person, One Model, One World: Learning Continual User Representation without Forgetting
• Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
• Automatic Landmarks Correspondence Detection in Medical Images with an Application to Deformable Image Registration
• C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation
• Robust Variational Autoencoder
• Evolutionary-Neural Hybrid Agents for Architecture Search
• Intermittent Jamming against Telemetry and Telecommand of Satellite Systems and A Learning-driven Detection Strategy
• Multiple Adaptive Bayesian Linear Regression for Scalable Bayesian Optimization with Warm Start
• Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences
• Applying Deep Reinforcement Learning to the HP Model for Protein Structure Prediction
• Dividing and Conquering Cross-Modal Recipe Retrieval: from Nearest Neighbours Baselines to SoTA
• Real-Time Video Highlights for Yahoo Esports
• Double Neural Counterfactual Regret Minimization
• Development of a neural network to recognize standards and features from 3D CAD models
• Man-recon: manifold learning for reconstruction with deep autoencoder for smart seismic interpretation
• Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language
• Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
• Sea surface temperature prediction and reconstruction using patch-level neural network representations
• On Learning and Learned Data Representation by Capsule Networks
• Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
• Nigraha: Machine-learning based pipeline to identify and evaluate planet candidates from TESS
• Dial2Desc: End-to-end Dialogue Description Generation
• Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention
• DOOM Level Generation using Generative Adversarial Networks
• Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
• Geometric Transformers for Protein Interface Contact Prediction
• On the Vulnerability of Capsule Networks to Adversarial Attacks
• Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly
• Hybrid-DNNs: Hybrid Deep Neural Networks for Mixed Inputs
• REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
• Exploratory Lagrangian-Based Particle Tracing Using Deep Learning
• Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems
• Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
• Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs
• Facial Aging and Rejuvenation by Conditional Multi-Adversarial Autoencoder with Ordinal Regression
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications
• Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube
• Inductive Biases and Variable Creation in Self-Attention Mechanisms
• OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
• AraGPT2: Pre-Trained Transformer for Arabic Language Generation
• AMC: Attention guided Multi-modal Correlation Learning for Image Search
• Learning Visible Connectivity Dynamics for Cloth Smoothing
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• CartiMorph: a framework for automated knee articular cartilage morphometrics
• Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image
• Influence Functions in Deep Learning Are Fragile
• Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Model Aided Deep Learning Based MIMO OFDM Receiver With Nonlinear Power Amplifiers
• Reconstructing undersampled photoacoustic microscopy images using deep learning
• PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
• Joint calibration and mapping of satellite altimetry data using trainable variational models
• Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network
• Neural network enhanced measurement efficiency for molecular groundstates
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
• Radarize: Enhancing Radar SLAM with Generalizable Doppler-Based Odometry
• Deep Learning for Breast MRI Style Transfer with Limited Training Data
• Guiding Cascading Failure Search with Interpretable Graph Convolutional Network
• Information Dropout: Learning Optimal Representations Through Noisy Computation
• Specialized federated learning using a mixture of experts
• Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring
• Learning to Synthesize a 4D RGBD Light Field from a Single Image
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part II
• SimMIM: A Simple Framework for Masked Image Modeling
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• Learning to Reason in Large Theories without Imitation
• Reynolds-Averaged Turbulence Modeling Using Type I and Type II Machine Learning Frameworks with Deep Learning
• Learning-based Defect Recognition for Quasi-Periodic Microscope Images
• Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis
• A Divide-and-Conquer Machine Learning Approach for Modelling Turbulent Flows
• On the Effectiveness of Unlearning in Session-Based Recommendation
• DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling
• BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning
• Vehicle Re-identification with Viewpoint-aware Metric Learning
• Auditing Data Provenance in Text-Generation Models
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part I
• Extraction of hierarchical functional connectivity components in human brain using resting-state fMRI
• Tracking by Instance Detection: A Meta-Learning Approach
• Temporal Complementary Learning for Video Person Re-Identification
• Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
• Conditional Finite Mixtures of Poisson Distributions for Context-Dependent Neural Correlations
• Exploring Shared Structures and Hierarchies for Multiple NLP Tasks
• Emergent Symbols through Binding in External Memory
• Towards an Unsupervised Entrainment Distance in Conversational Speech using Deep Neural Networks
• Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
• Slip Detection with Combined Tactile and Visual Information
• Imitation Learning with Additional Constraints on Motion Style using Parametric Bias
• Neural Simpletrons - Minimalistic Directed Generative Networks for Learning with Few Labels
• Learning to Group and Label Fine-Grained Shape Components
• A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
• Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
• Inexact iterative numerical linear algebra for neural network-based spectral estimation and rare-event prediction
• Deep reinforcement learning for robust quantum optimization
• Quantifying Uncertainties in Natural Language Processing Tasks
• First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
• Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
• Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
• NFAD: Fixing anomaly detection using normalizing flows
• Representation Selective Self-distillation and wav2vec 2.0 Feature Exploration for Spoof-aware Speaker Verification
• Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
• Recognizing Birds from Sound - The 2018 BirdCLEF Baseline System
• Grow and Prune Compact, Fast, and Accurate LSTMs
• OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs
• Robust Deep Reinforcement Learning through Adversarial Loss
• SRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial Networks
• Bayesian LSTMs in medicine
• Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Single-shot Foothold Selection and Constraint Evaluation for Quadruped Locomotion
• Solving for high dimensional committor functions using artificial neural networks
• Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)
• PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings
• Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• Discovering Nonlinear Relations with Minimum Predictive Information Regularization
• Finer Grained Entity Typing with TypeNet
• Bridging the domain gap in cross-lingual document classification
• Bayesian Spatio-Temporal Graph Convolutional Network for Traffic Forecasting
• I${}^3$Net: Inter-Intra-slice Interpolation Network for Medical Slice Synthesis
• Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
• Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach
• Auxiliary Task Reweighting for Minimum-data Learning
• Deconvolution-Based Global Decoding for Neural Machine Translation
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
• Beyond optimization -- supervised learning applications in relativistic laser-plasma experiments
• Ad Headline Generation using Self-Critical Masked Language Model
• Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes
• Unimodal probability distributions for deep ordinal classification
• Study on a Poisson's Equation Solver Based On Deep Learning Technique
• Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Neural representation of a time optimal, constant acceleration rendezvous
• Accelerating Bayesian microseismic event location with deep learning
• Supplementing Recurrent Neural Networks with Annealing to Solve Combinatorial Optimization Problems
• HAT: Hierarchical Aggregation Transformers for Person Re-identification
• Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches
• Bridging the Gap for Tokenizer-Free Language Models
• Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing Strategy
• Multitask Emotion Recognition with Incomplete Labels
• Exploring wav2vec 2.0 on speaker verification and language identification
• Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees
• Best of both worlds: local and global explanations with human-understandable concepts
• Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning
• Reconstruction of FRI Signals using Deep Neural Network Approaches
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
• Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
• Perceptual Reward Functions
• Density Estimation for Geolocation via Convolutional Mixture Density Network
• Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
• Monitoring and mapping of crop fields with UAV swarms based on information gain
• Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement
• A hybrid inference system for improved curvature estimation in the level-set method using machine learning
• Where and What: Driver Attention-based Object Detection
• Restoring degraded speech via a modified diffusion model
• Constrained Combinatorial Optimization with Reinforcement Learning
• A Condense-then-Select Strategy for Text Summarization
• REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
• Segmentation-free PVC for Cardiac SPECT using a Densely-connected Multi-dimensional Dynamic Network
• Identifying MgII Narrow Absorption Lines with Deep Learning
• Adapting Physics-Informed Neural Networks to Improve ODE Optimization in Mosquito Population Dynamics
• Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
• CMB-GAN: Fast Simulations of Cosmic Microwave background anisotropy maps using Deep Learning
• Destruction of Image Steganography using Generative Adversarial Networks
• Transfer Learning From Sound Representations For Anger Detection in Speech
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Riemannian approach to batch normalization
• Machine learning in the study of phase transition of two-dimensional complex plasmas
• Curriculum Learning for Safe Mapless Navigation
• Early Rumor Detection Using Neural Hawkes Process with a New Benchmark Dataset
• EIGEN: Event Influence GENeration using Pre-trained Language Models
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• DiffLoop: Tuning PID controllers by differentiating through the feedback loop
• KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
• State Space Representations of Deep Neural Networks
• Inducing Regular Grammars Using Recurrent Neural Networks
• Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
• Deblending Galaxies with Generative Adversarial Networks
• Variance Networks: When Expectation Does Not Meet Your Expectations
• Encoding protein dynamic information in graph representation for functional residue identification
• Deep Gaussian Covariance Network
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
• Quickly Inserting Pegs into Uncertain Holes using Multi-view Images and Deep Network Trained on Synthetic Data
• Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• Deep Feature Consistent Variational Autoencoder
• Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data
• NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping
• HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
• Source Free Unsupervised Graph Domain Adaptation
• Hateful Memes Detection via Complementary Visual and Linguistic Networks
• FedBoosting: Federated Learning with Gradient Protected Boosting for Text Recognition
• Deep Adversarial Network Alignment
• Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
• The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• Audio-noise Power Spectral Density Estimation Using Long Short-term Memory
• Rapid Estimation of Left Ventricular Contractility with a Physics-Informed Neural Network Inverse Modeling Approach
• Frame-Recurrent Video Inpainting by Robust Optical Flow Inference
• CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
• DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification
• Automatic classification of eclipsing binary stars using deep learning methods
• One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation
• An Online Learning Approach to Generative Adversarial Networks
• What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes
• Thermal variational quantum simulation on a superconducting quantum processor
• Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
• Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
• Hierarchical Training of Deep Neural Networks Using Early Exiting
• Puzzle-AE: Novelty Detection in Images through Solving Puzzles
• Density of States Estimation for Out-of-Distribution Detection
• Saliency is a Possible Red Herring When Diagnosing Poor Generalization
• Temporal-Clustering Invariance in Irregular Healthcare Time Series
• Mel-spectrogram augmentation for sequence to sequence voice conversion
• Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates
• 21cm Global Signal Extraction: Extracting the 21cm Global Signal using Artificial Neural Networks
• A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms
• Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
• Probabilistic Models of Relational Implication
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
• Predicting Outcome of Indian Premier League (IPL) Matches Using Machine Learning
• Boosted top quark tagging and polarization measurement using machine learning
• Continuous PDE Dynamics Forecasting with Implicit Neural Representations
• Learning Multivariate New Physics
• What they do when in doubt: a study of inductive biases in seq2seq learners
• Match-Tensor: a Deep Relevance Model for Search
• Berkeley Open Extended Reality Recordings 2023 (BOXRR-23): 4.7 Million Motion Capture Recordings from 105,852 Extended Reality Device Users
• Elvet -- a neural network-based differential equation and variational problem solver
• Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
• Short-Term Solar Irradiance Forecasting Under Data Transmission Constraints
• RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
• A Federated Learning Framework for Non-Intrusive Load Monitoring
• A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast
• Lightweight Speaker Verification for Online Identification of New Speakers with Short Segments
• Secure short-term load forecasting for smart grids with transformer-based federated learning
• Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions
• DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
• Single Image Reflection Separation with Perceptual Losses
• Decoding-History-Based Adaptive Control of Attention for Neural Machine Translation
• Techniques for visualizing LSTMs applied to electrocardiograms
• A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification
• Dirichlet Variational Autoencoder for Text Modeling
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
• Facelet-Bank for Fast Portrait Manipulation
• Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
• Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM
• Projection Based Weight Normalization for Deep Neural Networks
• SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
• A novel ECG signal denoising filter selection algorithm based on conventional neural networks
• Early prediction of the risk of ICU mortality with Deep Federated Learning
• Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory
• Debiasing Standard Siren Inference of the Hubble Constant with Marginal Neural Ratio Estimation
• Representation Based Regression for Object Distance Estimation
• Vprop: Variational Inference using RMSprop
• Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing
• Deeply Learning Derivatives
• Learning to Remember More with Less Memorization
• Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
• Nematus: a Toolkit for Neural Machine Translation
• CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Deep GrabCut for Object Selection
• PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms using Fully Convolutional Neural Networks
• Long Short-Term Memory for Spatial Encoding in Multi-Agent Path Planning
• SelFlow: Self-Supervised Learning of Optical Flow
• Stochastic Generative Hashing
• Prediction Under Uncertainty with Error-Encoding Networks
• Joint PMD Tracking and Nonlinearity Compensation with Deep Neural Networks
• Classification of Cardiac Arrhythmias from Single Lead ECG with a Convolutional Recurrent Neural Network
• Reliable Node Similarity Matrix Guided Contrastive Graph Clustering
• Bayesian Optimization using Deep Gaussian Processes
• LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
• Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
• Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
• Deep Learning in the Wavelet Domain
• Data-driven discovery of multiscale chemical reactions governed by the law of mass action
• End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression
• Information-theoretic generalization bounds for black-box learning algorithms
• From Audio to Semantics: Approaches to end-to-end spoken language understanding
• Time series forecasting of multiphase microstructure evolution using deep learning
• Learning to Optimize in Swarms
• Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment
• Distributed Learning of Deep Neural Networks using Independent Subnet Training
• Learning Causal Models Online
• Learning semantic sentence representations from visually grounded language without lexical knowledge
• Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data
• Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
• Unsupervised Online Learning for Robotic Interestingness with Visual Memory
• Sliced Kernelized Stein Discrepancy
• Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
• Speech-Based Visual Question Answering
• DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction
• A Spectral View of Adversarially Robust Features
• Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution
• Multi-Task Bidirectional Transformer Representations for Irony Detection
• 3D Human Pose Estimation from a Single Image via Distance Matrix Regression
• Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
• Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
• Cross Domain Knowledge Transfer for Person Re-identification
• Robust deep learning for emulating turbulent viscosities
• Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state
• Pricing equity-linked life insurance contracts with multiple risk factors by neural networks
• KiNet: A Deep Neural Network Representation of Chemical Kinetics
• Blind Face Restoration via Deep Multi-scale Component Dictionaries
• A zero-inflated gamma model for deconvolved calcium imaging traces
• Implicit Solvent Approach Based on Generalised Born and Transferable Graph Neural Networks for Molecular Dynamics Simulations
• GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
• Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models
• LaplacianFusion: Detailed 3D Clothed-Human Body Reconstruction
• DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
• DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
• OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation
• Stochastic loss reserving with mixture density neural networks
• Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
• Incorporating Dictionaries into Deep Neural Networks for the Chinese Clinical Named Entity Recognition
• Fully Automatic Wound Segmentation with Deep Convolutional Neural Networks
• Scalable Coordinated Exploration in Concurrent Reinforcement Learning
• Deep Recurrent Neural Network for Protein Function Prediction from Sequence
• Machine learning and atomic layer deposition: predicting saturation times from reactor growth profiles using artificial neural networks
• User Modeling for Task Oriented Dialogues
• ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking
• RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments
• Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently
• CRUDE: Calibrating Regression Uncertainty Distributions Empirically
• Speech recognition with quaternion neural networks
• Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
• TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services
• Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement
• VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge
• Learning Tversky Similarity
• Reconstructing the exit wave in high-resolution transmission electron microscopy using machine learning
• EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks
• Multi-Objective Predictive Taxi Dispatch via Network Flow Optimization
• Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text
• Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines
• Music theme recognition using CNN and self-attention
• Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge
• Using learned optimizers to make models robust to input noise
• Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning
• Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
• Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
• Falsification-Based Robust Adversarial Reinforcement Learning
• Aerial Vehicles Tracking Using Noncoherent Crowdsourced Wireless Networks
• DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
• From source to target and back: symmetric bi-directional adaptive GAN
• Convolution-enhanced Evolving Attention Networks
• Multi-Advisor Reinforcement Learning
• End-to-End Prediction of Buffer Overruns from Raw Source Code via Neural Memory Networks
• Depth estimation from 4D light field videos
• Driver Assistance Eco-driving and Transmission Control with Deep Reinforcement Learning
• Finding Nano-Ötzi: Semi-Supervised Volume Visualization for Cryo-Electron Tomography
• On Learning Disentangled Representations for Gait Recognition
• Determinantal Point Processes for Mini-Batch Diversification
• Artificial Intelligence Model for Tumoral Clinical Decision Support Systems
• DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
• DARNet: Deep Active Ray Network for Building Segmentation
• Integrated Neural Network and Machine Vision Approach For Leather Defect Classification
• Deep Learning-Based Modeling of 5G Core Control Plane for 5G Network Digital Twin
• Toward a Theory of Causation for Interpreting Neural Code Models
• Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
• Connecting Look and Feel: Associating the visual and tactile properties of physical materials
• Materials Graph Transformer predicts the outcomes of inorganic reactions with reliable uncertainties
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Detecting False Data Injection Attacks in Smart Grids with Modeling Errors: A Deep Transfer Learning Based Approach
• JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
• Machine learning classification of non-Markovian noise disturbing quantum dynamics
• Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• Image-to-Image Translation with Text Guidance
• SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments
• The Efficiency of Human Cognition Reflects Planned Information Processing
• Attribute Aware Pooling for Pedestrian Attribute Recognition
• Feature Selection Based on Sparse Neural Network Layer with Normalizing Constraints
• Prediction of Kidney Function from Biopsy Images Using Convolutional Neural Networks
• Automatic Gesture Recognition in Robot-assisted Surgery with Reinforcement Learning and Tree Search
• Deep Deformable 3D Caricatures with Learned Shape Control
• Improving Sampling from Generative Autoencoders with Markov Chains
• Stabilizing Dynamical Systems via Policy Gradient Methods
• On the Treatment of Optimization Problems with L1 Penalty Terms via Multiobjective Continuation
• AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation
• A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction
• A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition
• Supervised Learning and the Finite-Temperature String Method for Computing Committor Functions and Reaction Rates
• Sequence to Sequence Mixture Model for Diverse Machine Translation
• Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
• Unsupervised Neural Rendering for Image Hazing
• Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus
• Learning Material-Aware Local Descriptors for 3D Shapes
• Understanding the computational demands underlying visual reasoning
• From the Lab to the Wild: Affect Modeling via Privileged Information
• AAG-Stega: Automatic Audio Generation-based Steganography
• Data Acquisition and Preparation for Dual-reference Deep Learning of Image Super-Resolution
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Evaluating language models of tonal harmony
• Neural Invertible Variable-degree Optical Aberrations Correction
• KHAN: Knowledge-Aware Hierarchical Attention Networks for Accurate Political Stance Prediction
• COLTRANE: ConvolutiOnaL TRAjectory NEtwork for Deep Map Inference
• Performance Analysis of ML-based MTC Traffic Pattern Predictors
• ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries
• Training Invertible Neural Networks as Autoencoders
• MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters
• NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
• Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Study
• Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications
• Conditional BERT Contextual Augmentation
• Dual-interest Factorization-heads Attention for Sequential Recommendation
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Rich Prosody Diversity Modelling with Phone-level Mixture Density Network
• What You See is What You Get: Exploiting Visibility for 3D Object Detection
• SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network
• Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis
• DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
• CKConv: Continuous Kernel Convolution For Sequential Data
• Multi-view Human Pose and Shape Estimation Using Learnable Volumetric Aggregation
• No-Reference Image Quality Assessment via Feature Fusion and Multi-Task Learning
• 4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications
• Locally-symplectic neural networks for learning volume-preserving dynamics
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation
• Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
• Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
• Leveraging Native Language Speech for Accent Identification using Deep Siamese Networks
• Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires
• Distilling Relation Embeddings from Pre-trained Language Models
• ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
• Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets
• Learning Navigation Subroutines from Egocentric Videos
• An Attentive Neural Architecture for Fine-grained Entity Type Classification
• Anisotropic Stroke Control for Multiple Artists Style Transfer
• The intriguing role of module criticality in the generalization of deep networks
• Leveraging Prior Knowledge for Protein-Protein Interaction Extraction with Memory Network
• Machine Learning Algorithms for Classification of Microcirculation Images from Septic and Non-Septic Patients
• Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
• End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression
• One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
• Deep Learning for Launching and Mitigating Wireless Jamming Attacks
• Continual self-training with bootstrapped remixing for speech enhancement
• Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis
• Supervised learning of few dirty bosons with variable particle number
• Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
• Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signals
• Deep Multigrid: learning prolongation and restriction matrices
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• Position-Aware Tagging for Aspect Sentiment Triplet Extraction
• Activation Landscapes as a Topological Summary of Neural Network Performance
• Extracting Lungs from CT Images using Fully Convolutional Networks
• A General Framework for Structured Learning of Mechanical Systems
• Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
• Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
• Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
• Improving Video Generation for Multi-functional Applications
• Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks
• Robust Partial-to-Partial Point Cloud Registration in a Full Range
• Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation
• SepAl: Sepsis Alerts On Low Power Wearables With Digital Biomarkers and On-Device Tiny Machine Learning
• Content-driven Magnitude-Derivative Spectrum Complementary Learning for Hyperspectral Image Classification
• "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction
• Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving Linear Elasticity Problems
• U-Det: A Modified U-Net architecture with bidirectional feature network for lung nodule segmentation
• Multi-Task Learning for Arousal and Sleep Stage Detection Using Fully Convolutional Networks
• Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records
• Counting Fish and Dolphins in Sonar Images Using Deep Learning
• Large-scale weakly supervised audio classification using gated convolutional neural network
• FAIM -- A ConvNet Method for Unsupervised 3D Medical Image Registration
• Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slides
• Multi-Modal Hybrid Deep Neural Network for Speech Enhancement
• Generative Partial Multi-View Clustering
• Speech Enhancement using a Deep Mixture of Experts
• Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Data
• Intraoperative Liver Surface Completion with Graph Convolutional VAE
• Classification of COVID-19 X-ray Images Using a Combination of Deep and Handcrafted Features
• Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction
• DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator
• Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
• Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
• TraDE: Transformers for Density Estimation
• Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
• Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization
• Pruning via Iterative Ranking of Sensitivity Statistics
• Automatic Discovery of Novel Intents & Domains from Text Utterances
• Comparative and Interpretative Analysis of CNN and Transformer Models in Predicting Wildfire Spread Using Remote Sensing Data
• Physics-informed attention-based neural network for solving non-linear partial differential equations
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Local Information Assisted Attention-free Decoder for Audio Captioning
• Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation
• AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images
• Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report
• Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
• RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
• Deep learning for Gaussian process tomography model selection using the ASDEX Upgrade SXR system
• Deep Outdoor Illumination Estimation
• Chemical Reaction Neural Networks for Fitting Accelerating Rate Calorimetry Data
• Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
• Gradient Amplification: An efficient way to train deep neural networks
• Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
• Deep-Energy: Unsupervised Training of Deep Neural Networks
• An improved neural network model for joint POS tagging and dependency parsing
• Disentangled Variational Auto-Encoder for Semi-supervised Learning
• Matching Entities Across Different Knowledge Graphs with Graph Embeddings
• Semantic Video Segmentation by Gated Recurrent Flow Propagation
• Coupling weak and strong supervision for classification of prostate cancer histopathology images
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing
• Musical Tempo and Key Estimation using Convolutional Neural Networks with Directional Filters
• Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
• The WiLI benchmark dataset for written language identification
• Estimation of cell lineage trees by maximum-likelihood phylogenetics
• Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
• Deep Learning for Classifying and Characterizing Atmospheric Ducting within the Maritime Setting
• Accelerating High-Strain Continuum-Scale Brittle Fracture Simulations with Machine Learning
• Joint Learning of Vessel Segmentation and Artery/Vein Classification with Post-processing
• Document-Level $N$-ary Relation Extraction with Multiscale Representation Learning
• Novel Video Prediction for Large-scale Scene using Optical Flow
• Explicit Interaction Model towards Text Classification
• A PCA-like Autoencoder
• Video-based Person Re-identification with Accumulative Motion Context
• Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
• Non-Parallel Voice Conversion with Cyclic Variational Autoencoder
• GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps
• Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning
• Learning monocular depth estimation infusing traditional stereo knowledge
• Graph Attention-Based Symmetry Constraint Extraction for Analog Circuits
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
• Deep Graph Neural Networks with Shallow Subgraph Samplers
• Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
• Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
• Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration
• (Martingale) Optimal Transport And Anomaly Detection With Neural Networks: A Primal-dual Algorithm
• Orthogonal Recurrent Neural Networks with Scaled Cayley Transform
• Lifelong Domain Word Embedding via Meta-Learning
• The limits of min-max optimization algorithms: convergence to spurious non-critical sets
• Source-Free Domain Adaptation for Semantic Segmentation
• Smoothing Methods for Automatic Differentiation Across Conditional Branches
• Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• Example-Guided Style Consistent Image Synthesis from Semantic Labeling
• Hidden Talents of the Variational Autoencoder
• Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
• Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey
• TDEFSI: Theory Guided Deep Learning Based Epidemic Forecasting with Synthetic Information
• A biology-driven deep generative model for cell-type annotation in cytometry
• Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
• Monotone operator equilibrium networks
• Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures
• A Model Drift Detection and Adaptation Framework for 5G Core Networks
• Hybrid explicit-implicit learning for multiscale problems with time dependent source
• CNN-based Facial Affect Analysis on Mobile Devices
• A regularized deep matrix factorized model of matrix completion for image restoration
• On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks
• Transferring Implicit Knowledge of Non-Visual Object Properties Across Heterogeneous Robot Morphologies
• Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
• DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
• Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks
• Designing impact-resistant bio-inspired low-porosity structures using neural networks
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
• DeepResp: Deep learning solution for respiration-induced B0 fluctuation artifacts in multi-slice GRE
• An unsupervised deep learning approach in solving partial integro-differential equations
• Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
• Text Level Graph Neural Network for Text Classification
• Ultra Fast Structure-aware Deep Lane Detection
• Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps
• Streaming Variational Monte Carlo
• Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
• Learning Obstacle Representations for Neural Motion Planning
• Breast Mass Detection with Faster R-CNN: On the Feasibility of Learning from Noisy Annotations
• Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint
• Human Action Forecasting by Learning Task Grammars
• Reciprocal Attention Fusion for Visual Question Answering
• Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
• Deep Forest: Neural Network reconstruction of the Lyman-alpha forest
• Attractor Selection in Nonlinear Energy Harvesting Using Deep Reinforcement Learning
• Image Deconvolution via Noise-Tolerant Self-Supervised Inversion
• An In-Depth Analysis of Visual Tracking with Siamese Neural Networks
• Hierarchical Opacity Propagation for Image Matting
• Passive Non-Line-of-Sight Imaging with Light Transport Modulation
• Joint Spatial and Angular Super-Resolution from a Single Image
• HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
• Approximate Inference Turns Deep Networks into Gaussian Processes
• VoxelContext-Net: An Octree based Framework for Point Cloud Compression
• Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
• NeurOpt: Neural network based optimization for building energy management and climate control
• Accelerating Algebraic Multigrid Methods via Artificial Neural Networks
• Adam${}^{+}$: A Stochastic Method with Adaptive Variance Reduction
• DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
• Generative modeling of living cells with SO(3)-equivariant implicit neural representations
• Understanding and Mitigating Annotation Bias in Facial Expression Recognition
• P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware
• Deep learning optimal quantum annealing schedules for random Ising models
• Sequence Labeling: A Practical Approach
• Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery
• Near-Term Quantum-Classical Associative Adversarial Networks
• Inexact Newton Methods for Stochastic Nonconvex Optimization with Applications to Neural Network Training
• A Universal Adversarial Policy for Text Classifiers
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Solve Traveling Salesman Problem by Monte Carlo Tree Search and Deep Neural Network
• CNN-based event classification for alpha-decay events in nuclear emulsion
• Seizure Prediction Using Bidirectional LSTM
• A machine learning approach for efficient multi-dimensional integration
• 3-Dimensional residual neural architecture search for ultrasonic defect detection
• Domain-specific Communication Optimization for Distributed DNN Training
• Gradient-free Policy Architecture Search and Adaptation
• Parkinson's Disease Assessment from a Wrist-Worn Wearable Sensor in Free-Living Conditions: Deep Ensemble Learning and Visualization
• Simplify-then-Translate: Automatic Preprocessing for Black-Box Machine Translation
• ExpMRC: Explainability Evaluation for Machine Reading Comprehension
• A Deep Learning Based Attack for The Chaos-based Image Encryption
• Scalable Deep Reinforcement Learning for Ride-Hailing
• End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning
• CFVNet: An End-to-End Cancelable Finger Vein Network for Recognition
• Gradient-Aware Model-based Policy Search
• TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
• Deep learning for full-field ultrasonic characterization
• Next2You: Robust Copresence Detection Based on Channel State Information
• Dual Attention Networks for Visual Reference Resolution in Visual Dialog
• Deep Learning Optimized Sparse Antenna Activation for Reconfigurable Intelligent Surface Assisted Communication
• Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration
• MM-ALT: A Multimodal Automatic Lyric Transcription System
• Neural network--featured timing systems for radiation detectors: performance evaluation based on bound analysis
• On the Relation between Color Image Denoising and Classification
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks
• Learning to Describe for Predicting Zero-shot Drug-Drug Interactions
• Interpretable Medical Image Classification using Prototype Learning and Privileged Information
• Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses
• A Universal Marginalizer for Amortized Inference in Generative Models
• Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
• Pulsar Candidate Identification with Artificial Intelligence Techniques
• BINet: a binary inpainting network for deep patch-based image compression
• Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
• LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
• Reducing the variance in online optimization by transporting past gradients
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
• COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation
• Deep learning for accelerating Monte Carlo radiation transport simulation in intensity-modulated radiation therapy
• Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking
• The gap between theory and practice in function approximation with deep neural networks
• HarperValleyBank: A Domain-Specific Spoken Dialog Corpus
• Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective
• Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
• PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
• Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
• The Dual Information Bottleneck
• Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network
• Sparse Representations for Object and Ego-motion Estimation in Dynamic Scenes
• High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format
• Group Identification via Transitional Hypergraph Convolution with Cross-view Self-supervised Learning
• MSR: Multi-Scale Shape Regression for Scene Text Detection
• Text segmentation on multilabel documents: A distant-supervised approach
• Artificial Intelligence Assisted Inversion (AIAI) of Synthetic Type Ia Supernova Spectra
• How recurrent networks implement contextual processing in sentiment analysis
• Supervised Learning Enhanced Quantum Circuit Transformation
• Improved Forecasting of Cryptocurrency Price using Social Signals
• Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima
• A Deep Learning Approach to Object Affordance Segmentation
• Reinforcement Learning for Systematic FX Trading
• Semi-parametric Image Inpainting
• An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish
• Markovian Score Climbing: Variational Inference with KL(p||q)
• FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
• Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
• A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
• Inaudible Adversarial Perturbations for Targeted Attack in Speaker Recognition
• "Dependency Bottleneck" in Auto-encoding Architectures: an Empirical Study
• Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
• Decision-making and control with diffractive optical networks
• Monocular UAV Localisation with Deep Learning and Uncertainty Propagation
• One-Shot Learning for Text-to-SQL Generation
• Deep Double Self-Expressive Subspace Clustering
• Unsupervised Clustering and Performance Prediction of Vortex Wakes from Bio-inspired Propulsors
• A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
• Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning
• Progressive Localization Networks for Language-based Moment Localization
• Learning to Brachiate via Simplified Model Imitation
• Learning to Predict Indoor Illumination from a Single Image
• AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
• Geometry meets semantics for semi-supervised monocular depth estimation
• RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
• Multitask Learning for Fundamental Frequency Estimation in Music
• Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images
• Gaze-enhanced Crossmodal Embeddings for Emotion Recognition
• Sensor Fusion using Backward Shortcut Connections for Sleep Apnea Detection in Multi-Modal Data
• Deep learning based projection domain metal segmentation for metal artifact reduction in cone beam computed tomography
• Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction
• Learning To Rank Resources with GNN
• Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems
• This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
• Iterative, Deep Synthetic Aperture Sonar Image Segmentation
• LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
• TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking
• Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework
• Parallelizing Legendre Memory Unit Training
• Meta-learning autoencoders for few-shot prediction
• DeepSI: Interactive Deep Learning for Semantic Interaction
• Relation-based Motion Prediction using Traffic Scene Graphs
• End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings
• Autonomous Time-Optimal Many-Revolution Orbit Raising for Electric Propulsion GEO Satellites via Neural Networks
• File Fragment Classification using Light-Weight Convolutional Neural Networks
• Fast Differentiable Sorting and Ranking
• Automatic Article Commenting: the Task and Dataset
• Pose Neural Fabrics Search
• Automated Spectral Kernel Learning
• Enhanced Behavioral Cloning Based self-driving Car Using Transfer Learning
• Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images
• Disentangling Multiple Conditional Inputs in GANs
• PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction
• Topic-Centric Explanations for News Recommendation
• Unbiasing Semantic Segmentation For Robot Perception using Synthetic Data Feature Transfer
• Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
• QDNN: DNN with Quantum Neural Network Layers
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• Paraphrase Augmented Task-Oriented Dialog Generation
• Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech
• Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement
• No-Transaction Band Network: A Neural Network Architecture for Efficient Deep Hedging
• Muesli: Combining Improvements in Policy Optimization
• End-to-end deep meta modelling to calibrate and optimize energy consumption and comfort
• Inter-Image Communication for Weakly Supervised Localization
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• Artificial neural network as a universal model of nonlinear dynamical systems
• Autonomous Warehouse Robot using Deep Q-Learning
• Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR
• Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
• Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE
• Quantum Approximate Optimization Algorithm Parameter Prediction Using a Convolutional Neural Network
• Visualization Of Class Activation Maps To Explain AI Classification Of Network Packet Captures
• On Network Science and Mutual Information for Explaining Deep Neural Networks
• Learning Bidirectional LSTM Networks for Synthesizing 3D Mesh Animation Sequences
• Autism Spectrum Disorder Classification with Interpretability in Children based on Structural MRI Features Extracted using Contrastive Variational Autoencoder
• Contrastive Registration for Unsupervised Medical Image Segmentation
• DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
• Uformer-ICS: A U-Shaped Transformer for Image Compressive Sensing Service
• A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
• Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
• Multitask Recalibrated Aggregation Network for Medical Code Prediction
• How Can CNNs Use Image Position for Segmentation?
• Competitive Training of Mixtures of Independent Deep Generative Models
• Building Surrogate Models of Nuclear Density Functional Theory with Gaussian Processesand Autoencoders
• SMIL: Multimodal Learning with Severely Missing Modality
• Interpretable Deep Convolutional Neural Networks via Meta-learning
• Knowledge-integrated AutoEncoder Model
• Keep It Simple: CNN Model Complexity Studies for Interference Classification Tasks
• Optimal Feature Transport for Cross-View Image Geo-Localization
• Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet
• Neural canonical transformations for vibrational spectra of molecules
• A Vocoder Based Method For Singing Voice Extraction
• Music Boundary Detection using Convolutional Neural Networks: A comparative analysis of combined input features
• CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning
• A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese
• Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval
• DwinFormer: Dual Window Transformers for End-to-End Monocular Depth Estimation
• Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images
• Early Stopping is Nonparametric Variational Inference
• A Style-Aware Content Loss for Real-time HD Style Transfer
• Analyzing the Galactic pulsar distribution with machine learning
• Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem
• Benchmarking the Neural Linear Model for Regression
• Spiking neuromorphic chip learns entangled quantum states
• An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
• Multi-dimensional Graph Convolutional Networks
• A modular software framework for the design and implementation of ptychography algorithms
• Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems
• Non-Learning based Deep Parallel MRI Reconstruction (NLDpMRI)
• A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning
• Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy
• A Comparison of deep learning methods for environmental sound
• Event Extraction with Generative Adversarial Imitation Learning
• Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention
• Distributional Adversarial Networks
• Graph Neural News Recommendation with Long-term and Short-term Interest Modeling
• A Minimal Span-Based Neural Constituency Parser
• Distributed Machine-Learning for Early HARQ Feedback Prediction in Cloud RANs
• World Discovery Models
• Learning finite difference methods for reaction-diffusion type equations with FCNN
• Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• PYInfer: Deep Learning Semantic Type Inference for Python Variables
• A hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEs
• What Catches the Eye? Visualizing and Understanding Deep Saliency Models
• A CNN-based tool for automatic tongue contour tracking in ultrasound images
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
• Aggregated Multi-GANs for Controlled 3D Human Motion Prediction
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• English Broadcast News Speech Recognition by Humans and Machines
• Influence-guided Data Augmentation for Neural Tensor Completion
• Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks
• Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence
• NN2Poly: A polynomial representation for deep feed-forward artificial neural networks
• Information Leakage in Embedding Models
• More Grounded Image Captioning by Distilling Image-Text Matching Model
• MaskRNN: Instance Level Video Object Segmentation
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification
• Estimation of Tissue Microstructure Using a Deep Network Inspired by a Sparse Reconstruction Framework
• A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction
• Neural Tensor Factorization
• Joint Learning for Pulmonary Nodule Segmentation, Attributes and Malignancy Prediction
• Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
• Deep Transfer Learning for Classification of Variable Sources
• Compressing Neural Language Models by Sparse Word Representations
• KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning
• Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
• Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
• Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning
• Deep Appearance Prefiltering
• Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma
• On the Interpolation of Contextualized Term-based Ranking with BM25 for Query-by-Example Retrieval
• Improving Regression Performance with Distributional Losses
• Machine learning in interpretation of electronic core-level spectra
• The Liar's Walk: Detecting Deception with Gait and Gesture
• HAM: Hybrid Associations Models for Sequential Recommendation
• Non-Autoregressive Neural Dialogue Generation
• UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation
• Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning
• Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction
• Automatic lesion segmentation and Pathological Myopia classification in fundus images
• A semigroup method for high dimensional committor functions based on neural network
• Deep Restricted Boltzmann Networks
• GANBERT: Generative Adversarial Networks with Bidirectional Encoder Representations from Transformers for MRI to PET synthesis
• Data-Driven Thermal Modelling for Anomaly Detection in Electric Vehicle Charging Stations
• Backdoor Attacks on Crowd Counting
• Audio-only Bird Species Automated Identification Method with Limited Training Data Based on Multi-Channel Deep Convolutional Neural Networks
• Assessment Modeling: Fundamental Pre-training Tasks for Interactive Educational Systems
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Zero-Shot Sketch-Image Hashing
• MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction
• Analysis of diversity-accuracy tradeoff in image captioning
• Cross-domain Recommendation via Deep Domain Adaptation
• Transcoding Quality Prediction for Adaptive Video Streaming
• A Multi-Granularity Matching Attention Network for Query Intent Classification in E-commerce Retrieval
• Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function
• Learning-to-Ask: Knowledge Acquisition via 20 Questions
• Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data
• Two Stream Networks for Self-Supervised Ego-Motion Estimation
• ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
• Thermometry of one-dimensional Bose gases with neural networks
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• High-fidelity reproduction of central galaxy joint distributions with Neural Networks
• Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
• ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing
• A Time-domain Monaural Speech Enhancement with Feedback Learning
• Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
• SF-Net: Single-Frame Supervision for Temporal Action Localization
• SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
• Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression
• LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
• Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
• LanSER: Language-Model Supported Speech Emotion Recognition
• EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System
• Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts
• CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning
• Neural network gradient-based learning of black-box function interfaces
• Not Hydro: Using Neural Networks to estimate galaxy properties on a Dark-Matter-Only simulation
• Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand
• Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
• Neural Graph Embedding Methods for Natural Language Processing
• Synthesizing impurity clustering in the edge plasma of tokamaks using neural networks
• Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
• Unsupervised Deep Metric Learning via Auxiliary Rotation Loss
• Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
• Convolutional Normalizing Flows
• Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
• Inverse Problems, Deep Learning, and Symmetry Breaking
• HIN: Hierarchical Inference Network for Document-Level Relation Extraction
• TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs
• Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
• VaPar Synth -- A Variational Parametric Model for Audio Synthesis
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• Shape Completion Enabled Robotic Grasping
• AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
• Effectiveness of LSTMs in Predicting Congestive Heart Failure Onset
• MSC: A Dataset for Macro-Management in StarCraft II
• Deep Spiking Neural Network with Spike Count based Learning Rule
• DeepUKF-VIN: Adaptively-tuned Deep Unscented Kalman Filter for 3D Visual-Inertial Navigation based on IMU-Vision-Net
• Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
• TPNet: Trajectory Proposal Network for Motion Prediction
• Image-Question-Answer Synergistic Network for Visual Dialog
• Forward and Inverse Simulation of Pseudo-Two-Dimensional Model of Lithium-Ion Batteries Using Neural Networks
• Efficient Convolutional Neural Network For Audio Event Detection
• Automated Enriched Medical Concept Generation for Chest X-ray Images
• Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
• Deep Optimization model for Screen Content Image Quality Assessment using Neural Networks
• Deep Learning based End-to-End Wireless Communication Systems with Conditional GAN as Unknown Channel
• SLOctolyzer: Fully automatic analysis toolkit for segmentation and feature extracting in scanning laser ophthalmoscopy images
• Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous media
• Equivariant Deep Learning of Mixed-Integer Optimal Control Solutions for Vehicle Decision Making and Motion Planning
• StartNet: Online Detection of Action Start in Untrimmed Videos
• Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling
• Lending Orientation to Neural Networks for Cross-view Geo-localization
• Quantum error reduction with deep neural network applied at the post-processing stage
• A Semi-Supervised Assessor of Neural Architectures
• Can physical information aid the generalization ability of Neural Networks for hydraulic modeling?
• iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
• Walsh-domain Neural Network for Power Amplifier Behavioral Modelling and Digital Predistortion
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• P${}^2$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
• A possible late-time transition of $M_B$ inferred via neural networks
• Acoustic scene classification using teacher-student learning with soft-labels
• A Safe Reinforcement Learning Algorithm for Supervisory Control of Power Plants
• Personalized Re-ranking for Recommendation
• Cascaded Text Generation with Markov Transformers
• $f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning
• A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experiments
• GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
• Prediction of Influenza A virus infections in humans using an Artificial Neural Network learning approach
• Learning Physical Constraints with Neural Projections
• When Does Preconditioning Help or Hurt Generalization?
• Human Action Generation with Generative Adversarial Networks
• Self-Imitation Learning via Generalized Lower Bound Q-learning
• Quantum support vector data description for anomaly detection
• Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations
• Functional Tensors for Probabilistic Programming
• Continuous 3D Myocardial Motion Tracking via Echocardiography
• Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
• The Kanerva Machine: A Generative Distributed Memory
• Vectorial phase retrieval in super-resolution polarization microscopy
• A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing
• Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
• CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation
• Mitigating Aberration-Induced Noise: A Deep Learning-Based Aberration-to-Aberration Approach
• Physics-Informed Boundary Integral Networks (PIBI-Nets): A Data-Driven Approach for Solving Partial Differential Equations
• Multiplicative update rules for accelerating deep learning training and increasing robustness
• DAISI: Database for AI Surgical Instruction
• Learning Active Subspaces and Discovering Important Features with Gaussian Radial Basis Functions Neural Networks
• Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics
• Sustainable Federated Learning
• A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images
• Dataset balancing can hurt model performance
• Evaluating the Task Generalization of Temporal Convolutional Networks for Surgical Gesture and Motion Recognition using Kinematic Data
• Enhancing variational quantum state diagonalization using reinforcement learning techniques
• On the Utility of Model Learning in HRI
• Explainable Representation Learning of Small Quantum States
• Exploration and preference satisfaction trade-off in reward-free learning
• CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
• Acoustic Scene Classification with Spectrogram Processing Strategies
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
• Quantum Fourier Iterative Amplitude Estimation
• Application of Graph Networks to background rejection in Imaging Air Cherenkov Telescopes
• Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
• Machine learning depinning of dislocation pileups
• A Cross Channel Context Model for Latents in Deep Image Compression
• Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
• Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
• Counterfactual Data Augmentation using Locally Factored Dynamics
• Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
• Doubly Contrastive Deep Clustering
• From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining
• Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition
• A Stochastic Quasi-Newton Method with Nesterov's Accelerated Gradient
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
• Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
• Interpretable Adversarial Training for Text
• Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
• Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks
• Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue
• BERTSurv: BERT-Based Survival Models for Predicting Outcomes of Trauma Patients
• Unsupervised learning for concept detection in medical images: a comparative analysis
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator
• Geometry Normalization Networks for Accurate Scene Text Detection
• Improved Deep Spectral Convolution Network For Hyperspectral Unmixing With Multinomial Mixture Kernel and Endmember Uncertainty
• Regularized linear autoencoders recover the principal components, eventually
• Pulse shape discrimination using a convolutional neural network for organic liquid scintillator signals
• Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
• The effect of variable labels on deep learning models trained to predict breast density
• Few-shot Image Generation via Masked Discrimination
• SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Features
• Neural Lattice-to-Sequence Models for Uncertain Inputs
• Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
• Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
• Improved Dropout for Shallow and Deep Learning
• VizADS-B: Analyzing Sequences of ADS-B Images Using Explainable Convolutional LSTM Encoder-Decoder to Detect Cyber Attacks
• Incremental Adaptation of NMT for Professional Post-editors: A User Study
• T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstruction
• Semi-supervised Clustering for Short Text via Deep Representation Learning
• Modeling Extremal Streamflow using Deep Learning Approximations and a Flexible Spatial Process
• Continuous Speech Separation with Conformer
• Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
• Sentence Simplification with Deep Reinforcement Learning
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• TensorDiffEq: Scalable Multi-GPU Forward and Inverse Solvers for Physics Informed Neural Networks
• Supervised learning of random quantum circuits via scalable neural networks
• Human Activity Analysis and Recognition from Smartphones using Machine Learning Techniques
• Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
• AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization
• Post-breach Recovery: Protection against White-box Adversarial Examples for Leaked DNN Models
• Modeling Gate-Level Abstraction Hierarchy Using Graph Convolutional Neural Networks to Predict Functional De-Rating Factors
• Interactive Medical Image Segmentation via Point-Based Interaction and Sequential Patch Learning
• Visual Odometry Revisited: What Should Be Learnt?
• Learning and controlling the source-filter representation of speech with a variational autoencoder
• Importance mixing: Improving sample reuse in evolutionary policy search methods
• Universal Adversarial Perturbation for Text Classification
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• Counterexample-Guided Learning of Monotonic Neural Networks
• Eformer: Edge Enhancement based Transformer for Medical Image Denoising
• FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
• Integrating Lattice-Free MMI into End-to-End Speech Recognition
• Learning Residual Images for Face Attribute Manipulation
• OCM3D: Object-Centric Monocular 3D Object Detection
• Localization of gravitational waves using machine learning
• Adversarial Learning of Deepfakes in Accounting
• An Open-Source Framework for Adaptive Traffic Signal Control
• Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
• Improving Multi-Person Pose Estimation using Label Correction
• Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
• DSAC - Differentiable RANSAC for Camera Localization
• Knowledge Enhanced Attention for Robust Natural Language Inference
• Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks
• Predicting Peak Stresses In Microstructured Materials Using Convolutional Encoder-Decoder Learning
• Interactive Language Learning by Question Answering
• Dynamic Entity Representations in Neural Language Models
• Thermal Infrared Colorization via Conditional Generative Adversarial Network
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• Identifying Harm Events in Clinical Care through Medical Narratives
• LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
• Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
• Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition
• Adversarial nets with perceptual losses for text-to-image synthesis
• Generative Convolution Layer for Image Generation
• Proximity Sensing: Modeling and Understanding Noisy RSSI-BLE Signals and Other Mobile Sensor Data for Digital Contact Tracing
• Normalized Attention Without Probability Cage
• Deep multi-stations weather forecasting: explainable recurrent convolutional neural networks
• Machine learning synthetic spectra for probabilistic redshift estimation: SYTH-Z
• Prediction Model for Mortality Analysis of Pregnant Women Affected With COVID-19
• Predicting Movie Genres Based on Plot Summaries
• Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients
• Game of Learning Bloch Equation Simulations for MR Fingerprinting
• Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
• Benefit-aware Early Prediction of Health Outcomes on Multivariate EEG Time Series
• A Deep Learning Approach for Determining Effects of Tuta Absoluta in Tomato Plants
• Neural Architectures for Fine-grained Entity Type Classification
• Sparsely Activated Networks
• STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networks
• Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models
• A Deep Learning Approach for Expert Identification in Question Answering Communities
• Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference
• A Co-Interactive Transformer for Joint Slot Filling and Intent Detection
• RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes
• The JHU submission to VoxSRC-21: Track 3
• Coarse grained intermolecular interactions on quantum processors
• Semantically Consistent Image Completion with Fine-grained Details
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning
• Learning to Adapt by Minimizing Discrepancy
• Learning K-way D-dimensional Discrete Code For Compact Embedding Representations
• MCQA: Multimodal Co-attention Based Network for Question Answering
• Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization
• RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
• Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Prediction
• Anytime Stereo Image Depth Estimation on Mobile Devices
• MCNNTUNES: tuning Shower Monte Carlo generators with machine learning
• Mutually exciting point process graphs for modelling dynamic networks
• Self-adaptive deep neural network: Numerical approximation to functions and PDEs
• PAC-Bayes Information Bottleneck
• Using Graph Neural Networks for Mass Spectrometry Prediction
• Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
• TransCT: Dual-path Transformer for Low Dose Computed Tomography
• Machine learning methods for the prediction of micromagnetic magnetization dynamics
• Efficient exploration and calibration of a semi-analytical model of galaxy formation with deep learning
• Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
• Perturbation Analysis of Gradient-based Adversarial Attacks
• Beam Search with Bidirectional Strategies for Neural Response Generation
• Stacking Neural Network Models for Automatic Short Answer Scoring
• Early-Phase Performance-Driven Design using Generative Models
• Low-Cost Recurrent Neural Network Expected Performance Evaluation
• UMONS Submission for WMT18 Multimodal Translation Task
• Contrastive Graph Neural Network Explanation
• Attention-guided Generative Models for Extractive Question Answering
• Scatter Correction in X-ray CT by Physics-Inspired Deep Learning
• From General to Specific: Online Updating for Blind Super-Resolution
• Learning document embeddings along with their uncertainties
• Multi-Label Product Categorization Using Multi-Modal Fusion Models
• Invariant Representation Learning for Treatment Effect Estimation
• Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
• SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
• Learning spectro-temporal representations of complex sounds with parameterized neural networks
• Unsupervised Pose Flow Learning for Pose Guided Synthesis
• Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation
• AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
• A tissue-fraction estimation-based segmentation method for quantitative dopamine transporter SPECT
• Emergent Communication Pretraining for Few-Shot Machine Translation
• Magnetic Resonance Fingerprinting Reconstruction Using Recurrent Neural Networks
• A Deep Probabilistic Model for Customer Lifetime Value Prediction
• KECRS: Towards Knowledge-Enriched Conversational Recommendation System
• CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopy
• privGAN: Protecting GANs from membership inference attacks at low cost
• HatCUP: Hybrid Analysis and Attention based Just-In-Time Comment Updating
• Learning to Adapt Domain Shifts of Moral Values via Instance Weighting
• Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers
• SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
• ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
• Spatial-Temporal Self-Attention Network for Flow Prediction
• Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution
• Attention-based Wav2Text with Feature Transfer Learning
• Ego-Pose Estimation and Forecasting as Real-Time PD Control
• Lightweight Pyramid Networks for Image Deraining
• Designing deep neural networks for driver intention recognition
• Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
• OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• Deep Quantile Regression: Mitigating the Curse of Dimensionality Through Composition
• Block-diagonal Hessian-free Optimization for Training Neural Networks
• Geometric Constellation Shaping for Fiber Optic Communication Systems via End-to-end Learning
• Improving Vessel Segmentation with Multi-Task Learning and Auxiliary Data Available Only During Model Training
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• DVMark: A Deep Multiscale Framework for Video Watermarking
• Object detection on aerial imagery using CenterNet
• Learning Directional Feature Maps for Cardiac MRI Segmentation
• ECINN: Efficient Counterfactuals from Invertible Neural Networks
• Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning
• From Discrete to Continuous Convolution Layers
• Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions
• Higher Order Automatic Differentiation of Higher Order Functions
• Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
• DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
• Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations
• Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
• Stochastic Gradient Descent: Going As Fast As Possible But Not Faster
• Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
• Fingerprint Spoof Generalization
• Incorporating Unlabeled Data into Distributionally Robust Learning
• Deep Multimodal Neural Architecture Search
• Shaping Visual Representations with Attributes for Few-Shot Recognition
• Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model
• Recurrent Filter Learning for Visual Tracking
• Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders
• Deep Short Text Classification with Knowledge Powered Attention
• Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments
• MM-Rec: Multimodal News Recommendation
• Divide and Conquer the Embedding Space for Metric Learning
• Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering
• Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learning
• T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
• Empirical modeling and hybrid machine learning framework for nucleate pool boiling on microchannel structured surfaces
• Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems
• Run Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach
• Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
• Residual Correction in Real-Time Traffic Forecasting
• 1D Convolutional Neural Network Models for Sleep Arousal Detection
• DeepAlloc: CNN-Based Approach to Efficient Spectrum Allocation in Shared Spectrum Systems
• BHAAV- A Text Corpus for Emotion Analysis from Hindi Stories
• Gender and Ethnicity Classification based on Palmprint and Palmar Hand Images from Uncontrolled Environment
• Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging
• Likelihood Estimation for Generative Adversarial Networks
• Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module
• Efficient end-to-end learning for quantizable representations
• Cyclic Differentiable Architecture Search
• Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
• Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks
• Deep learning inference of the neutron star equation of state
• LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
• Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences
• MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
• On the Generation of Medical Dialogues for COVID-19
• Batch Group Normalization
• Landmark-based consonant voicing detection on multilingual corpora
• Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
• Sparse Weight Activation Training
• A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting
• Deconvolution-Based Backproject-Filter (BPF) Computed Tomography Image Reconstruction Method Using Deep Learning Technique
• Low-complexity Near-optimum Symbol Detection Based on Neural Enhancement of Factor Graphs
• Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring
• A Dataset for Document Grounded Conversations
• PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
• MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent
• Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning
• Reverse engineering of one-qubit filter functions with dynamical invariants
• Two-Player Games for Efficient Non-Convex Constrained Optimization
• Grammatical Error Correction with Neural Reinforcement Learning
• Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction
• Modeling Stochastic Microscopic Traffic Behaviors: a Physics Regularized Gaussian Process Approach
• Deep CT to MR Synthesis using Paired and Unpaired Data
• Deep Active Learning for Dialogue Generation
• Can Graph Neural Networks Help Logic Reasoning?
• Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
• Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization
• Neuromorphic Imaging with Super-Resolution
• Pose Graph Optimization for Unsupervised Monocular Visual Odometry
• Comparing Generative Adversarial Network Techniques for Image Creation and Modification
• KETO: Learning Keypoint Representations for Tool Manipulation
• Learning Compressed Sentence Representations for On-Device Text Processing
• Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets
• On the Limitations of Denoising Strategies as Adversarial Defenses
• Deep Contextual Multi-armed Bandits
• Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
• The PAU Survey: Background light estimation with deep learning techniques
• Magnetic Phases of Spatially-Modulated Spin-1 Chains in Rydberg Excitons: Classical and Quantum Simulations
• Automatic structured variational inference
• High-Resolution Network for Photorealistic Style Transfer
• Semantic Variation in Online Communities of Practice
• Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
• The CORSMAL benchmark for the prediction of the properties of containers
• Neural Architecture Search for Class-incremental Learning
• End-to-End Wireframe Parsing
• Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain
• A Dilated Inception Network for Visual Saliency Prediction
• IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
• CovNet: Covariance Networks for Functional Data on Multidimensional Domains
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks
• Optimising longitudinal and lateral calorimeter granularity for software compensation in hadronic showers using deep neural networks
• Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints
• Link prediction in dynamic networks using random dot product graphs
• Vetting Asteroseismic $\Delta \nu$ Measurements using Neural Networks
• Adaptive Denoising via GainTuning
• Towards hybrid primary intersubjectivity: a neural robotics library for human science
• Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation
• Deep Learning assisted microwave-plasma interaction based technique for plasma density estimation
• Heterogeneous Information Network-based Interest Composition with Graph Neural Network for Recommendation
• Second-order step-size tuning of SGD for non-convex optimization
• Sample-efficient Deep Reinforcement Learning for Dialog Control
• Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Reproducing Activation Function for Deep Learning
• One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks
• Forecasting through deep learning and modal decomposition in two-phase concentric jets
• A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
• Git Loss for Deep Face Recognition
• Generating Neural Networks with Neural Networks
• DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding
• Hamiltonian learning with real-space impurity tomography in topological moire superconductors
• Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues
• Optimization of Graph Neural Networks with Natural Gradient Descent
• Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition
• Deep Online Video Stabilization
• Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstruction
• Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
• Fairness-Aware Node Representation Learning
• Evolving Attention with Residual Convolutions
• Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
• Enabling Early Audio Event Detection with Neural Networks
• Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
• AMR Parsing as Sequence-to-Graph Transduction
• Learning Deep Robotic Skills on Riemannian manifolds
• AMR Parsing via Graph-Sequence Iterative Inference
• End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear Model Predictive Control
• Enforcing exact boundary and initial conditions in the deep mixed residual method
• Multi-Attention Based Ultra Lightweight Image Super-Resolution
• Learning High Dynamic Range from Outdoor Panoramas
• Extended Depth-of-Field Lensless Imaging using an Optimized Radial Mask
• Recurrent Neural Networks for Fuzz Testing Web Browsers
• Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning
• Modelling Latent Translations for Cross-Lingual Transfer
• Physics-informed Neural Networks for Solving Inverse Problems of Nonlinear Biot's Equations: Batch Training
• CCS Explorer: Relevance Prediction, Extractive Summarization, and Named Entity Recognition from Clinical Cohort Studies
• MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
• Disparity-based Stereo Image Compression with Aligned Cross-View Priors
• Two-stream convolutional networks for end-to-end learning of self-driving cars
• Phrase-Based Attentions
• SDNet: mutil-branch for single image deraining using swin
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response
• Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors
• A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
• Modeling Personalized Item Frequency Information for Next-basket Recommendation
• Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
• Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equations
• Deep API Programmer: Learning to Program with APIs
• STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?
• General Partial Label Learning via Dual Bipartite Graph Autoencoder
• DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration
• Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference
• ContCap: A scalable framework for continual image captioning
• Hull Form Optimization with Principal Component Analysis and Deep Neural Network
• ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language
• Domain Invariant Representation Learning with Domain Density Transformations
• Identification of diffracted vortex beams at different propagation distances using deep learning
• Training Generative Adversarial Networks Via Turing Test
• Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding
• Variational Neural Discourse Relation Recognizer
• Unsupervised High-Resolution Depth Learning From Videos With Dual Networks
• Improved Analysis of Clipping Algorithms for Non-convex Optimization
• Identifying the Defective: Detecting Damaged Grains for Cereal Appearance Inspection
• X-GANs: Image Reconstruction Made Easy for Extreme Cases
• Automatic audiovisual synchronisation for ultrasound tongue imaging
• Detecting Social Media Manipulation in Low-Resource Languages
• Human-in-the-Loop Imitation Learning using Remote Teleoperation
• Building Disease Detection Algorithms with Very Small Numbers of Positive Samples
• Ex2Vec: Characterizing Users and Items from the Mere Exposure Effect
• Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
• Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite Rules
• Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China
• Safe Interactive Model-Based Learning
• VQA-LOL: Visual Question Answering under the Lens of Logic
• Semantics-Aligned Representation Learning for Person Re-identification
• Graph Neural Networks for Topological Feature Extraction in ECG Classification
• Deep Embedding for Spatial Role Labeling
• ML-based Approaches for Wireless NLOS Localization: Input Representations and Uncertainty Estimation
• A Comparison of Super-Resolution and Nearest Neighbors Interpolation Applied to Object Detection on Satellite Data
• Learning the Base Distribution in Implicit Generative Models
• Generalization Guarantees for Imitation Learning
• When and Why is Unsupervised Neural Machine Translation Useless?
• Coupling the reduced-order model and the generative model for an importance sampling estimator
• Learning to Grasp from a Single Demonstration
• A Contrastive Learning Approach to Auroral Identification and Classification
• Tensor Networks for Medical Image Classification
• Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
• LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning
• MulGAN: Facial Attribute Editing by Exemplar
• Learning Deep Representations with Probabilistic Knowledge Transfer
• Building Chinese Biomedical Language Models via Multi-Level Text Discrimination
• Going Beneath the Surface: Evaluating Image Captioning for Grammaticality, Truthfulness and Diversity
• Positive-Unlabeled Reward Learning
• Dense Depth Posterior (DDP) from Single Image and Sparse Range
• Optimizing ZX-Diagrams with Deep Reinforcement Learning
• Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
• Frame Averaging for Invariant and Equivariant Network Design
• RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution
• Fast MRI Reconstruction via Edge Attention
• Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
• Acceleration Strategies for MR-STAT: Achieving High-Resolution Reconstructions on a Desktop PC within 3 minutes
• Real-Time Vibration-Based Bearing Fault Diagnosis Under Time-Varying Speed Conditions
• DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
• Decoding the Rejuvenating Effects of Mechanical Loading on Skeletal Maturation using in Vivo Imaging and Deep Learning
• DREAM: Deep Regret minimization with Advantage baselines and Model-free learning
• Metameric Varifocal Holography
• Unsupervised Deep Learning-based clustering for Human Activity Recognition
• LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention
• EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
• Temporal Interpolation via Motion Field Prediction
• Symmetry-invariant quantum machine learning force fields
• Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
• Bayesian Learning of Parameterised Quantum Circuits
• NLRP3 monomer Functional Dynamics: from the Effects of Allosteric Binding to Implications for Drug Design
• Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
• Can Neural Networks Understand Logical Entailment?
• ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs
• Rebalancing Social Feed to Minimize Polarization and Disagreement
• Cura: Curation at Social Media Scale
• Solving Non-local Fokker-Planck Equations by Deep Learning
• Multi-turn Inference Matching Network for Natural Language Inference
• Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators
• Unsupervised Image Captioning
• A Classifying Variational Autoencoder with Application to Polyphonic Music Generation
• An adaptive surrogate modeling based on deep neural networks for large-scale Bayesian inverse problems
• A Lightweight Method for Modeling Confidence in Recommendations with Learned Beta Distributions
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
• Do Neural Language Representations Learn Physical Commonsense?
• A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models
• Artificial Intelligence for Molecular Communication
• Blind Predicting Similar Quality Map for Image Quality Assessment
• Asymptotic preserving scheme for anisotropic elliptic equations with deep neural network
• Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
• DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
• Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems
• Dynamic Experience Replay
• Edge-Assisted ML-Aided Uncertainty-Aware Vehicle Collision Avoidance at Urban Intersections
• Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
• Convolutional Recurrent Neural Network Based Progressive Learning for Monaural Speech Enhancement
• Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments
• Learning Awareness Models
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• Conformal Prediction using Conditional Histograms
• Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark
• Understanding Audio Pattern Using Convolutional Neural Network From Raw Waveforms
• A novel machine learning based framework for detection of Autism Spectrum Disorder (ASD)
• Deep Point Cloud Reconstruction
• PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation
• Seismic-Net: A Deep Densely Connected Neural Network to Detect Seismic Events
• Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Tracking
• Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
• The Universe from a Single Particle
• TMP: Temporal Motion Propagation for Online Video Super-Resolution
• Neural Empirical Bayes
• VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
• Deep Q-Networks for Accelerating the Training of Deep Neural Networks
• Open Set Medical Diagnosis
• Adaptive Robotic Tool-Tip Control Learning Considering Online Changes in Grasping State
• Compositional Generalization for Primitive Substitutions
• FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization
• Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
• Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
• Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation
• Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
• Neural Controlled Differential Equations for Online Prediction Tasks
• Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
• Neural Architectures for Nested NER through Linearization
• AdaS: Adaptive Scheduling of Stochastic Gradients
• Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
• Pose Representations for Deep Skeletal Animation
• SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Signal Combination for Language Identification
• PyTester: Deep Reinforcement Learning for Text-to-Testcase Generation
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• A Memory-Efficient Dynamic Image Reconstruction Method using Neural Fields
• An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
• Converting Your Thoughts to Texts: Enabling Brain Typing via Deep Feature Learning of EEG Signals
• On transfer learning of neural networks using bi-fidelity data for uncertainty propagation
• Latent Variable Modelling with Hyperbolic Normalizing Flows
• Machine learning structure preserving brackets for forecasting irreversible processes
• Centroid-based deep metric learning for speaker recognition
• Interval Neural Networks: Uncertainty Scores
• Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
• Efficient Deep Neural Networks
• MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism
• Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks
• Implementing Neural Turing Machines
• Fuzzy Unique Image Transformation: Defense Against Adversarial Attacks On Deep COVID-19 Models
• Kronecker Recurrent Units
• Neural Baselines for Word Alignment
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
• Stochastic Gradient Descent for Semilinear Elliptic Equations with Uncertainties
• Anticipating contingengies in power grids using fast neural net screening
• Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
• An Empirical Exploration of Skip Connections for Sequential Tagging
• Deep Contextualized Biomedical Abbreviation Expansion
• Machine learning assisted coarse-grained molecular dynamics modeling of meso-scale interfacial fluids
• Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning
• AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
• Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
• Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
• Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
• Deep Neural Networks for Creating Reliable PmP Database with a Case Study in Southern California
• Simplified Minimal Gated Unit Variations for Recurrent Neural Networks
• Automatic Health Problem Detection from Gait Videos Using Deep Neural Networks
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
• Fast Adaptation via Policy-Dynamics Value Functions
• A Novel Correlation-optimized Deep Learning Method for Wind Speed Forecast
• SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation
• Weakly Supervised Learning for Analyzing Political Campaigns on Facebook
• Federated $f$-Differential Privacy
• Learning Deep Matrix Representations
• Blockchain-based Bidirectional Updates on Fine-grained Medical Data
• Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
• Weak Supervision for Fake News Detection via Reinforcement Learning
• BERE: An accurate distantly supervised biomedical entity relation extraction network
• Federated Mixture of Experts
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions
• High-dimensional reinforcement learning for optimization and control of ultracold quantum gases
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraints
• Multi-variable integration with a variational quantum circuit
• Sustainable transparency in Recommender Systems: Bayesian Ranking of Images for Explainability
• IDLat: An Importance-Driven Latent Generation Method for Scientific Data
• Reconstruction of Protein Structures from Single-Molecule Time Series
• Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention
• Designing and Training of A Dual CNN for Image Denoising
• Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
• BERT-Based Arabic Social Media Author Profiling
• Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parsers
• Towards Open Intent Discovery for Conversational Text
• Learning to Identify Patients at Risk of Uncontrolled Hypertension Using Electronic Health Records Data
• Latent Disentanglement in Mesh Variational Autoencoders Improves the Diagnosis of Craniofacial Syndromes and Aids Surgical Planning
• Fast Inference in Capsule Networks Using Accumulated Routing Coefficients
• Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation
• Do End-to-End Speech Recognition Models Care About Context?
• Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models
• OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference
• Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces
• Neural Networks with A La Carte Selection of Activation Functions
• Neuralogram: A Deep Neural Network Based Representation for Audio Signals
• Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
• Simple lessons from complex learning: what a neural network model learns about cosmic structure formation
• Personalized Embedding-based e-Commerce Recommendations at eBay
• Large-time asymptotics in deep learning
• Adaptive Parameterization for Neural Dialogue Generation
• Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments
• Attention-based End-to-End Models for Small-Footprint Keyword Spotting
• TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients
• Unsupervised Representation Learning of Structured Radio Communication Signals
• Deep Learning Techniques for Inverse Problems in Imaging
• Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
• Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
• Effects of Forward Error Correction on Communications Aware Evasion Attacks
• SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation
• Monocular, One-stage, Regression of Multiple 3D People
• Online Collective Animal Movement Activity Recognition
• Learning to Prove from Synthetic Theorems
• Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words
• Smooth Exploration for Robotic Reinforcement Learning
• First Steps Toward CNN based Source Classification of Document Images Shared Over Messaging App
• Towards Foundation Model for Chemical Reactor Modeling: Meta-Learning with Physics-Informed Adaptation
• ActionFlowNet: Learning Motion Representation for Action Recognition
• Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
• Shifting Mean Activation Towards Zero with Bipolar Activation Functions
• Discovering dynamical features of Hodgkin-Huxley-type model of physiological neuron using artificial neural network
• Fooling Vision and Language Models Despite Localization and Attention Mechanism
• Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
• Learning Edge Properties in Graphs from Path Aggregations
• Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
• Learning language through pictures
• Deep Reinforcement Agent for Scheduling in HPC
• Multi-soliton solutions and data-driven discovery of higher-order Burgers' hierarchy equations with physics informed neural networks
• Training speaker recognition systems with limited data
• On the performance of residual block design alternatives in convolutional neural networks for end-to-end audio classification
• A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics
• Improving Neural Question Generation using Answer Separation
• Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity
• Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
• Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)
• Cultivating DNN Diversity for Large Scale Video Labelling
• f-GANs in an Information Geometric Nutshell
• SGD momentum optimizer with step estimation by online parabola model
• B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction
• TEE-based decentralized recommender systems: The raw data sharing redemption
• A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging
• Towards Context-aware Convolutional Network for Image Restoration
• Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation
• Try This Instead: Personalized and Interpretable Substitute Recommendation
• DIMENSION: Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Training
• Ionospheric activity prediction using convolutional recurrent neural networks
• Sustainable Greenhouse Microclimate Modeling: A Comparative Analysis of Recurrent and Graph Neural Networks
• OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
• Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary
• Deep unfolding of the weighted MMSE beamforming algorithm
• Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow
• Hybrid Dialog State Tracker
• Adaptive Adversarial Attack on Scene Text Recognition
• Natural Language Generation with Neural Variational Models
• VisRecall: Quantifying Information Visualisation Recallability via Question Answering
• Unlocking the Potential of Deep Counterfactual Value Networks
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Learning spectro-temporal features with 3D CNNs for speech emotion recognition
• Deep Normalization for Speaker Vectors
• Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection
• Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum
• OCoR: An Overlapping-Aware Code Retriever
• Neural Latent Extractive Document Summarization
• A Deep Learning-Accelerated Data Assimilation and Forecasting Workflow for Commercial-Scale Geologic Carbon Storage
• SunnyNet: A neural network approach to 3D non-LTE radiative transfer
• Improving Biomedical Pretrained Language Models with Knowledge
• Context-Aware Visual Compatibility Prediction
• Pileup mitigation at the Large Hadron Collider with Graph Neural Networks
• End-to-End Neural Entity Linking
• Implementing a Bayes Filter in a Neural Circuit: The Case of Unknown Stimulus Dynamics
• Real-time convolutional networks for sonar image classification in low-power embedded systems
• OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
• Detection and Classification of mental illnesses on social media using RoBERTa
• Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
• Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
• Conditional Neural Process for non-parametric modeling of AGN light curve
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
• Classification of Multi-Parametric Body MRI Series Using Deep Learning
• Enhancing eLoran Timing Accuracy via Machine Learning with Meteorological and Terrain Data
• Adversarial Binaries for Authorship Identification
• G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• Can LSTM Learn to Capture Agreement? The Case of Basque
• Task-specific Self-body Controller Acquisition by Musculoskeletal Humanoids: Application to Pedal Control in Autonomous Driving
• Content Adaptive and Error Propagation Aware Deep Video Compression
• IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision
• An improved set of electron-THFA cross sections refined through a neural network-based analysis of swarm data
• HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
• Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records
• Deep Learning applied to Road Traffic Speed forecasting
• Many-Joint Robot Arm Control with Recurrent Spiking Neural Networks
• Hierarchical Text Classification As Sub-Hierarchy Sequence Generation
• UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images
• Towards Information-Seeking Agents
• Inferring Multidimensional Rates of Aging from Cross-Sectional Data
• End-to-end Network for Twitter Geolocation Prediction and Hashing
• EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning
• Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization
• Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism
• IMS-Speech: A Speech to Text Tool
• Fine-grained Synthesis of Unrestricted Adversarial Examples
• Correct-and-Memorize: Learning to Translate from Interactive Revisions
• Almost instant brain atlas segmentation for large-scale studies
• Hierarchical Pooling Structure for Weakly Labeled Sound Event Detection
• Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlations
• Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
• Robust Line Segments Matching via Graph Convolution Networks
• Deep Neural Network application: Higgs boson CP state mixing angle in H to tau tau decay and at LHC
• Transportation mode recognition based on low-rate acceleration and location signals with an attention-based multiple-instance learning network
• Explicit Utilization of General Knowledge in Machine Reading Comprehension
• TripletGAN: Training Generative Model with Triplet Loss
• Automatic Defect Detection in Sewer Network Using Deep Learning Based Object Detector
• Stochastic Calibration of Radio Interferometers
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
• Generative Adversarial U-Net for Domain-free Medical Image Augmentation
• Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning
• Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
• Online Smoothing for Diffusion Processes Observed with Noise
• MeshingNet: A New Mesh Generation Method based on Deep Learning
• FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
• All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks
• Cross Temporal Recurrent Networks for Ranking Question Answer Pairs
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• Test Time Embedding Normalization for Popularity Bias Mitigation
• Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism
• Any-Precision Deep Neural Networks
• Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
• Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning
• Applications of Deep Learning to Nuclear Fusion Research
• Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
• Improving Generative Imagination in Object-Centric World Models
• Omni SCADA Intrusion Detection Using Deep Learning Algorithms
• Online Nonlinear Estimation via Iterative L2-Space Projections: Reproducing Kernel of Subspace
• Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Embedding-based Instance Segmentation in Microscopy
• Towards automated patient data cleaning using deep learning: A feasibility study on the standardization of organ labeling
• Soft Gradient Boosting Machine
• Solving Irregular and Data-enriched Differential Equations using Deep Neural Networks
• Nonparametric Inference for Auto-Encoding Variational Bayes
• Building a Parallel Corpus and Training Translation Models Between Luganda and English
• CORAL8: Concurrent Object Regression for Area Localization in Medical Image Panels
• End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
• Incorporating Kinematic Wave Theory into a Deep Learning Method for High-Resolution Traffic Speed Estimation
• Combining Learning and Optimization for Transprecision Computing
• Multi-Modal Detection of Alzheimer's Disease from Speech and Text
• Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
• AlphaCrystal: Contact map based crystal structure prediction using deep learning
• Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
• AMD-HookNet for Glacier Front Segmentation
• Object and Relation Centric Representations for Push Effect Prediction
• On the detectability of ultra-compact binary pulsar systems
• Multi-Output Artificial Neural Network for Storm Surge Prediction in North Carolina
• Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
• SwitchNet: a neural network model for forward and inverse scattering problems
• Inception-Based Network and Multi-Spectrogram Ensemble Applied For Predicting Respiratory Anomalies and Lung Diseases
• Distributed Deep Learning for Question Answering
• ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding
• Integrating Uncertainty into Neural Network-based Speech Enhancement
• Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks
• Is the PPG signal chaotic?
• Diversifying Sample Generation for Accurate Data-Free Quantization
• A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
• Improving Interpretability of Word Embeddings by Generating Definition and Usage
• LibAUC: A Deep Learning Library for X-Risk Optimization
• Application of the Diamond Gate in Quantum Fourier Transformations and Quantum Machine Learning
• LCEval: Learned Composite Metric for Caption Evaluation
• Learning Graph-Level Representations with Recurrent Neural Networks
• Disentangling Geometric Deformation Spaces in Generative Latent Shape Models
• Bridging Fidelities to Predict Nanoindentation Tip Radii Using Interpretable Deep Learning Models
• Integrating Multimodal Information in Large Pretrained Transformers
• Qsun: an open-source platform towards practical quantum machine learning applications
• The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning
• Nonnegative spatial factorization
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
• FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction
• Temporal-Relational Hypergraph Tri-Attention Networks for Stock Trend Prediction
• A deep learning method for solving Fokker-Planck equations
• EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
• Selective Distillation of Weakly Annotated GTD for Vision-based Slab Identification System
• Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation
• On Graph Neural Networks versus Graph-Augmented MLPs
• ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networks
• DeepLogic: Towards End-to-End Differentiable Logical Reasoning
• Towards Domain-Agnostic Contrastive Learning
• Self-Supervised Feature Learning by Learning to Spot Artifacts
• Deep Tactile Experience: Estimating Tactile Sensor Output from Depth Sensor Data
• An Interpretable Deep Hierarchical Semantic Convolutional Neural Network for Lung Nodule Malignancy Classification
• ViWi Vision-Aided mmWave Beam Tracking: Dataset, Task, and Baseline Solutions
• False Discovery Rate Control via Data Splitting
• On Statistical Optimality of Variational Bayes
• AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation
• MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
• Toward an Automated Auction Framework for Wireless Federated Learning Services Market
• GACNN: Training Deep Convolutional Neural Networks with Genetic Algorithm
• InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
• Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences
• Sound Context Classification Basing on Join Learning Model and Multi-Spectrogram Features
• An Auxiliary Task for Learning Nuclei Segmentation in 3D Microscopy Images
• Temporal Segmentation of Surgical Sub-tasks through Deep Learning with Multiple Data Sources
• Triple Generative Adversarial Networks
• DSRNA: Differentiable Search of Robust Neural Architectures
• CT Perfusion is All We Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Ischemic Stroke
• Unsupervised Landmark Learning from Unpaired Data
• Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training
• Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification
• Transfer Learning Enhanced Full Waveform Inversion
• Interpreting Deep Neural Networks Through Variable Importance
• Neural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning
• Generating Lode Runner Levels by Learning Player Paths with LSTMs
• Multi-label Contrastive Predictive Coding
• Leveraging Medical Visual Question Answering with Supporting Facts
• Task-Aware Feature Generation for Zero-Shot Compositional Learning
• Constraining cosmological parameters from N-body simulations with Variational Bayesian Neural Networks
• Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series
• Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
• Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment
• ScaDLES: Scalable Deep Learning over Streaming data at the Edge
• Non-local NetVLAD Encoding for Video Classification
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• Perceive and predict: self-supervised speech representation based loss functions for speech enhancement
• Learning Semantic Annotations for Tabular Data
• Self-Supervised Learning of Depth and Ego-motion with Differentiable Bundle Adjustment
• DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
• Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts
• Lattice-Based Transformer Encoder for Neural Machine Translation
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Mutual Information Scaling and Expressive Power of Sequence Models
• Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification
• Theoretical Interpretation of Learned Step Size in Deep-Unfolded Gradient Descent
• Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
• Inefficiency of the Brazilian Stock Market: the IBOVESPA Future Contracts
• REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study
• Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimation
• Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
• Unsupervised Domain Adaptation for Cross-sensor Pore Detection in High-resolution Fingerprint Images
• A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes
• A Softmax-free Loss Function Based on Predefined Optimal-distribution of Latent Features for Deep Learning Classifier
• Cost-aware Multi-objective Bayesian optimisation
• Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning
• On Synthetic Data for Back Translation
• Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and Transformation
• Test Selection for Deep Learning Systems
• DeepClimGAN: A High-Resolution Climate Data Generator
• Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow
• Real-Time Adversarial Attacks
• Machine-learning Kohn-Sham potential from dynamics in time-dependent Kohn-Sham systems
• MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation
• EEV: A Large-Scale Dataset for Studying Evoked Expressions from Video
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• Face Completion with Semantic Knowledge and Collaborative Adversarial Learning
• The dilemma of quantum neural networks
• Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC
• Statistical Adaptive Stochastic Gradient Methods
• Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
• Modern French Poetry Generation with RoBERTa and GPT-2
• Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications
• Information Losses in Neural Classifiers from Sampling
• Model-based 3D Hand Reconstruction via Self-Supervised Learning
• Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI
• Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation
• Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes
• Adversarial Cross-Domain Action Recognition with Co-Attention
• Robust and Decomposable Average Precision for Image Retrieval
• Measuring non-trivial compositionality in emergent communication
• Learning Runtime Parameters in Computer Systems with Delayed Experience Injection
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
• Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
• Convolutional Mixture Density Recurrent Neural Network for Predicting User Location with WiFi Fingerprints
• KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
• Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks
• Learned Hardware/Software Co-Design of Neural Accelerators
• Right whale recognition using convolutional neural networks
• Deep Transfer Learning for Blended Source Identification in Galaxy Survey Data
• Mathematical Analysis of Adversarial Attacks
• Generating Text Sequence Images for Recognition
• Session-based Social and Dependency-aware Software Recommendation
• Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters
• Robust Deep Gaussian Processes
• ACtuAL: Actor-Critic Under Adversarial Learning
• FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
• Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding
• Debiasing Concept-based Explanations with Causal Analysis
• Vid2speech: Speech Reconstruction from Silent Video
• Semantic Segmentation of Human Thigh Quadriceps Muscle in Magnetic Resonance Images
• An Efficient Approach to Informative Feature Extraction from Multimodal Data
• Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach
• S2RMs: Spatially Structured Recurrent Modules
• Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks
• Playing it Safe: Adversarial Robustness with an Abstain Option
• Cross-Modal and Hierarchical Modeling of Video and Text
• Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling
• Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
• From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
• A deep learning approach to the measurement of long-lived memory kernels from Generalised Langevin Dynamics
• (Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
• Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN
• AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• Secost: Sequential co-supervision for large scale weakly labeled audio event detection
• Learning Position From Vehicle Vibration Using an Inertial Measurement Unit
• Regional Tree Regularization for Interpretability in Black Box Models
• Hybrid Quantum Machine Learning Assisted Classification of COVID-19 from Computed Tomography Scans
• Uncertainty-Aware Self-supervised Neural Network for Liver $T_{1\rho }$ Mapping with Relaxation Constraint
• Dynamic Multi-Level Multi-Task Learning for Sentence Simplification
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
• Empirical study towards understanding line search approximations for training neural networks
• A Study of Multilingual Neural Machine Translation
• Faster Neural Network Training with Approximate Tensor Operations
• Contributing Components of Metabolic Energy Models to Metabolic Cost Estimations in Gait
• Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning
• Effect of Duration and Delay on the Identifiability of VR Motion
• Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
• Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding
• A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
• Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
• Capability Iteration Network for Robot Path Planning
• Learning to Select: A Fully Attentive Approach for Novel Object Captioning
• Lossy compression of statistical data using quantum annealer
• Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction
• Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs
• Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
• CAGAN: Text-To-Image Generation with Combined Attention GANs
• Deep Learning for Surface Material Classification Using Haptic And Visual Information
• Marker-Based Localisation System Using an Active PTZ Camera and CNN-Based Ellipse Detection
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• Document Neural Autoregressive Distribution Estimation
• Brain informed transfer learning for categorizing construction hazards
• Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
• Deep Learning Meets Adaptive Filtering: A Stein's Unbiased Risk Estimator Approach
• Probabilistic Contrastive Principal Component Analysis
• Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation
• Meshless physics-informed deep learning method for three-dimensional solid mechanics
• MARF: The Medial Atom Ray Field Object Representation
• A reinforcement learning approach for VQA validation: an application to diabetic macular edema grading
• On the interplay between noise and curvature and its effect on optimization and generalization
• Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning
• Answering Complicated Question Intents Expressed in Decomposed Question Sequences
• Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• Supervised Anomaly Detection based on Deep Autoregressive Density Estimators
• A Spontaneous Driver Emotion Facial Expression (DEFE) Dataset for Intelligent Vehicles
• When Does Stochastic Gradient Algorithm Work Well?
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks
• AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
• Supermasks in Superposition
• Unsupervised Domain Adaptation with Adapter
• Mesh Density Adaptation for Template-based Shape Reconstruction
• HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
• Application of pattern spectra and convolutional neural networks to the analysis of simulated Cherenkov Telescope Array data
• A Real-time Global Inference Network for One-stage Referring Expression Comprehension
• Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
• Learning to Localize and Align Fine-Grained Actions to Sparse Instructions
• PidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to English
• Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders
• Computing a human-like reaction time metric from stable recurrent vision models
• Jointly embedding the local and global relations of heterogeneous graph for rumor detection
• Evolutionary Architecture Search For Deep Multitask Networks
• Application of quantum-inspired generative models to small molecular datasets
• Probabilistic Active Meta-Learning
• VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval
• Resilient In-Season Crop Type Classification in Multispectral Satellite Observations using Growth Stage Normalization
• Learning to Discriminate Information for Online Action Detection: Analysis and Application
• Deep Neural Network Approach to Forward-Inverse Problems
• Group Equivariant Generative Adversarial Networks
• Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
• Revisiting 2D Convolutional Neural Networks for Graph-based Applications
• ALOHA: Auxiliary Loss Optimization for Hypothesis Augmentation
• Self-Supervised 3D Keypoint Learning for Ego-motion Estimation
• DeepAISE -- An End-to-End Development and Deployment of a Recurrent Neural Survival Model for Early Prediction of Sepsis
• The Utility of Sparse Representations for Control in Reinforcement Learning
• Accelerating Inverse Rendering By Using a GPU and Reuse of Light Paths
• Hyper-Parameter Sweep on AlphaZero General
• Language Graph Distillation for Low-Resource Machine Translation
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Visual Depth Mapping from Monocular Images using Recurrent Convolutional Neural Networks
• SpikePipe: Accelerated Training of Spiking Neural Networks via Inter-Layer Pipelining and Multiprocessor Scheduling
• Towards fast machine-learning-assisted Bayesian posterior inference of microseismic event location and source mechanism
• Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction
• Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
• Pose Guided Fashion Image Synthesis Using Deep Generative Model
• Temporal Context Aggregation for Video Retrieval with Contrastive Learning
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets
• Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE
• ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network
• Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentation
• MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records
• Material Segmentation of Multi-View Satellite Imagery
• Differentiable Optics with dLux I: Deep calibration of Flat Field and Phase Retrieval with Automatic Differentiation
• Mix and match networks: encoder-decoder alignment for zero-pair image translation
• Deep Learning Blazar Classification based on Multi-frequency Spectral Energy Distribution Data
• Super-Resolution with Deep Adaptive Image Resampling
• A Survey of Latent Factor Models in Recommender Systems
• An adaptive safety layer with hard constraints for safe reinforcement learning in multi-energy management systems
• Spectrum-Guided Adversarial Disparity Learning
• Toward a full-scale neural machine translation in production: the Booking.com use case
• Scene Graph Parsing by Attention Graph
• Training GANs with Stronger Augmentations via Contrastive Discriminator
• Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
• Differentiable Rendering with Perturbed Optimizers
• Enhancing Explainability of Neural Networks through Architecture Constraints
• Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
• ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image
• Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
• FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network
• Dynamic Capacity Networks
• In Situ Cane Toad Recognition
• DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation
• Parton distribution functions
• Predicting 4D Liver MRI for MR-guided Interventions
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
• Music Source Separation with Generative Flow
• Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution
• GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
• TOM-Net: Learning Transparent Object Matting from a Single Image
• PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain
• Multimodal Approach for Harmonized System Code Prediction
• Learning a Static Bug Finder from Data
• Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
• Does Yoga Make You Happy? Analyzing Twitter User Happiness using Textual and Temporal Information
• ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
• Progressive Point Cloud Deconvolution Generation Network
• Learning of viscosity functions in rarefied gas flows with physics-informed neural networks
• Facial Expression Recognition Using Disentangled Adversarial Learning
• EAPS: Edge-Assisted Predictive Sleep Scheduling for 802.11 IoT Stations
• Leveraging the Channel as a Sensor: Real-time Vehicle Classification Using Multidimensional Radio-fingerprinting
• Data-driven multifidelity topology design with multi-channel variational auto-encoder for concurrent optimization of multiple design variable fields
• A single formula for the law of the wall and its application to wall-modelled large-eddy simulation
• Long-term Human Motion Prediction with Scene Context
• Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution
• Learning Dense Rewards for Contact-Rich Manipulation Tasks
• A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference
• Authorship Identification of Source Code Segments Written by Multiple Authors Using Stacking Ensemble Method
• Classification Logit Two-sample Testing by Neural Networks
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
• On Versatile Video Coding at UHD with Machine-Learning-Based Super-Resolution
• On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems
• Lightweight Adaptive Mixture of Neural and N-gram Language Models
• DebiasedRec: Bias-aware User Modeling and Click Prediction for Personalized News Recommendation
• Automatic breast cancer grading in lymph nodes using a deep neural network
• Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learning
• 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning
• Empirical study of extreme overfitting points of neural networks
• GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• Leveraging End-to-End Speech Recognition with Neural Architecture Search
• Hybrid Quantum-Classical Autoencoders for End-to-End Radio Communication
• Estimating semantic structure for the VQA answer space
• Prune and Replace NAS
• Fast Successive-Cancellation List Flip Decoding of Polar Codes
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
• DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
• Quantum Chaos and Circuit Parameter Optimization
• Federated Learning on Non-IID Data: A Survey
• Neural Machine Translation: A Review of Methods, Resources, and Tools
• Real-time Deep Video Deinterlacing
• GLONET: Mercator's end-to-end neural Global Ocean forecasting system
• Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning
• Counterfactual Credit Assignment in Model-Free Reinforcement Learning
• Learning Semantic Embedding Spaces for Slicing Vegetables
• Rare event failure test case generation in Learning-Enabled-Controllers
• Classification of Diabetic Retinopathy via Fundus Photography: Utilization of Deep Learning Approaches to Speed up Disease Detection
• Background Discrimination for Neutrinoless Double Beta Decay in Liquid Xenon Using Cherenkov Light
• Gromov-Wasserstein Factorization Models for Graph Clustering
• An IoT Based Framework For Activity Recognition Using Deep Learning Technique
• A Comparative Study on COVID-19 Fake News Detection Using Different Transformer Based Models
• Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
• Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation
• Multi-Task Learning in Histo-pathology for Widely Generalizable Model
• Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
• Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
• Faithful Inversion of Generative Models for Effective Amortized Inference
• Residual-Concatenate Neural Network with Deep Regularization Layers for Binary Classification
• A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models
• Translation-Enhanced Multilingual Text-to-Image Generation
• Deep Learning Based Computed Tomography Whys and Wherefores
• Memory-Efficient Network for Large-scale Video Compressive Sensing
• Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation
• AG2U -- Autonomous Grading Under Uncertainties
• Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
• SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
• Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision
• Personalized Language Model for Query Auto-Completion
• RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation
• General-to-Detailed GAN for Infrequent Class Medical Images
• Domain Attention Consistency for Multi-Source Domain Adaptation
• DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing
• MaLeFiSenta: Machine Learning for FilamentS Identification and orientation in the ISM
• Neural source-filter waveform models for statistical parametric speech synthesis
• Real galaxy mergers from galaxy pair catalogs
• Predicting ConceptNet Path Quality Using Crowdsourced Assessments of Naturalness
• Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement
• Deep transformation models for functional outcome prediction after acute ischemic stroke
• Image Matters: Visually modeling user behaviors using Advanced Model Server
• Robot Navigation with Map-Based Deep Reinforcement Learning
• A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis
• Automated Learning Rate Scheduler for Large-batch Training
• DeePN${}^2$: A deep learning-based non-Newtonian hydrodynamic model
• Deep Image Clustering with Category-Style Representation
• A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining
• Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods
• Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
• PRANK: motion Prediction based on RANKing
• Artificial Neural Network Modeling for Airline Disruption Management
• HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Images
• Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling
• Attention on Abstract Visual Reasoning
• Colour alignment for relative colour constancy via non-standard references
• ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER
• Efficient time stepping for numerical integration using reinforcement learning
• Learning Deep Nets for Gravitational Dynamics with Unknown Disturbance through Physical Knowledge Distillation: Initial Feasibility Study
• Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation
• Efficient Solutions of Fermionic Systems using Artificial Neural Networks
• Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective
• Targeted Nonlinear Adversarial Perturbations in Images and Videos
• A Two-stream Neural Network for Pose-based Hand Gesture Recognition
• Deriving Machine Attention from Human Rationales
• Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data
• Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation
• TAdam: A Robust Stochastic Gradient Optimizer
• Adding Attentiveness to the Neurons in Recurrent Neural Networks
• Deep learning for quality control of surface physiographic fields using satellite Earth observations
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• Control-Aware Representations for Model-based Reinforcement Learning
• Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
• Designing high-fidelity multi-qubit gates for semiconductor quantum dots through deep reinforcement learning
• Predicting distributions with Linearizing Belief Networks
• Space of Functions Computed by Deep-Layered Machines
• Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs
• A Latent Morphology Model for Open-Vocabulary Neural Machine Translation
• Cross-modal Deep Face Normals with Deactivable Skip Connections
• The Validation of Graph Model-Based, Gate Level Low-Dimensional Feature Data for Machine Learning Applications
• TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
• SCREENet: A Multi-view Deep Convolutional Neural Network for Classification of High-resolution Synthetic Mammographic Screening Scans
• Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training
• Deep Learning for Multi-User Proactive Beam Handoff: A 6G Application
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• Efficient Palm-Line Segmentation with U-Net Context Fusion Module
• Solving high-dimensional parabolic PDEs using the tensor train format
• Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing
• Mapping individual differences in cortical architecture using multi-view representation learning
• Learning to Impute: A General Framework for Semi-supervised Learning
• Parametric Gaussian Process Regressors
• A deep learning theory for neural networks grounded in physics
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
• Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Method
• Dynamic NeRFs for Soccer Scenes
• Joint Neural Collaborative Filtering for Recommender Systems
• Transform and Tell: Entity-Aware News Image Captioning
• GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB
• Fine-Grained Image Captioning with Global-Local Discriminative Objective
• Improvements to short-term weather prediction with recurrent-convolutional networks
• Diffusion-based Deep Active Learning
• A Deep Neuro-Fuzzy Network for Image Classification
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
• Learning-Based Reconstruction of FRI Signals
• LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT
• Rating for Parents: Predicting Children Suitability Rating for Movies Based on Language of the Movies
• Random Hinge Forest for Differentiable Learning
• Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016
• Interpreting Deep Learning: The Machine Learning Rorschach Test?
• Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
• A Federated Semi-Supervised Learning Approach for Network Traffic Classification
• A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering
• Learnable Spectro-temporal Receptive Fields for Robust Voice Type Discrimination
• Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• Recurrent neural network based parameter estimation of Hawkes model on high-frequency financial data
• Masked Conditional Neural Networks for Automatic Sound Events Recognition
• Czert -- Czech BERT-like Model for Language Representation
• Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects
• On-device modeling of user's social context and familiar places from smartphone-embedded sensor data
• SlimmeRF: Slimmable Radiance Fields
• Fast Face-swap Using Convolutional Neural Networks
• A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
• SPINE: Structural Identity Preserved Inductive Network Embedding
• Synthesizing Action Sequences for Modifying Model Decisions
• Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems
• Transfer Learning Study of Motion Transformer-based Trajectory Predictions
• Multi-grained Attention Networks for Single Image Super-Resolution
• Learning to Attend, Copy, and Generate for Session-Based Query Suggestion
• A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems
• The Wang-Landau Algorithm as Stochastic Optimization and Its Acceleration
• Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes
• Analytical derivatives of Neural Networks
• On the Importance of Consistency in Training Deep Neural Networks
• TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks
• Video Captioning with Guidance of Multimodal Latent Topics
• FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation
• Generating High Quality Visible Images from SAR Images Using CNNs
• ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks
• Analysis of Twitter Users' Lifestyle Choices using Joint Embedding Model
• Software defined demodulation of multiple frequency shift keying with dense neural network for weak signal communications
• SOAC: The Soft Option Actor-Critic Architecture
• LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
• Agent-Centric Representations for Multi-Agent Reinforcement Learning
• Data-to-Text Generation with Style Imitation
• RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
• Fully-Featured Attribute Transfer
• Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings
• Learning Probabilistic Coordinate Fields for Robust Correspondences
• Bringing Attention to CAD: Boundary Representation Learning via Transformer
• The NES Music Database: A multi-instrumental dataset with expressive performance attributes
• Information-theoretic machine learning for time-varying mode decomposition of separated aerodynamic flows
• Learning Variations in Human Motion via Mix-and-Match Perturbation
• Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
• Graph Classification via Deep Learning with Virtual Nodes
• Convolutional Neural Networks and Stokes Response Functions
• Deep Spiking Convolutional Neural Network for Single Object Localization Based On Deep Continuous Local Learning
• A machine learning approach to drug repositioning based on drug expression profiles: Applications to schizophrenia and depression/anxiety disorders
• Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
• Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations
• Capturing Financial markets to apply Deep Reinforcement Learning
• Learning to Reason With Adaptive Computation
• End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement
• Training a Fully Convolutional Neural Network to Route Integrated Circuits
• Generative networks as inverse problems with Scattering transforms
• Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
• Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
• A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection
• SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator
• Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media
• Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
• An Enhanced Knowledge Injection Model for Commonsense Generation
• E3D: Event-Based 3D Shape Reconstruction
• Compromise-free Bayesian neural networks
• Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
• Deep Subspace Clustering Networks
• Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information
• Syntactic Scaffolds for Semantic Structures
• Long term dynamics of the subgradient method for Lipschitz path differentiable functions
• Deep Generative Models to Extend Active Directory Graphs with Honeypot Users
• DECONET: an Unfolding Network for Analysis-based Compressed Sensing with Generalization Error Bounds
• Stock Price Prediction Under Anomalous Circumstances
• Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
• TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
• Maximum Entropy Flow Networks
• Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety
• MoEL: Mixture of Empathetic Listeners
• Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
• Semi-Supervised Learning with Normalizing Flows
• Textual Echo Cancellation
• Initializing LSTM internal states via manifold learning
• ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
• Data-Driven Estimation of Capacity Upper Bounds
• Information Potential Auto-Encoders
• Leveraging Non-uniformity in First-order Non-convex Optimization
• Deep Class Aware Denoising
• DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
• End-to-end optimized image compression with competition of prior distributions
• Interpretable Set Functions
• Towards Emotional Support Dialog Systems
• Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G
• MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction
• Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy
• Dangers of Bayesian Model Averaging under Covariate Shift
• Learning the Tangent Space of Dynamical Instabilities from Data
• A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
• A Qualitative Study of the Dynamic Behavior for Adaptive Gradient Algorithms
• Discriminative Pedestrian Features and Gated Channel Attention for Clothes-Changing Person Re-Identification
• Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
• N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems
• Large-scale Heteroscedastic Regression via Gaussian Process
• A Temporal-Spectral Fusion Transformer with Subject-Specific Adapter for Enhancing RSVP-BCI Decoding
• PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
• Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
• Support-Set Based Cross-Supervision for Video Grounding
• Better Text Understanding Through Image-To-Text Transfer
• Image Generation from Layout
• Deep Attentional Structured Representation Learning for Visual Recognition
• TPCN: Temporal Point Cloud Networks for Motion Forecasting
• Which cycling environment appears safer? Learning cycling safety perceptions from pairwise image comparisons
• Learning Filter Basis for Convolutional Neural Network Compression
• Single Image Reflection Removal through Cascaded Refinement
• Learning to Prove Theorems by Learning to Generate Theorems
• Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification
• Bounding Multivariate Trigonometric Polynomials with Applications to Filter Bank Design
• Generalized Bayesian Likelihood-Free Inference
• Video-Based Inpatient Fall Risk Assessment: A Case Study
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation
• Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion
• Provably Secure Generative Linguistic Steganography
• Fast ultrasonic imaging using end-to-end deep learning
• GapPredict: A Language Model for Resolving Gaps in Draft Genome Assemblies
• Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data
• Generating Representative Headlines for News Stories
• Temporal Embeddings and Transformer Models for Narrative Text Understanding
• Generating Grasp Poses for a High-DOF Gripper Using Neural Networks
• Learning from scarce information: using synthetic data to classify Roman fine ware pottery
• A Deep-learning-based Method for PIR-based Multi-person Localization
• FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
• Prediction of head motion from speech waveforms with a canonical-correlation-constrained autoencoder
• CAR-Net: Clairvoyant Attentive Recurrent Network
• Transformer based unsupervised pre-training for acoustic representation learning
• Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement
• Jointly Optimizing Diversity and Relevance in Neural Response Generation
• Dynamic Task Control Method of a Flexible Manipulator Using a Deep Recurrent Neural Network
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
• Adversarial Partial Multi-Label Learning
• Data-Efficient Mutual Information Neural Estimator
• Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
• Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation
• Query-based Attention CNN for Text Similarity Map
• Transfer Learning-based Channel Estimation in Orthogonal Frequency Division Multiplexing Systems Using Data-nulling Superimposed Pilots
• Automated Design using Neural Networks and Gradient Descent
• Semi-supervised Learning for Quantification of Pulmonary Edema in Chest X-Ray Images
• Multi-bin Trainable Linear Unit for Fast Image Restoration Networks
• Adversarial Attacks in Sound Event Classification
• DAGCN: Dual Attention Graph Convolutional Networks
• Physics-Informed Graph-Mesh Networks for PDEs: A hybrid approach for complex problems
• Improving Grammatical Error Correction with Machine Translation Pairs
• Rethinking Recurrent Neural Networks and Other Improvements for Image Classification
• Complementary to Multiple Labels: A Correlation-Aware Correction Approach
• ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification
• Identifying Learning Rules From Neural Network Observables
• PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
• Order Matters: Shuffling Sequence Generation for Video Prediction
• Admission Prediction in Undergraduate Applications: an Interpretable Deep Learning Approach
• Data Augmentation for Bayesian Deep Learning
• Between-class Learning for Image Classification
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
• Adversarial Defense of Image Classification Using a Variational Auto-Encoder
• End to End Trainable Active Contours via Differentiable Rendering
• Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
• Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
• Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface
• Predicting Semen Motility using three-dimensional Convolutional Neural Networks
• Pre-training Text Representations as Meta Learning
• All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network
• Analyzing the Engagement of Social Relationships During Life Event Shocks in Social Media
• Learning monocular depth estimation with unsupervised trinocular assumptions
• Naturalistic Driver Intention and Path Prediction using Recurrent Neural Networks
• Effective parameter estimation methods for an ExcitNet model in generative text-to-speech systems
• A Federated Learning Benchmark on Tabular Data: Comparing Tree-Based Models and Neural Networks
• Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
• Learning Operations on a Stack with Neural Turing Machines
• A Deep Neural Network for Finger Counting and Numerosity Estimation
• Variational Bi-LSTMs
• Learning Personal Style from Few Examples
• LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
• Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm
• Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data
• Variational Adaptive-Newton Method for Explorative Learning
• Learning a quantum channel from its steady-state
• PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex
• Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation
• A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning
• End-to-End Learning for Image Burst Deblurring
• ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
• Learning Independent Object Motion from Unlabelled Stereoscopic Videos
• Improved Chord Recognition by Combining Duration and Harmonic Language Models
• Self-supervised Motion Learning from Static Images
• Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder
• Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset
• Learning Autocomplete Systems as a Communication Game
• DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation
• Dynamic Context Correspondence Network for Semantic Alignment
• Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning
• MVF-Net: Multi-View 3D Face Morphable Model Regression
• Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
• Extended dynamic mode decomposition with dictionary learning using neural ordinary differential equations
• Information Geometry of Orthogonal Initializations and Training
• Generating Multiple Diverse Responses for Short-Text Conversation
• Beyond Imitation: Generative and Variational Choreography via Machine Learning
• Trigger Hunting with a Topological Prior for Trojan Detection
• MeshWalker: Deep Mesh Understanding by Random Walks
• Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
• Perceptual Extreme Super Resolution Network with Receptive Field Block
• Attention as a Guide for Simultaneous Speech Translation
• Geometric Style Transfer
• Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes
• Probing Neural Dialog Models for Conversational Understanding
• Modernizing Historical Documents: a User Study
• Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks
• Towards a Precipitation Bias Corrector against Noise and Maldistribution
• Dynamic Control of a Fiber Manufacturing Process using Deep Reinforcement Learning
• Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation
• Probabilistic selection of inducing points in sparse Gaussian processes
• Automatic view plane prescription for cardiac magnetic resonance imaging via supervision by spatial relationship between views
• Graph-Revised Convolutional Network
• Neural-networks model for force prediction in multi-principal-element alloys
• Instance-level Facial Attributes Transfer with Geometry-Aware Flow
• Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray
• Learning representations for multivariate time series with missing data using Temporal Kernelized Autoencoders
• Analysis of chaotic dynamical systems with autoencoders
• Image Correction via Deep Reciprocating HDR Transformation
• A Deep Learning based Framework to Detect and Recognize Humans using Contactless Palmprints in the Wild
• What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks
• Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
• Persis: A Persian Font Recognition Pipeline Using Convolutional Neural Networks
• Fiedler Regularization: Learning Neural Networks with Graph Sparsity
• Policy Evaluation with Latent Confounders via Optimal Balance
• TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
• Open-World Lifelong Graph Learning
• Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand
• Formal Methods for Autonomous Systems
• NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval
• PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets
• Measuring and Harnessing Transference in Multi-Task Learning
• Teaching DNNs to design fast fashion
• Retargeting video with an end-to-end framework
• Framing RNN as a kernel method: A neural ODE approach
• Zooming Into the Darknet: Characterizing Internet Background Radiation and its Structural Changes
• Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
• Neural Temporal Point Processes For Modelling Electronic Health Records
• Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze
• Scalable, Proposal-free Instance Segmentation Network for 3D Pixel Clustering and Particle Trajectory Reconstruction in Liquid Argon Time Projection Chambers
• Localizing Discriminative Visual Landmarks for Place Recognition
• Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
• Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
• TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
• Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees
• Beyond Fine Tuning: A Modular Approach to Learning on Small Data
• Forward Prediction for Physical Reasoning
• Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors
• Deep learning complete intersection Calabi-Yau manifolds
• Image-Based Soil Organic Carbon Remote Sensing from Satellite Images with Fourier Neural Operator and Structural Similarity
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations
• Deep Semi-Supervised Learning for Time Series Classification
• Extraction of Complex DNN Models: Real Threat or Boogeyman?
• Efficient Halftoning via Deep Reinforcement Learning
• Temporal Aggregate Representations for Long-Range Video Understanding
• TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding
• Spatially Covariant Lesion Segmentation
• Convolutional Regression for Visual Tracking
• RankGAN: A Maximum Margin Ranking GAN for Generating Faces
• BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine
• DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
• Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks
• Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics
• SkillSpan: Hard and Soft Skill Extraction from English Job Postings
• Return-based Scaling: Yet Another Normalisation Trick for Deep RL
• Student Performance Prediction Using Dynamic Neural Models
• Neural Machine Transliteration: Preliminary Results
• Reinforcement Learning for Load-balanced Parallel Particle Tracing
• Exploratory State Representation Learning
• Cross-Domain Perceptual Reward Functions
• Adaloss: Adaptive Loss Function for Landmark Localization
• Cardiac Arrhythmia Detection from ECG with Convolutional Recurrent Neural Networks
• Variational Inference for Deblending Crowded Starfields
• Deep Neural Network Based Active User Detection for Grant-free NOMA Systems
• EfficientSeg: An Efficient Semantic Segmentation Network
• An Unbiased Estimator of the Full-sky CMB Angular Power Spectrum at Large Scales using Neural Networks
• Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET
• Response to LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
• Powerpropagation: A sparsity inducing weight reparameterisation
• Point-less: More Abstractive Summarization with Pointer-Generator Networks
• Feature Reweighting for EEG-based Motor Imagery Classification
• Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation
• Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature Interactions
• Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
• Conditional Adversarial Networks for Multi-Domain Text Classification
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet
• Recapture as You Want
• LiBRe: A Practical Bayesian Approach to Adversarial Detection
• Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization
• Wasserstein Index Generation Model: Automatic Generation of Time-series Index with Application to Economic Policy Uncertainty
• Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data
• Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding
• GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environment
• Inducing Interpretable Representations with Variational Autoencoders
• Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control
• Exemplar Auditing for Multi-Label Biomedical Text Classification
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Docmarking: Real-Time Screen-Cam Robust Document Image Watermarking
• On Scalable and Efficient Computation of Large Scale Optimal Transport
• Towards a population-informed approach to the definition of data-driven models for structural dynamics
• Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
• Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping in Clutter by State Representation Learning Based on Disentanglement of a Raw Input Image
• Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study
• Very Deep Convolutional Neural Networks for Raw Waveforms
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Reservoir Computing Hardware with Cellular Automata
• Deep Representation for Patient Visits from Electronic Health Records
• Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
• Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
• Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC
• SATformer: Transformer-Based UNSAT Core Learning
• Real-time End-to-End Federated Learning: An Automotive Case Study
• High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
• On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference
• Sequential Experimental Design for X-Ray CT Using Deep Reinforcement Learning
• Experimental Performance of Blind Position Estimation Using Deep Learning
• To Split or Not to Split: The Impact of Disparate Treatment in Classification
• Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
• Implementation of Stochastic Quasi-Newton's Method in PyTorch
• Deep 2FBSDEs For Systems With Control Multiplicative Noise
• Learning from Label Proportions with Consistency Regularization
• Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization
• Hierarchical Feature Embedding for Attribute Recognition
• Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN
• Online Semi-Supervised Learning with Bandit Feedback
• Two-step Machine Learning Approach for Channel Estimation with Mixed Resolution RF Chains
• Adversarial Bi-Regressor Network for Domain Adaptive Regression
• Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
• Monocular Depth Estimators: Vulnerabilities and Attacks
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Graph Markov Network for Traffic Forecasting with Missing Data
• Neural Arithmetic Expression Calculator
• Blind Deinterleaving of Signals in Time Series with Self-attention Based Soft Min-cost Flow Learning
• BachProp: Learning to Compose Music in Multiple Styles
• Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network
• Neural Conditional Reweighting
• Deep Iterative Phase Retrieval for Ptychography
• Move Forward and Tell: A Progressive Generator of Video Descriptions
• Enforcing exact physics in scientific machine learning: a data-driven exterior calculus on graphs
• Lymph Node Graph Neural Networks for Cancer Metastasis Prediction
• Image Segmentation of Zona-Ablated Human Blastocysts
• EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
• Figure Captioning with Reasoning and Sequence-Level Training
• End-to-End Neural Ranking for eCommerce Product Search: an application of task models and textual embeddings
• Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
• Deep Keyphrase Generation
• Predicting Entity Popularity to Improve Spoken Entity Recognition by Virtual Assistants
• Self-supervised edge features for improved Graph Neural Network training
• Iterative peak-fitting of frequency-domain data via deep convolution neural networks
• ProtoryNet - Interpretable Text Classification Via Prototype Trajectories
• IVUS-Net: An Intravascular Ultrasound Segmentation Network
• Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions
• Inference over radiative transfer models using variational and expectation maximization methods
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
• Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning
• Neural Dynamics on Complex Networks
• Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery
• StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks
• Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks
• A Deep Learning-Based FPGA Function Block Detection Method with Bitstream to Image Transformation
• Examining the Benefits of Capsule Neural Networks
• Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization
• Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods
• Medical image super-resolution method based on dense blended attention network
• A Multimodal Dialogue System for Conversational Image Editing
• Action Unit Memory Network for Weakly Supervised Temporal Action Localization
• Domain-Scalable Unpaired Image Translation via Latent Space Anchoring
• Structuring Latent Spaces for Stylized Response Generation
• Deep Learning of Cell Classification using Microscope Images of Intracellular Microtubule Networks
• Group-wise Correlation Stereo Network
• Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks
• Solving PDEs on Unknown Manifolds with Machine Learning
• An AI System for Continuous Knee Osteoarthritis Severity Grading Using Self-Supervised Anomaly Detection with Limited Data
• Feature Assisted bi-directional LSTM Model for Protein-Protein Interaction Identification from Biomedical Texts
• Learning to Communicate Implicitly By Actions
• $(f,\Gamma )$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics
• Calibrating Bayesian Generative Machine Learning for Bayesiamplification
• Linear Convergence of Adaptive Stochastic Gradient Descent
• Multiscale sequence modeling with a learned dictionary
• Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
• Effective Actor-centric Human-object Interaction Detection
• ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
• BiAdam: Fast Adaptive Bilevel Optimization Methods
• Physics-Informed Neural Networks for Transonic Flows around an Airfoil
• Deep convolutional tensor network
• Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
• Information Newton's flow: second-order optimization method in probability space
• A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning
• Inverse design of plasma metamaterial devices with realistic elements
• Object classification on video data of meteors and meteor-like phenomena: algorithm and data
• A Hybrid Neural Network Model for Commonsense Reasoning
• Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition
• Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
• Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation
• Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
• DAmageNet: A Universal Adversarial Dataset
• SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control
• LaFurca: Iterative Refined Speech Separation Based on Context-Aware Dual-Path Parallel Bi-LSTM
• Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory
• A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
• An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
• Stable and expressive recurrent vision models
• Prototypical Clustering Networks for Dermatological Disease Diagnosis
• Realizing Quantum Boltzmann Machines Through Eigenstate Thermalization
• SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian
• Basis Prediction Networks for Effective Burst Denoising with Large Kernels
• Deep Neural Networks to Correct Sub-Precision Errors in CFD
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
• RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
• Stochastic Gradient Descent with Polyak's Learning Rate
• Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures
• Scene Graph Parsing as Dependency Parsing
• A DNN Based Post-Filter to Enhance the Quality of Coded Speech in MDCT Domain
• Self-supervised Learning for Single View Depth and Surface Normal Estimation
• Stochastic reserving with a stacked model based on a hybridized Artificial Neural Network
• Global and Local Reduced Models for Interacting, Heterogeneous Agents
• Automatic Tracking of the Muscle Tendon Junction in Healthy and Impaired Subjects using Deep Learning
• Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
• Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
• Dynamic Tomography Reconstruction by Projection-Domain Separable Modeling
• Convolution Aware Initialization
• Deep Semi-Supervised Learning with Linguistically Motivated Sequence Labeling Task Hierarchies
• A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering
• Automatic Variational ABC
• Reblur2Deblur: Deblurring Videos via Self-Supervised Learning
• Deep analytics of atomically-resolved images: manifest and latent features
• Deep Stacked Networks with Residual Polishing for Image Inpainting
• Context-Aware Semantic Inpainting
• Real-value and confidence prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning
• Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things
• DLR : Toward a deep learned rhythmic representation for music content analysis
• Error Correction for Dense Semantic Image Labeling
• Improving Visually Grounded Sentence Representations with Self-Attention
• Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks
• Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Accumulated Gradient Normalization
• Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks
• Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning
• Leveraging Discourse Information Effectively for Authorship Attribution
• Material Editing Using a Physically Based Rendering Network
• Variational Generative Stochastic Networks with Collaborative Shaping
• Deep residual learning in CT physics: scatter correction for spectral CT
• Modeling Label Ambiguity for Neural List-Wise Learning to Rank
• Specializing Joint Representations for the task of Product Recommendation
• Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• Human-like Clustering with Deep Convolutional Neural Networks
• TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation
• Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network
• Self-supervised Hyperspectral Image Restoration using Separable Image Prior
• Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn from a Digital Twin
• Lifelong Bayesian Optimization
• Deep Learning of Preconditioners for Conjugate Gradient Solvers in Urban Water Related Problems
• Improving Visual Question Answering by Referring to Generated Paragraph Captions
• Multi-objects Generation with Amortized Structural Regularization
• Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods
• RF-Net: An End-to-End Image Matching Network based on Receptive Field
• Controlled CNN-based Sequence Labeling for Aspect Extraction
• Learning Perspective Undistortion of Portraits
• A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
• New Item Consumption Prediction Using Deep Learning
• Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization
• AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
• Time-series Insights into the Process of Passing or Failing Online University Courses using Neural-Induced Interpretable Student States
• ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning
• Something's Brewing! Early Prediction of Controversy-causing Posts from Discussion Features
• Reconstruction of $\tau$ lepton pair invariant mass using an artificial neural network
• Learning Correspondence from the Cycle-Consistency of Time
• Learning Bodily and Temporal Attention in Protective Movement Behavior Detection
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
• Making Neural Machine Reading Comprehension Faster
• Using Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery
• Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching
• Deep Learning for UL/DL Channel Calibration in Generic Massive MIMO Systems
• Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
• Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning
• On the Variance of Unbiased Online Recurrent Optimization
• Artificial Intelligence and Machine Learning to Predict and Improve Efficiency in Manufacturing Industry
• A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series Forecasting
• Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
• Deep Learning-Aided Trainable Projected Gradient Decoding for LDPC Codes
• On Relativistic $f$-Divergences
• Closing the gap towards end-to-end autonomous vehicle system
• Exploring spectro-temporal features in end-to-end convolutional neural networks
• Music Artist Classification with Convolutional Recurrent Neural Networks
• Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension
• PuzzleNet: Scene Text Detection by Segment Context Graph Learning
• Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
• Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• Classifying the classifier: dissecting the weight space of neural networks
• Superbloom: Bloom filter meets Transformer
• Continuous Geodesic Convolutions for Learning on 3D Shapes
• Deep synthesis regularization of inverse problems
• Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networks
• Natural Image Matting via Guided Contextual Attention
• Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
• Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
• Leveraging Dependency Forest for Neural Medical Relation Extraction
• Deep Learning based Multiple Regression to Predict Total Column Water Vapor (TCWV) from Physical Parameters in West Africa by using Keras Library
• Multimodal Generative Models for Compositional Representation Learning
• U-CNNpred: A Universal CNN-based Predictor for Stock Markets
• Lidar-Camera Co-Training for Semi-Supervised Road Detection
• Traffic map prediction using UNet based deep convolutional neural network
• Differentiable Meta-learning Model for Few-shot Semantic Segmentation
• WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation
• Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network
• A Hierarchical Location Prediction Neural Network for Twitter User Geolocation
• Bootstrapping deep music separation from primitive auditory grouping principles
• Texture Bias Of CNNs Limits Few-Shot Classification Performance
• Heterogeneous Graph Matching Networks
• Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
• Robust and efficient algorithms for high-dimensional black-box quantum optimization
• Learning from Indirect Observations
• Model-based Behavioral Cloning with Future Image Similarity Learning
• Neural Turtle Graphics for Modeling City Road Layouts
• Adversarial Colorization Of Icons Based On Structure And Color Conditions
• On Universal Equivariant Set Networks
• Sentence Constituent-Aware Aspect-Category Sentiment Analysis with Graph Attention Networks
• Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Learning from Multimodal and Multitemporal Earth Observation Data for Building Damage Mapping
• Semantic Graph Based Place Recognition for 3D Point Clouds
• Using Deep Networks for Scientific Discovery in Physiological Signals
• Learning Trailer Moments in Full-Length Movies
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
• AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• A Lightweight Neural Network for Monocular View Generation with Occlusion Handling
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
• Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
• Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation
• HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
• Usefulness of interpretability methods to explain deep learning based plant stress phenotyping
• Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation
• Policy Gradient Optimization of Thompson Sampling Policies
• Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies
• Graph-Aware Transformer: Is Attention All Graphs Need?
• DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction
• Light-in-the-loop: using a photonics co-processor for scalable training of neural networks
• Robust Object Detection under Occlusion with Context-Aware CompositionalNets
• Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks
• qDKT: Question-centric Deep Knowledge Tracing
• Inverse Estimation of Elastic Modulus Using Physics-Informed Generative Adversarial Networks
• Domain Adaptation for Image Dehazing
• Plan2Vec: Unsupervised Representation Learning by Latent Plans
• Inter-sequence Enhanced Framework for Personalized Sequential Recommendation
• Neural Topic Modeling with Bidirectional Adversarial Training
• The 1st Agriculture-Vision Challenge: Methods and Results
• Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences
• What is Wrong with One-Class Anomaly Detection?
• DAGN: Discourse-Aware Graph Network for Logical Reasoning
• Attention-based model for predicting question relatedness on Stack Overflow
• CDFI: Compression-Driven Network Design for Frame Interpolation
• Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling
• Consistent Sparse Deep Learning: Theory and Computation
• NeRD: Neural Representation of Distribution for Medical Image Segmentation
• Causal Analysis of Agent Behavior for AI Safety
• Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
• Contrastive Unsupervised Learning for Speech Emotion Recognition
• Partition of unity networks: deep hp-approximation
• Measuring Dependence with Matrix-based Entropy Functional
• An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation
• Deep Dose Plugin Towards Real-time Monte Carlo Dose Calculation Through a Deep Learning based Denoising Algorithm
• DenoiSpeech: Denoising Text to Speech with Frame-Level Noise Modeling
• Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording
• Deep-Learning-Based Kinematic Reconstruction for DUNE
• Convex Regularization Behind Neural Reconstruction
• ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
• A Machine Learning Approach to Correcting Atmospheric Seeing in Solar Flare Observations
• AIM 2020 Challenge on Rendering Realistic Bokeh
• A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning
• Frequency-compensated PINNs for Fluid-dynamic Design Problems
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
• Learning Vision-based Reactive Policies for Obstacle Avoidance
• Large-Scale MIDI-based Composer Classification
• Patch vs. Global Image-Based Unsupervised Anomaly Detection in MR Brain Scans of Early Parkinsonian Patients
• The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
• FR-Detect: A Multi-Modal Framework for Early Fake News Detection on Social Media Using Publishers Features
• On Accelerating Distributed Convex Optimizations
• Learning intermolecular forces at liquid-vapor interfaces
• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
• LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization
• Robust Nonparametric Regression with Deep Neural Networks
• Cross-modal Attention for MRI and Ultrasound Volume Registration
• 1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
• Dual Reweighting Domain Generalization for Face Presentation Attack Detection
• Predicting bulge to total luminosity ratio of galaxies using deep learning
• Psycholinguistic Tripartite Graph Network for Personality Detection
• Variational Leakage: The Role of Information Complexity in Privacy Leakage
• Adversarial Attack and Defense in Deep Ranking
• Controllable Abstractive Dialogue Summarization with Sketch Supervision
• Hierarchically Regularized Deep Forecasting
• StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
• Singing Language Identification using a Deep Phonotactic Approach
• Homography-Based Loss Function for Camera Pose Regression
• Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentation
• HoneyModels: Machine Learning Honeypots
• Acoustic Event Detection with Classifier Chains
• ECAS-ML: Edge Computing Assisted Adaptation Scheme with Machine Learning for HTTP Adaptive Streaming
• How Powerful are Interest Diffusion on Purchasing Prediction: A Case Study of Taocode
• FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
• Coverings of planar and three-dimensional sets with subsets of smaller diameter
• Discriminatory and orthogonal feature learning for noise robust keyword spotting
• POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
• The Beauty of Repetition in Machine Composition Scenarios
• Brain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System
• An Exploration of How Training Set Composition Bias in Machine Learning Affects Identifying Rare Objects
• Personalized Image Enhancement Featuring Masked Style Modeling
• Visual Reasoning: from State to Transformation
• Item Graph Convolution Collaborative Filtering for Inductive Recommendations
• Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
• Learning Coordination Policies over Heterogeneous Graphs for Human-Robot Teams via Recurrent Neural Schedule Propagation
• A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
• SSIN: Self-Supervised Learning for Rainfall Spatial Interpolation
• A hybrid approach for solving the gravitational N-body problem with Artificial Neural Networks
• Image-Text Pre-Training for Logo Recognition
• AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• A Multi-Task, Multi-Modal Approach for Predicting Categorical and Dimensional Emotions
• Radiomics-guided Multimodal Self-attention Network for Predicting Pathological Complete Response in Breast MRI
• Provably-Stable Neural Network-Based Control of Nonlinear Systems
• Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks
• Map-level baryonification: unified treatment of weak lensing two-point and higher-order statistics
• DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset
• A PINN Methodology for Temperature Field Reconstruction in the PIV Measurement Plane: Case of Rayleigh-Bénard Convection
• Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
• CLIP4Sketch: Enhancing Sketch to Mugshot Matching through Dataset Augmentation using Diffusion Models
• Lowering threshold of NaI(Tl) scintillator to 0.7 keV in the COSINE-100 experiment
• D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention
• Site-Specific Ground Motion Generative Model for Crustal Earthquakes in Japan Based on Generative Adversarial Networks
• Unsupervised Learning for Equitable DER Control
• FieldNet: Efficient Real-Time Shadow Removal for Enhanced Vision in Field Robotics
• Towards quantum gravity with neural networks: Solving the quantum Hamilton constraint of U(1) BF theory
• Monocular Per-Object Distance Estimation with Masked Object Modeling
• Learning Domain-Independent Heuristics for Grounded and Lifted Planning
• PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction
• End-to-End Chess Recognition
• Shape Completion with Prediction of Uncertain Regions
• JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval
• A hybrid finite element/neural network solver and its application to the Poisson problem
• Accelerating Distributed ML Training via Selective Synchronization
• Clarify Confused Nodes via Separated Learning
• Invertible residual networks in the context of regularization theory for linear inverse problems
• Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models
• Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?
• Tempo vs. Pitch: understanding self-supervised tempo estimation
• Decoding Neural Activity to Assess Individual Latent State in Ecologically Valid Contexts
• Learning to Recover Spectral Reflectance from RGB Images
• Scavenger: A Cloud Service for Optimizing Cost and Performance of ML Training
• DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning
• STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
• Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings
• Machine Learning for Relaying Topology: Optimization of IoT Network with Energy Harvesting
• Forged Image Detection using SOTA Image Classification Deep Learning Methods for Image Forensics with Error Level Analysis
• Understanding COVID-19 Vaccine Campaign on Facebook using Minimal Supervision
• Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
• Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
• Deep learning for track recognition in pixel and strip-based particle detectors
• Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration
• CCOM-HuQin: an Annotated Multimodal Chinese Fiddle Performance Dataset
• Unrolled Compressed Blind-Deconvolution
• Modeling Soft-Failure Evolution for Triggering Timely Repair with Low QoT Margins
• Quantum topology optimization of ground structures using noisy intermediate-scale quantum devices
• Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors
• On Classifying Images using Quantum Image Representation
• Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
• RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
• Binarizing by Classification: Is soft function really necessary?
• On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
• Parallel Synthesis for Autoregressive Speech Generation
• Reducing overestimating and underestimating volatility via the augmented blending-ARCH model
• Variational quantum simulation of long-range interacting systems
• Memory-guided Image De-raining Using Time-Lapse Data
• The Dark Side of the Language: Pre-trained Transformers in the DarkNet
• Validation and Generalizability of Self-Supervised Image Reconstruction Methods for Undersampled MRI
• Analyzing Multispectral Satellite Imagery of South American Wildfires Using Deep Learning
• Inferring Markovian quantum master equations of few-body observables in interacting spin chains
• Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis
• Leveraging Unsupervised Image Registration for Discovery of Landmark Shape Descriptor
• Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
• Identification of new M31 star cluster candidates from PAndAS images using convolutional neural networks
• Path Integral Sampler: a stochastic control approach for sampling
• Phonology Recognition in American Sign Language
• Perturbated Gradients Updating within Unit Space for Deep Learning
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
• Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information
• EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
• Multi-frame Joint Enhancement for Early Interlaced Videos
• Learning through structure: towards deep neuromorphic knowledge graph embeddings
• SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
• Sensing Integrated DFT-Spread OFDM Waveform and Deep Learning-powered Receiver Design for Terahertz Integrated Sensing and Communication Systems
• Did you take the pill? - Detecting Personal Intake of Medicine from Twitter
• Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes
• Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
• Normalized Augmented Inverse Probability Weighting with Neural Network Predictions
• Adaptive Sample Selection for Robust Learning under Label Noise
• Towards Interpretable Attention Networks for Cervical Cancer Analysis
• Prediction of Ultrasonic Guided Wave Propagation in Solid-fluid and their Interface under Uncertainty using Machine Learning
• A Fusion-Denoising Attack on InstaHide with Data Augmentation
• A Unified Transferable Model for ML-Enhanced DBMS
• CosmicRIM : Reconstructing Early Universe by Combining Differentiable Simulations with Recurrent Inference Machines
• Accurate Prediction of Bonding Properties by A Machine Learning-based Model using Isolated States Before Bonding
• Ranking Structured Objects with Graph Neural Networks
• Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models
• DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• Neural Network Training as an Optimal Control Problem: An Augmented Lagrangian Approach
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
• Nondeterminism and Instability in Neural Network Optimization
• Trumpets: Injective Flows for Inference and Inverse Problems
• From Extreme Multi-label to Multi-class: A Hierarchical Approach for Automated ICD-10 Coding Using Phrase-level Attention
• Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
• Model-Based Domain Generalization
• Sequential Neural Posterior and Likelihood Approximation
• Identifying acoustic wave sources on the Sun I. Two-dimensional waves in a simulated photosphere
• Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations
• Robust Asymmetric Learning in POMDPs
• Autonomous Robotic Screening of Tubular Structures based only on Real-Time Ultrasound Imaging Feedback
• Deoscillated Graph Collaborative Filtering
• A Sequence-to-Sequence Approach to Dialogue State Tracking
• Power Allocation for Relayed OFDM with Index Modulation Assisted by Artificial Neural Network
• Probabilistic Numeric Convolutional Neural Networks
• Wireless Localisation in WiFi using Novel Deep Architectures
• GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
• Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries
• AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data
• Adversarial Robustness of Supervised Sparse Coding
• Schizophrenia-mimicking layers outperform conventional neural network layers
• AutoKWS: Keyword Spotting with Differentiable Architecture Search
• Inverse modified differential equations for discovery of dynamics
• Deep Self-Supervised Hierarchical Clustering for Speaker Diarization
• Generate High Resolution Images With Generative Variational Autoencoder
• Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting
• Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction
• Learning Differentiable Programs with Admissible Neural Heuristics
• Low-light Image Restoration with Short- and Long-exposure Raw Pairs
• VINNAS: Variational Inference-based Neural Network Architecture Search
• Adaptive L2 Regularization in Person Re-Identification
• To Each Optimizer a Norm, To Each Norm its Generalization
• AMEIR: Automatic Behavior Modeling, Interaction Exploration and MLP Investigation in the Recommender System
• Critical Assessment of Transfer Learning for Medical Image Segmentation with Fully Convolutional Neural Networks
• Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning
• Multi Layer Neural Networks as Replacement for Pooling Operations
• Neural Methods for Point-wise Dependency Estimation
• End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network
• Attend and Decode: 4D fMRI Task State Decoding Using Attention Models
• A Recursive Network with Dynamic Attention for Monaural Speech Enhancement
• Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling
• Correspondence Networks with Adaptive Neighbourhood Consensus
• Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
• DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains
• DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos
• Learning Cost Functions for Optimal Transport
• A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functions
• Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
• Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
• Information Theoretic Model Predictive Q-Learning
• Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds
• Tag-less Back-Translation
• Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
• A Bayesian Approach to Recurrence in Neural Networks
• Modeling plate and spring reverberation using a DSP-informed deep neural network
• Two-sample Testing Using Deep Learning
• X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trust
• Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks
• On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
• Improving End-to-End Sequential Recommendations with Intent-aware Diversification
• Open Event Extraction from Online Text using a Generative Adversarial Network
• SDIT: Scalable and Diverse Cross-domain Image Translation
• With Malice Towards None: Assessing Uncertainty via Equalized Coverage
• EMPNet: Neural Localisation and Mapping Using Embedded Memory Points
• Automatic acute ischemic stroke lesion segmentation using semi-supervised learning
• Nesterov's method with decreasing learning rate leads to accelerated stochastic gradient descent
• Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods
• Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval
• Is Texture Predictive for Age and Sex in Brain MRI?
• Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
• Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions
• Improving VAEs' Robustness to Adversarial Attack
• Learning Feature Embeddings for Discriminant Model based Tracking
• cGANs with Conditional Convolution Layer
• Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximations
• Solving general elliptical mixture models through an approximate Wasserstein manifold
• AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
• Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation
• Amortized Bethe Free Energy Minimization for Learning MRFs
• Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields
• Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting
• Structured Output Learning with Conditional Generative Flows
• Investigating an Effective Character-level Embedding in Korean Sentence Classification
• FReeNet: Multi-Identity Face Reenactment
• Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
• Complex Trainable ISTA for Linear and Nonlinear Inverse Problems
• Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
• Reduced-order Deep Learning for Flow Dynamics
• Building Sequential Inference Models for End-to-End Response Selection
• Multiple Instance Learning for ECG Risk Stratification
• Learning to Take Directions One Step at a Time
• Effects of Loss Functions And Target Representations on Adversarial Robustness
• Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization
• Web Applicable Computer-aided Diagnosis of Glaucoma Using Deep Learning
• Combining High-Level Features of Raw Audio Waves and Mel-Spectrograms for Audio Tagging
• Fine Grained Classification of Personal Data Entities
• MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image
• Strength in Numbers: Trading-off Robustness and Computation via Adversarially-Trained Ensembles
• Sequential Neural Methods for Likelihood-free Inference
• Generating Responses Expressing Emotion in an Open-domain Dialogue System
• Leveraging Financial News for Stock Trend Prediction with Attention-Based Recurrent Neural Network
• DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
• Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks
• Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding
• InstaNAS: Instance-aware Neural Architecture Search
• Deep Object-Centric Policies for Autonomous Driving
• Gradient target propagation
• Sequence-to-sequence Models for Small-Footprint Keyword Spotting
• ReviewQA: a relational aspect-based opinion reading dataset
• Using stigmergy to incorporate the time into artificial neural networks
• A Multimodal Approach towards Emotion Recognition of Music using Audio and Lyrical Content
• Deep Quality-Value (DQV) Learning
• A Neural Transition-based Model for Nested Mention Recognition
• Unbiased deep solvers for linear parametric PDEs
• MeshAdv: Adversarial Meshes for Visual Recognition
• Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
• Sampled Policy Gradient for Learning to Play the Game Agar.io
• Time Series Analysis of Clickstream Logs from Online Courses
• A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification
• Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data
• GANs beyond divergence minimization
• Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models
• Variational Autoencoder with Implicit Optimal Priors
• Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network
• Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
• LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
• An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
• Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis
• Neural Named Entity Recognition from Subword Units
• Generative Adversarial Frontal View to Bird View Synthesis
• Towards Effective Deep Embedding for Zero-Shot Learning
• Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
• Improving the Annotation of DeepFashion Images for Fine-grained Attribute Recognition
• Layer-wise Relevance Propagation for Explainable Recommendations
• Deep Learning Detection Networks in MIMO Decode-Forward Relay Channels
• A Simple but Effective Classification Model for Grammatical Error Correction
• Using Mode Connectivity for Loss Landscape Analysis
• Sparse Pursuit and Dictionary Learning for Blind Source Separation in Polyphonic Music Recordings
• Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
• Implicit Policy for Reinforcement Learning
• Towards multi-instrument drum transcription
• Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
• Wearable Audio and IMU Based Shot Detection in Racquet Sports
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Fusion Graph Convolutional Networks
• Multi-modality Sensor Data Classification with Selective Attention
• Variational Inference In Pachinko Allocation Machines
• Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
• Detecting Alzheimer's Disease Using Gated Convolutional Neural Network from Audio Data
• ClickBAIT-v2: Training an Object Detector in Real-Time
• Reinforcement Learning for Fair Dynamic Pricing
• Learn to segment single cells with deep distance estimator and deep cell detector
• Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps
• Learning Sparse Wavelet Representations
• Music Genre Classification using Masked Conditional Neural Networks
• Dual Recurrent Attention Units for Visual Question Answering
• Tensor Decomposition for Compressing Recurrent Neural Network
• Multiple Description Convolutional Neural Networks for Image Compression
• Ensemble Neural Relation Extraction with Adaptive Boosting
• Differentiable lower bound for expected BLEU score
• ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
• Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks
• Liquid Splash Modeling with Neural Networks
• Simplified End-to-End MMI Training and Voting for ASR
• Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding
• Real-time visual tracking by deep reinforced decision making
• Intent Recognition in Smart Living Through Deep Recurrent Neural Networks
• Composing Music with Grammar Argumented Neural Networks and Note-Level Encoding
• PixelCNN Models with Auxiliary Variables for Natural Image Modeling
• #HashtagWars: Learning a Sense of Humor
• Morphological Inflection Generation with Hard Monotonic Attention
• One-to-Many Network for Visually Pleasing Compression Artifacts Reduction
• Low-rank passthrough neural networks
• MimosaNet: An Unrobust Neural Network Preventing Model Stealing
• How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part I: the 1-D Case of Two Layers with Random First Layer
• About optimal loss function for training physics-informed neural networks under respecting causality
• Sequential learning based PINNs to overcome temporal domain complexities in unsteady flow past flapping wings
• Adversarial Image Alignment and Interpolation
• Environmentally Adaptive Control Including Variance Minimization Using Stochastic Predictive Network with Parametric Bias: Application to Mobile Robots
• A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions
• Deep Shape from Polarization
• Online Learning of Wheel Odometry Correction for Mobile Robots with Attention-based Neural Network
• Generative Dual Adversarial Network for Generalized Zero-shot Learning
• Modeling Taxi Drivers' Behaviour for the Next Destination Prediction
• Comparison of Machine Learning Methods for Predicting Karst Spring Discharge in North China
• A Deep Learning Approach for COVID-19 Trend Prediction
• Recommendation Through Mixtures of Heterogeneous Item Relationships
• Semantic-aware Image Deblurring
• Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
• All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling
• Deep Residual Network for Joint Demosaicing and Super-Resolution
• A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
• Meta Learning for Few-Shot One-class Classification
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Autonomous Driving using Safe Reinforcement Learning by Incorporating a Regret-based Human Lane-Changing Decision Model
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Deep Reinforcement Learning with Feedback-based Exploration
• Hierarchical deep learning-based adaptive time-stepping scheme for multiscale simulations
• Attentive Normalization for Conditional Image Generation
• LUCSS: Language-based User-customized Colourization of Scene Sketches
• DRILL: Dynamic Representations for Imbalanced Lifelong Learning
• Active learning for object detection in high-resolution satellite images
• Attentive batch normalization for lstm-based acoustic modeling of speech recognition
• Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations
• A 1Mb mixed-precision quantized encoder for image classification and patch-based compression
• CFSNet: Toward a Controllable Feature Space for Image Restoration
• Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
• Non-parallel Voice Conversion System with WaveNet Vocoder and Collapsed Speech Suppression
• Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
• Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes
• Generating artificial digital image correlation data using physics-guided adversarial networks
• Hubbard-Stratonovich Detector for Simple Trainable MIMO Signal Detection
• Improving Entity Linking by Modeling Latent Entity Type Information
• Teaching Robots Novel Objects by Pointing at Them
• Non-Gaited Legged Locomotion with Monte-Carlo Tree Search and Supervised Learning
• Identifying Sub-Phenotypes of Acute Kidney Injury using Structured and Unstructured Electronic Health Record Data with Memory Networks
• Prevent the Language Model from being Overconfident in Neural Machine Translation
• FMCode: A 3D In-the-Air Finger Motion Based User Login Framework for Gesture Interface
• Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing
• Active Learning for Breast Cancer Identification
• Pre-training Graph Transformer with Multimodal Side Information for Recommendation
• A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification
• Deep Reinforcement Learning in Fluid Mechanics: a promising method for both Active Flow Control and Shape Optimization
• STRIDE : Scene Text Recognition In-Device
• Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN
• Generative Hybrid Representations for Activity Forecasting with No-Regret Learning
• A pipeline for fair comparison of graph neural networks in node classification tasks
• Leveraging Event Specific and Chunk Span features to Extract COVID Events from tweets
• Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution
• Prediction-based One-shot Dynamic Parking Pricing
• Supervising the Transfer of Reasoning Patterns in VQA
• A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences
• Generative Deep Learning Techniques for Password Generation
• DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
• Deep Learning for Explicitly Modeling Optimization Landscapes
• Neural Network Model for Structure Factor of Polymer Systems
• Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
• Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
• Approximating the Hotelling Observer with Autoencoder-Learned Efficient Channels for Binary Signal Detection Tasks
• Motif Difference Field: A Simple and Effective Image Representation of Time Series for Classification
• Scalable Kernel Logistic Regression with Nyström Approximation: Theoretical Analysis and Application to Discrete Choice Modelling
• Shape Generation using Spatially Partitioned Point Clouds
• Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
• Distributed Training of Graph Convolutional Networks using Subgraph Approximation
• Estimating initial conditions for dynamical systems with incomplete information
• Can GAN Learn Topological Features of a Graph?
• Sequence Generation with Guider Network
• Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks
• Deep Learning in Robotics: A Review of Recent Research
• Predicting the motion of a high-Q pendulum subject to seismic perturbations using machine learning
• An Experience-based Direct Generation approach to Automatic Image Cropping
• Demand Forecasting from Spatiotemporal Data with Graph Networks and Temporal-Guided Embedding
• You Are Here: Geolocation by Embedding Maps and Images
• Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential Recommendation
• Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
• Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
• Adaptive Step Sizes in Variance Reduction via Regularization
• Deep learning-based estimation of whole-body kinematics from multi-view images
• Machine Learning for Generalizable Prediction of Flood Susceptibility
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
• Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
• Deep learning for lithological classification of carbonate rock micro-CT images
• Pseudo-Rehearsal for Continual Learning with Normalizing Flows
• Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• Towards Better Long-range Time Series Forecasting using Generative Adversarial Networks
• Investigating Recurrence and Eligibility Traces in Deep Q-Networks
• Straight to Shapes: Real-time Detection of Encoded Shapes
• Uncertainty Prediction for Deep Sequential Regression Using Meta Models
• Automatic coding of students' writing via Contrastive Representation Learning in the Wasserstein space
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
• Using probabilistic programs as proposals
• Approaching the Limit of Image Rescaling via Flow Guidance
• Consistent Representation Learning for High Dimensional Data Analysis
• Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs
• Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
• Simple Models for Word Formation in English Slang
• Heterogeneous Graph Attention Networks for Early Detection of Rumors on Twitter
• BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
• Product Kanerva Machines: Factorized Bayesian Memory
• Deep learning method for identifying mass composition of ultra-high-energy cosmic rays
• Learning Fine Grained Place Embeddings with Spatial Hierarchy from Human Mobility Trajectories
• Collaborative Label Correction via Entropy Thresholding
• ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
• Deep Gaussian Markov Random Fields
• SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation
• Nested Multiple Instance Learning in Modelling of HTTP network traffic
• Anomalous Sound Detection using unsupervised and semi-supervised autoencoders and gammatone audio representation
• Mini-batch stochastic gradient descent with dynamic sample sizes
• A new regret analysis for Adam-type algorithms
• Handling Long-Tail Queries with Slice-Aware Conversational Systems
• Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
• Sens-BERT: Enabling Transferability and Re-calibration of Calibration Models for Low-cost Sensors under Reference Measurements Scarcity
• Indoor Localization Techniques Within a Home Monitoring Platform
• Out-of-Sample Extrapolation with Neuron Editing
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment
• Single- to multi-fidelity history-dependent learning with uncertainty quantification and disentanglement: application to data-driven constitutive modeling
• cosmosage: A Natural-Language Assistant for Cosmologists
• mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
• A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
• Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency
• Regularising Non-linear Models Using Feature Side-information
• Learning to Transfer: Unsupervised Meta Domain Translation
• Temporal Convolution Derived Multi-Layered Reservoir Computing
• Parameter-Free Style Projection for Arbitrary Style Transfer
• Probabilistic Generative Adversarial Networks
• Neuromorphic computing for attitude estimation onboard quadrotors
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals
• Full-Network Embedding in a Multimodal Embedding Pipeline
• Learning Object-Centric Video Models by Contrasting Sets
• Weak-Attention Suppression For Transformer Based Speech Recognition
• Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism
• Simulating Diffusion Bridges with Score Matching
• An Encoder-Decoder CNN for Hair Removal in Dermoscopic Images
• Deep Semantic Architecture with discriminative feature visualization for neuroimage analysis
• A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks
• Improving Direct Physical Properties Prediction of Heterogeneous Materials from Imaging Data via Convolutional Neural Network and a Morphology-Aware Generative Model
• Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
• Set-Conditional Set Generation for Particle Physics
• Reinforced Medical Report Generation with X-Linear Attention and Repetition Penalty
• On the equivalence of molecular graph convolution and molecular wave function with poor basis set
• The 2ST-UNet for Pneumothorax Segmentation in Chest X-Rays using ResNet34 as a Backbone for U-Net
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence Model
• Latent Iterative Refinement for Modular Source Separation
• Self-supervised Graph Representation Learning via Bootstrapping
• Improving Source Separation via Multi-Speaker Representations
• Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames
• Energy-Based Models for Code Generation under Compilability Constraints
• Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
• Learning Manifold Patch-Based Representations of Man-Made Shapes
• MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
• Physics-regularized neural network of the ideal-MHD solution operator in Wendelstein 7-X configurations
• Label-Agnostic Sequence Labeling by Copying Nearest Neighbors
• Gradient descent revisited via an adaptive online learning rate
• CNN depth analysis with different channel inputs for Acoustic Scene Classification
• Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors
• Environmental Sound Recognition using Masked Conditional Neural Networks
• Bayesian Multi-Scale Neural Network for Crowd Counting
• Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation
• Arabic aspect based sentiment analysis using bidirectional GRU based models
• End-to-end optimization of nonlinear transform codes for perceptual quality
• A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
• Approximating meta-heuristics with homotopic recurrent neural networks
• Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations
• Compositional Video Synthesis with Action Graphs
• Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited Memory
• Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Resource-Constrained Federated Learning with Heterogeneous Labels and Models
• Improving RNN transducer with normalized jointer network
• Learning to Optimise General TSP Instances
• Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
• A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning
• End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data
• Twitter User Representation Using Weakly Supervised Graph Embedding
• Active Robotic Mapping through Deep Reinforcement Learning
• Convolutional Sparse Support Estimator Network (CSEN) From energy efficient support estimation to learning-aided Compressive Sensing
• Modeling Music Modality with a Key-Class Invariant Pitch Chroma CNN
• Can we Estimate Truck Accident Risk from Telemetric Data using Machine Learning?
• Photon detection probability prediction using one-dimensional generative neural network
• Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling
• Anomaly scores for generative models
• Combining band-frequency separation and deep neural networks for optoacoustic imaging
• HNPE: Leveraging Global Parameters for Neural Posterior Estimation
• Spatial PixelCNN: Generating Images from Patches
• FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods
• Learning Functions over Sets via Permutation Adversarial Networks
• On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attacks
• Multi-layered Discriminative Restricted Boltzmann Machine with Untrained Probabilistic Layer
• An Investigation of the Effectiveness of Phase for Audio Classification
• Few-Shot Open-Set Recognition using Meta-Learning
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
• Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment
• Seq2Mol: Automatic design of de novo molecules conditioned by the target protein sequences through deep neural networks
• Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks
• Variational Inference for Data-Efficient Model Learning in POMDPs
• RoeNets: Predicting Discontinuity of Hyperbolic Systems from Continuous Data
• Compositional Generalization with Tree Stack Memory Units
• Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning
• Wider Channel Attention Network for Remote Sensing Image Super-resolution
• Linear Transformations for Cross-lingual Sentiment Analysis
• Reduced Data-Driven Turbulence Closure for Capturing Long-Term Statistics
• Neural Distortion Fields for Spatial Calibration of Wide Field-of-View Near-Eye Displays
• Boosting Supervision with Self-Supervision for Few-shot Learning
• Deep Learning-Based Position Detection for Hydraulic Cylinders Using Scattering Parameters
• Mitigating Uncertainty in Document Classification
• TTS-by-TTS: TTS-driven Data Augmentation for Fast and High-Quality Speech Synthesis
• English-Twi Parallel Corpus for Machine Translation
• On learning latent dynamics of the AUG plasma state
• Initial condition assessment for reaction-diffusion glioma growth models: A translational MRI/histology (in)validation study
• RecipeMind: Guiding Ingredient Choices from Food Pairing to Recipe Completion using Cascaded Set Transformer
• Post-synaptic potential regularization has potential
• Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems
• DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement
• Neural Theorem Provers Do Not Learn Rules Without Exploration
• Neural Garment Dynamics via Manifold-Aware Transformers
• Multilingual End-to-End Speech Translation
• Generalizing Downsampling from Regular Data to Graphs
• Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors
• Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
• Hierarchical Multi-Label Dialog Act Recognition on Spanish Data
• A fully recurrent feature extraction for single channel speech enhancement
• Extension of Direct Feedback Alignment to Convolutional and Recurrent Neural Network for Bio-plausible Deep Learning
• Revisiting Neural Program Smoothing for Fuzzing
• Mixture Proportion Estimation and PU Learning: A Modern Approach
• Learning Koopman Representations for Hybrid Systems
• Trust Region Value Optimization using Kalman Filtering
• Adversarial Graph Disentanglement
• Data-driven learning of non-autonomous systems
• Machine learning assisted measurement of local topological invariants
• Efficient LSTM Training with Eligibility Traces
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework
• A Medical Pre-Diagnosis System for Histopathological Image of Breast Cancer
• Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networks
• Visual Cues and Error Correction for Translation Robustness
• Towards Robust Neural Networks via Close-loop Control
• Future Person Localization in First-Person Videos
• Non-autoregressive Personalized Bundle Generation
• Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
• Recursive Visual Attention in Visual Dialog
• Automatic Music Highlight Extraction using Convolutional Recurrent Attention Networks
• Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments
• LQResNet: A Deep Neural Network Architecture for Learning Dynamic Processes
• Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms
• Exploiting Adam-like Optimization Algorithms to Improve the Performance of Convolutional Neural Networks
• Inferring the Langevin Equation with Uncertainty via Bayesian Neural Networks
• An Improved Semi-Supervised VAE for Learning Disentangled Representations
• Learning to Navigate in Turbulent Flows with Aerial Robot Swarms: A Cooperative Deep Reinforcement Learning Approach
• An Attention-Based Approach for Single Image Super Resolution
• Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach
• Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications
• Learning High Dimensional Wasserstein Geodesics
• Polynomial Ridge Flowfield Estimation
• SALD: Sign Agnostic Learning with Derivatives
• Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks
• Detect-and-describe: Joint learning framework for detection and description of objects
• Machine learning methods for Schlieren imaging of a plasma channel in tenuous atomic vapor
• Adversarial shape perturbations on 3D point clouds
• Morphological Disambiguation from Stemming Data
• Streaming egocentric action anticipation: An evaluation scheme and approach
• Multi-Stage Transfer Learning with an Application to Selection Process
• Discontinuous Named Entity Recognition as Maximal Clique Discovery
• PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
• Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples
• Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
• Deep Multi-camera People Detection
• A Variational Prosody Model for Mapping the Context-Sensitive Variation of Functional Prosodic Prototypes
• Deformation estimation of an elastic object by partial observation using a neural network
• Design of a SiPM-on-Tile ZDC for the future EIC and its Performance with Graph Neural Networks
• Assigning Species Information to Corresponding Genes by a Sequence Labeling Framework
• Language Anisotropic Cross-Lingual Model Editing
• MyDigitalFootprint: an extensive context dataset for pervasive computing applications at the edge
• A Multigrid Method for Efficiently Training Video Models
• Subclass Knowledge Distillation with Known Subclass Labels
• xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
• Evaluating Semantic Rationality of a Sentence: A Sememe-Word-Matching Neural Network based on HowNet
• Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
• Automatic airway segmentation from Computed Tomography using robust and efficient 3-D convolutional neural networks
• Position-aware Location Regression Network for Temporal Video Grounding
• Hamiltonian Variational Auto-Encoder
• Negative sampling in semi-supervised learning
• MomentumRNN: Integrating Momentum into Recurrent Neural Networks
• Convergence of a Relaxed Variable Splitting Method for Learning Sparse Neural Networks via ${\ell }_1,{\ell }_0$, and transformed-${\ell }_1$ Penalties
• Session-based Sequential Skip Prediction via Recurrent Neural Networks
• Fine-grained Noise Control for Multispeaker Speech Synthesis
• Robust Neural Malware Detection Models for Emulation Sequence Learning
• A Fully Convolutional Neural Network Approach to End-to-End Speech Enhancement
• Human-like Controllable Image Captioning with Verb-specific Semantic Roles
• A Convolutional Network for Sleep Stages Classification
• Visualization of Deep Transfer Learning In SAR Imagery
• Neural Word Search in Historical Manuscript Collections
• SAIFE: Unsupervised Wireless Spectrum Anomaly Detection with Interpretable Features
• Multi-view Sentence Representation Learning
• 3D solar coronal loop reconstructions with machine learning
• Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE
• Sound Event Detection Utilizing Graph Laplacian Regularization with Event Co-occurrence
• Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning
• Neural Topic Model via Optimal Transport
• Instance-aware multi-object self-supervision for monocular depth prediction
• A Neural Rendering Framework for Free-Viewpoint Relighting
• MLtuner: System Support for Automatic Machine Learning Tuning
• Learning Credible Deep Neural Networks with Rationale Regularization
• Meta-path Analysis on Spatio-Temporal Graphs for Pedestrian Trajectory Prediction
• Prediction of the facial growth direction with Machine Learning methods
• DEEPCHORUS: A Hybrid Model of Multi-scale Convolution and Self-attention for Chorus Detection
• Attention-GAN for Object Transfiguration in Wild Images
• Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction
• Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021
• Wasserstein-Wasserstein Auto-Encoders
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• DRAMNet: Authentication based on Physical Unique Features of DRAM Using Deep Convolutional Neural Networks
• Synaptic metaplasticity with multi-level memristive devices
• At Your Service: Coffee Beans Recommendation From a Robot Assistant
• Multi-Domain Image Completion for Random Missing Input Data
• Unsupervised Tracklet Person Re-Identification
• MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection
• Improving Parametric Neural Networks for High-Energy Physics (and Beyond)
• Mixed Diagnostics for Longitudinal Properties of Electron Bunches in a Free-Electron Laser
• Versatile Learned Video Compression
• Robust Variational Autoencoder for Tabular Data with Beta Divergence
• Guiding High-Performance SAT Solvers with Unsat-Core Predictions
• Interpretable Neuron Structuring with Graph Spectral Regularization
• Deep Learning of Koopman Representation for Control
• Training Stronger Baselines for Learning to Optimize
• Unsupervised Subword Modeling Using Autoregressive Pretraining and Cross-Lingual Phone-Aware Modeling
• Outlier Detection on Mixed-Type Data: An Energy-based Approach
• Improving Neural Machine Translation with Pre-trained Representation
• Dependency Parsing as Head Selection
• Learning to Synthesize Fashion Textures
• Text Embeddings for Retrieval From a Large Knowledge Base
• Generative Machine Learning for Multivariate Equity Returns
• Variational Sequential Optimal Experimental Design using Reinforcement Learning
• Compression of Deep Convolutional Neural Networks under Joint Sparsity Constraints
• Frame invariance and scalability of neural operators for partial differential equations
• Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
• Training Progressively Binarizing Deep Networks Using FPGAs
• Malaria Likelihood Prediction By Effectively Surveying Households Using Deep Reinforcement Learning
• Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations
• Eliminating artefacts in Polarimetric Images using Deep Learning
• Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction
• Approximating exponential family models (not single distributions) with a two-network architecture
• Secure Domain Adaptation with Multiple Sources
• Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
• A Novel Monocular Disparity Estimation Network with Domain Transformation and Ambiguity Learning
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• Domain-informed neural networks for interaction localization within astroparticle experiments
• Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks
• Power Allocation in Multi-user Cellular Networks With Deep Q Learning Approach
• A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement
• Training Strategies for Autoencoder-based Detection of False Data Injection Attacks
• A comparable study of modeling units for end-to-end Mandarin speech recognition
• CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation
• Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention
• Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds
• Memory-efficient Learning for High-Dimensional MRI Reconstruction
• ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression
• Exploring EEG and Eye Movement Fusion for Multi-Class Target RSVP-BCI
• Learning the Lantern: Neural network applications to broadband photonic lantern modelling
• GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
• BigSurvSGD: Big Survival Data Analysis via Stochastic Gradient Descent
• Causal Explanation Analysis on Social Media
• ${\alpha }^{\alpha }$-Rank: Practically Scaling $\alpha$-Rank through Stochastic Optimisation
• Newton-ADMM: A Distributed GPU-Accelerated Optimizer for Multiclass Classification Problems
• Anomaly Detection on Graph Time Series
• One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
• Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates
• GPU Accelerated Sub-Sampled Newton's Method
• Deep Feature Rotation for Multimodal Image Style Transfer
• StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
• Grounding Language for Transfer in Deep Reinforcement Learning
• Magnification-independent Histopathological Image Classification with Similarity-based Multi-scale Embeddings
• Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
• Chameleon: Learning Model Initializations Across Tasks With Different Schemas
• BitNet: Bit-Regularized Deep Neural Networks
• Regularized Fine-grained Meta Face Anti-spoofing
• TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images
• Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
• Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer
• ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network
• Adaptive Task Sampling for Meta-Learning
• Federated Learning in Adversarial Settings
• Comparison of Methods Generalizing Max- and Average-Pooling
• A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes
• Independence Promoted Graph Disentangled Networks
• A Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures with Gradient Learnings
• Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
• Detecting Transaction-based Tax Evasion Activities on Social Media Platforms Using Multi-modal Deep Neural Networks
• PT-VTON: an Image-Based Virtual Try-On Network with Progressive Pose Attention Transfer
• A Machine Learning Approach to Classify Kinematics and Vortex Wake Modes of Oscillating Foils
• Convolutional Relational Machine for Group Activity Recognition
• Person Re-identification Using Visual Attention
• Graph Neural Network Architecture Search for Molecular Property Prediction
• Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning
• Fast Spatio-Temporal Residual Network for Video Super-Resolution
• Variance Regularizing Adversarial Learning
• Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
• Semi-supervised Bayesian Deep Multi-modal Emotion Recognition
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• Mini-batch Tempered MCMC
• Moser Flow: Divergence-based Generative Modeling on Manifolds
• $k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
• AirObject: A Temporally Evolving Graph Embedding for Object Identification
• Seismic wave propagation and inversion with Neural Operators
• PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
• Visual Physics: Discovering Physical Laws from Videos
• A Simple Algorithm for Scalable Monte Carlo Inference
• Multiplex Graph Networks for Multimodal Brain Network Analysis
• Inter-Patient ECG Classification with Convolutional and Recurrent Neural Networks
• Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature
• Improved Gradient-Based Optimization Over Discrete Distributions
• Improving Sequential Latent Variable Models with Autoregressive Flows
• Gabor frames and deep scattering networks in audio processing
• Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit
• A Neural Network Perturbation Theory Based on the Born Series
• Stochastic Substitute Training: A Gray-box Approach to Craft Adversarial Examples Against Gradient Obfuscation Defenses
• Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games
• Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
• Reconstruction of 3D Porous Media From 2D Slices
• Word-Level Style Control for Expressive, Non-attentive Speech Synthesis
• Neural Message Passing for Multi-Label Classification
• UNIR-Net: A Novel Approach for Restoring Underwater Images with Non-Uniform Illumination Using Synthetic Data
• Center-Extraction-Based Three Dimensional Nuclei Instance Segmentation of Fluorescence Microscopy Images
• FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models
• Imperfect Segmentation Labels: How Much Do They Matter?
• DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
• Capturing Label Distribution: A Case Study in NLI
• MaCow: Masked Convolutional Generative Flow
• RandomOut: Using a convolutional gradient norm to rescue convolutional filters
• CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding
• Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
• Layer-structured 3D Scene Inference via View Synthesis
• A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI
• Predicting Research Trends in Artificial Intelligence with Gradient Boosting Decision Trees and Time-aware Graph Neural Networks
• Natural Gradient Deep Q-learning
• LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Values
• $\beta$-Variational Autoencoder as an Entanglement Classifier
• Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data
• Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features
• Denoising Arterial Spin Labeling Cerebral Blood Flow Images Using Deep Learning
• Longformer for MS MARCO Document Re-ranking Task
• Joint Neural Network Equalizer and Decoder
• Composed Variational Natural Language Generation for Few-shot Intents
• GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning
• Self-boosted Time-series Forecasting with Multi-task and Multi-view Learning
• Optimal day-ahead orders using stochastic programming and noise-driven RNNs
• How to Evaluate the Next System: Automatic Dialogue Evaluation from the Perspective of Continual Learning
• Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos
• Scalable Deep Unsupervised Clustering with Concrete GMVAEs
• Thermal Conductivity Calculation using Homogeneous Non-equilibrium Molecular Dynamics Simulation with Allegro
• Improving Robustness and Generality of NLP Models Using Disentangled Representations
• Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRI
• A Cross-Domain Transferable Neural Coherence Model
• Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction
• Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
• Communication-Efficient Federated Learning with Compensated Overlap-FedAvg
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation
• DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos nucifera
• Knowledge-Enhanced Recommendation with User-Centric Subgraph Network
• Understanding the Effectiveness of Reviews in E-commerce Top-N Recommendation
• Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition
• Topology Optimization under Uncertainty using a Stochastic Gradient-based Approach
• Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design
• A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
• Learning from Fact-checkers: Analysis and Generation of Fact-checking Language
• Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
• Attention-based Vocabulary Selection for NMT Decoding
• Machine Perception-Driven Image Compression: A Layered Generative Approach
• Precipitation nowcasting using a stochastic variational frame predictor with learned prior distribution
• Separation Guided Speaker Diarization in Realistic Mismatched Conditions
• Knowledge Distillation for Multi-task Learning
• RAVE: A variational autoencoder for fast and high-quality neural audio synthesis
• TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
• A New Deep Learning Method for Image Deblurring in Optical Microscopic Systems
• Polynomial Matrix Completion for Missing Data Imputation and Transductive Learning
• Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
• Degrees of Freedom Analysis of Unrolled Neural Networks
• Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
• Generating Goal-Directed Visuomotor Plans Based on Learning Using a Predictive Coding-type Deep Visuomotor Recurrent Neural Network Model
• LOSSGRAD: automatic learning rate in gradient descent
• A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem with a Convolutional Neural Network
• Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
• mcLARO: Multi-Contrast Learned Acquisition and Reconstruction Optimization for simultaneous quantitative multi-parametric mapping
• Searching for dark matter subhalos in the Fermi-LAT catalog with Bayesian neural networks
• A General Framework Combining Generative Adversarial Networks and Mixture Density Networks for Inverse Modeling in Microstructural Materials Design
• Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study
• Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions
• Enhancing CMB map reconstruction and power spectrum estimation with convolutional neural networks
• Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation
• Early Prediction for Physical Human Robot Collaboration in the Operating Room
• Adversarial Transfer Attacks With Unknown Data and Class Overlap
• Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
• NPE: Neural Personalized Embedding for Collaborative Filtering
• Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
• Using stigmergy as a computational memory in the design of recurrent neural networks
• DeepPhysics: a physics aware deep learning framework for real-time simulation
• Denoising convolutional autoencoder based B-mode ultrasound tongue image feature extraction
• Efficient hyperparameter optimization by way of PAC-Bayes bound minimization
• Artist Style Transfer Via Quadratic Potential
• Adversarial Attacks on Co-Occurrence Features for GAN Detection
• Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition
• Intent term selection and refinement in e-commerce queries
• Parameterized Convex Universal Approximators for Decision-Making Problems
• Different eigenvalue distributions encode the same temporal tasks in recurrent neural networks
• No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks
• Unsupervised and interpretable scene discovery with Discrete-Attend-Infer-Repeat
• Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
• Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering
• A Matrix-in-matrix Neural Network for Image Super Resolution
• A Multiple Source Hourglass Deep Network for Multi-Focus Image Fusion
• Learning Context-Sensitive Convolutional Filters for Text Processing
• An Improved Neural Baseline for Temporal Relation Extraction
• Query-by-example Spoken Term Detection using Attention-based Multi-hop Networks
• Learning to Segment 3D Point Clouds in 2D Image Space
• FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
• Data-driven Outer-Loop Control Using Deep Reinforcement Learning for Trajectory Tracking
• Autoencoding Binary Classifiers for Supervised Anomaly Detection
• Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
• Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks
• Deep Learning for Power System Security Assessment
• StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks
• A QP-adaptive Mechanism for CNN-based Filter in Video Coding
• Generative Adversarial Forests for Better Conditioned Adversarial Learning
• TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
• Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description
• Unsupervised Eyeglasses Removal in the Wild
• Speech denoising by parametric resynthesis
• Operation-aware Neural Networks for User Response Prediction
• Activity Driven Weakly Supervised Object Detection
• Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows
• Deep IDA: A Deep Learning Method for Integrative Discriminant Analysis of Multi-View Data with Feature Ranking -- An Application to COVID-19 severity
• Genetic Neural Architecture Search for automatic assessment of human sperm images
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
• Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
• Heterogeneous Graph Attention Networks for Learning Diverse Communication
• Deep learning methods based on cross-section images for predicting effective thermal conductivity of composites
• Talking-head Generation with Rhythmic Head Motion
• Capsule networks for low-data transfer learning
• Crowd Counting on Images with Scale Variation and Isolated Clusters
• Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
• Pun Generation with Surprise
• Is Object Detection Necessary for Human-Object Interaction Recognition?
• Matrix and tensor decompositions for training binary neural networks
• Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models
• Guided Learning Convolution System for DCASE 2019 Task 4
• Low-Rank Training of Deep Neural Networks for Emerging Memory Technology
• A Multi-Layer K-means Approach for Multi-Sensor Data Pattern Recognition in Multi-Target Localization
• Multilingual Neural Machine Translation for Zero-Resource Languages
• Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance
• Distributed generation of privacy preserving data with user customization
• Data-driven deep density estimation
• Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations
• Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
• Multi-View Frame Reconstruction with Conditional GAN
• Deep neural networks for efficient phase demodulation in wavelength shifting interferometry
• Deep Residual Neural Networks for Image in Speech Steganography
• Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks
• Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
• Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
• M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
• Variational Bayesian surrogate modelling with application to robust design optimisation
• Structure Destruction and Content Combination for Face Anti-Spoofing
• Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
• CLOVER: Convnet Line-fitting Of Velocities in Emission-line Regions
• Recovering Homography from Camera Captured Documents using Convolutional Neural Networks
• Attaining entropy production and dissipation maps from Brownian movies via neural networks
• Deep Learning Guided Building Reconstruction from Satellite Imagery-derived Point Clouds
• Scalable Variational Gaussian Process Regression Networks
• Finding Algebraic Structure of Care in Time: A Deep Learning Approach
• Learning a Single Tucker Decomposition Network for Lossy Image Compression with Multiple Bits-Per-Pixel Rates
• Detecting Information Relays in Deep Neural Networks
• BUZz: BUffer Zones for defending adversarial examples in image classification
• Towards an Hybrid Hodgkin-Huxley Action Potential Generation Model
• Unpaired Image Denoising
• Event Detection with Neural Networks: A Rigorous Empirical Evaluation
• IITP at WAT 2021: System description for English-Hindi Multimodal Translation Task
• Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
• Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
• ACE-Net: Fine-Level Face Alignment through Anchors and Contours Estimation
• Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
• Optimizing Deeper Transformers on Small Datasets
• Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
• Context-aware and Scale-insensitive Temporal Repetition Counting
• NSTO: Neural Synthesizing Topology Optimization for Modulated Structure Generation
• TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes
• Topological Data Analysis in Text Classification: Extracting Features with Additive Information
• Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
• Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data
• FastVC: Fast Voice Conversion with non-parallel data
• PIN: A Novel Parallel Interactive Network for Spoken Language Understanding
• Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
• SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
• Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback
• Causal Inference of General Treatment Effects using Neural Networks with A Diverging Number of Confounders
• Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification
• A Circular-Structured Representation for Visual Emotion Distribution Learning
• Interspecies Knowledge Transfer for Facial Keypoint Detection
• SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text
• CoReS: Compatible Representations via Stationarity
• GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search
• TurboNet: A Model-driven DNN Decoder Based on Max-Log-MAP Algorithm for Turbo Code
• Simplified Stochastic Feedforward Neural Networks
• ActionVLAD: Learning spatio-temporal aggregation for action classification
• Implicit Generative Modeling for Efficient Exploration
• Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering
• Information-Theoretic Local Minima Characterization and Regularization
• Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable
• Label Universal Targeted Attack
• Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
• Low-Cost Parameterizations of Deep Convolutional Neural Networks
• DeepSinger: Singing Voice Synthesis with Data Mined From the Web
• DNA Steganalysis Using Deep Recurrent Neural Networks
• Joint Effects of Context and User History for Predicting Online Conversation Re-entries
• Correlative Channel-Aware Fusion for Multi-View Time Series Classification
• Picking Up Quantization Steps for Compressed Image Classification
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion
• PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
• Technical Report: Temporal Aggregate Representations
• Word Embeddings via Tensor Factorization
• Automatic Reparameterisation of Probabilistic Programs
• The Power of Typed Affine Decision Structures: A Case Study
• Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
• Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
• Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet
• A novel guided deep learning algorithm to design low-cost SPP films
• Predicting nucleation near the spinodal in the Ising model using machine learning
• A Resource for Computational Experiments on Mapudungun
• A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
• DiDiSpeech: A Large Scale Mandarin Speech Corpus
• Joint Visual-Textual Embedding for Multimodal Style Search
• Learning to Estimate Driver Drowsiness from Car Acceleration Sensors using Weakly Labeled Data
• Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
• Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA
• 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
• RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
• A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
• Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
• Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans
• Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
• Negative-Free Self-Supervised Gaussian Embedding of Graphs
• Testing and Learning on Distributions with Symmetric Noise Invariance
• RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
• Modeling Spatio-Temporal Human Track Structure for Action Localization
• Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels
• A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
• On Reducing Negative Jacobian Determinant of the Deformation Predicted by Deep Registration Networks
• Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems
• On Expressivity and Trainability of Quadratic Networks
• Ranger21: a synergistic deep learning optimizer
• A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
• Speech enhancement aided end-to-end multi-task learning for voice activity detection
• Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
• Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control
• Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
• Fast Universal Style Transfer for Artistic and Photorealistic Rendering
• MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection
• TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
• EEG based Continuous Speech Recognition using Transformers
• DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems
• 8-bit Optimizers via Block-wise Quantization
• Avoiding Spurious Local Minima in Deep Quadratic Networks
• XCycles Backprojection Acoustic Super-Resolution
• A powerful machine learning technique to extract proton core, beam and alpha-particle parameters from velocity distribution functions in space plasmas
• Compression of Fully-Connected Layer in Neural Network by Kronecker Product
• Layerwise Optimization by Gradient Decomposition for Continual Learning
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification
• Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation
• Predicting Target Language CCG Supertags Improves Neural Machine Translation
• A Character-Word Compositional Neural Language Model for Finnish
• Gleason Score Prediction using Deep Learning in Tissue Microarray Image
• Surfing: Iterative optimization over incrementally trained deep networks
• Cosmic Ray Rejection with Attention Augmented Deep Learning
• Data-Driven Approach for Log Instruction Quality Assessment
• Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding
• Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
• Context-aware Reranking with Utility Maximization for Recommendation
• Classification of Traffic Using Neural Networks by Rejecting: a Novel Approach in Classifying VPN Traffic
• Reinforced stochastic gradient descent for deep neural network learning
• Can deep neural networks learn process model structure? An assessment framework and analysis
• NU-Class Net: A Novel Approach for Video Quality Enhancement
• Data-Space Inversion Using a Recurrent Autoencoder for Time-Series Parameterization
• Towards automated Capability Assessment leveraging Deep Learning
• Deep counter networks for asynchronous event-based processing
• Neural Ranking Models with Weak Supervision
• Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
• Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
• r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
• Boosting Column Generation with Graph Neural Networks for Joint Rider Trip Planning and Crew Shift Scheduling
• Extending C++ for Heterogeneous Quantum-Classical Computing
• $\xi$-torch: differentiable scientific computing library
• Modeling and Predicting Blood Flow Characteristics through Double Stenosed Artery from CFD simulation using Deep Learning Models
• On Sampling Strategies for Neural Network-based Collaborative Filtering
• Point Cloud Audio Processing
• Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
• NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
• Recognizing Scenes from Novel Viewpoints
• Adaptive Focus for Efficient Video Recognition
• Approximated Doubly Robust Search Relevance Estimation
• Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)
• Cross-Modality 3D Object Detection
• Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
• 3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
• Recurrent Neural Networks for Dialogue State Tracking
• Binarized Convolutional Neural Networks with Separable Filters for Efficient Hardware Acceleration
• Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models
• Self-Supervised Representations Improve End-to-End Speech Translation
• Do Explicit Alignments Robustly Improve Multilingual Encoders?
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• An Adversarial Transfer Network for Knowledge Representation Learning
• Partition Pooling for Convolutional Graph Network Applications in Particle Physics
• Gradient Descent Optimization of Fermion Nodes in Diffusion Monte Carlo
• Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments
• ERNet: Unsupervised Collective Extraction and Registration in Neuroimaging Data
• Early Improving Recurrent Elastic Highway Network
• ACK-Less Rate Adaptation for IEEE 802.11bc Enhanced Broadcast Services Using Sim-to-Real Deep Reinforcement Learning
• Visual Question Answering with Prior Class Semantics
• Explainable Artificial Intelligence for Improved Modeling of Processes
• On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study
• DeepRA: Predicting Joint Damage From Radiographs Using CNN with Attention
• Simulation-Based Inference with Approximately Correct Parameters via Maximum Entropy
• AlignVE: Visual Entailment Recognition Based on Alignment Relations
• Partially Oblivious Neural Network Inference
• PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
• Off-Policy Adversarial Inverse Reinforcement Learning
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data
• A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control
• Towards Synthesizing Twelve-Lead Electrocardiograms from Two Asynchronous Leads
• AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient
• Annealed Flow Transport Monte Carlo
• Time-domain Speech Enhancement with Generative Adversarial Learning
• End-to-End Text Classification via Image-based Embedding using Character-level Networks
• Continuous-Time Model-Based Reinforcement Learning
• Probabilistic Generating Circuits
• Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
• Neural Pharmacodynamic State Space Modeling
• Source Printer Identification from Document Images Acquired using Smartphone
• Deep Adversarial Belief Networks
• Random mesh projectors for inverse problems
• SaccadeNet: A Fast and Accurate Object Detector
• Dimension-free convergence rates for gradient Langevin dynamics in RKHS
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• Orthogonal Over-Parameterized Training
• Neural networks in day-ahead electricity price forecasting: Single vs. multiple outputs
• Training Deep Neural Network in Limited Precision
• IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers
• Learning Implicit Sampling Distributions for Motion Planning
• Neural Adaptation Layers for Cross-domain Named Entity Recognition
• NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
• Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields
• Transcriptome-supervised classification of tissue morphology using deep learning
• memeBot: Towards Automatic Image Meme Generation
• Enhancing high-content imaging for studying microtubule networks at large-scale
• Attacking CNN-based anti-spoofing face authentication in the physical domain
• Attention Forcing for Sequence-to-sequence Model Training
• Mixture-of-tastes Models for Representing Users with Diverse Interests
• Suspicious News Detection Using Micro Blog Text
• Track finding with deep neural networks
• Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
• Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
• Knowledge Graph Embedding with Multiple Relation Projections
• NeurReg: Neural Registration and Its Application to Image Segmentation
• Self-Attention Gazetteer Embeddings for Named-Entity Recognition
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
• Hierarchical Density Order Embeddings
• Feature Extraction on Synthetic Black Hole Images
• Linking emotions to behaviors through deep transfer learning
• Bayesian Optimization Algorithms for Accelerator Physics
• A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
• Machine-learning Based Extraction of the Short-Range Part of the Interaction in Non-contact Atomic Force Microscopy
• Visible and Infrared Image Fusion Using Encoder-Decoder Network
• DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising
• Obstacle Avoidance and Navigation Utilizing Reinforcement Learning with Reward Shaping
• Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment
• What Does a TextCNN Learn?
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
• AR: Auto-Repair the Synthetic Data for Neural Machine Translation
• A Simple Convolutional Generative Network for Next Item Recommendation
• Learning Feature Descriptors using Camera Pose Supervision
• Facial Expression Recognition Using Human to Animated-Character Expression Translation
• Knowledge Guided Metric Learning for Few-Shot Text Classification
• Attentional Prototype Inference for Few-Shot Segmentation
• Solving nonograms using Neural Networks
• A Geometric Approach of Gradient Descent Algorithms in Linear Neural Networks
• A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
• APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
• Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph
• Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning
• CANDiS: Coupled & Attention-Driven Neural Distant Supervision
• Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks
• Neural Logic Reasoning
• Baryons from Mesons: A Machine Learning Perspective
• Bidirectional recurrent imputation and abundance estimation of LULC classes with MODIS multispectral time series and geo-topographic and climatic data
• A Confidence-Calibrated MOBA Game Winner Predictor
• Privacy-oriented manipulation of speaker representations
• Learning Semantic Person Image Generation by Region-Adaptive Normalization
• Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
• AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms
• Mortality rate forecasting: can recurrent neural networks beat the Lee-Carter model?
• Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
• Second Harmonic Imaging Enhanced by Deep Learning Decipher
• Adversarial Regression. Generative Adversarial Networks for Non-Linear Regression: Theory and Assessment
• JotlasNet: Joint Tensor Low-Rank and Attention-based Sparse Unrolling Network for Accelerating Dynamic MRI
• SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
• Self-Supervised Light Field Reconstruction Using Shearlet Transform and Cycle Consistency
• Deep feature transfer between localization and segmentation tasks
• Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
• Simultaneous Decision Making for Stochastic Multi-echelon Inventory Optimization with Deep Neural Networks as Decision Makers
• Dynamic Upsampling of Smoke through Dictionary-based Learning
• 1-D CNN-Based Online Signature Verification with Federated Learning
• Real-Time Non-Invasive Imaging and Detection of Spreading Depolarizations through EEG: An Ultra-Light Explainable Deep Learning Approach
• Predicting Opioid Relapse Using Social Media Data
• Amortized learning of neural causal representations
• Accelerating science with human versus alien artificial intelligences
• Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
• Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
• Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder
• Exploration of Reinforcement Learning for Event Camera using Car-like Robots
• Playing 20 Question Game with Policy-Based Reinforcement Learning
• Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis
• A Data-Driven Approach to Morphogenesis under Structural Instability
• Strange Jet Tagging
• Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation
• Adaptive Serverless Learning
• New Insight in Cervical Cancer Diagnosis Using Convolution Neural Network Architecture
• Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
• Predicting Natural Hazards with Neuronal Networks
• Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching
• Inverse Reinforcement Learning with Conditional Choice Probabilities
• Inference of Recyclable Objects with Convolutional Neural Networks
• Comparison of neural network architectures for feature extraction from binary black hole merger waveforms
• Consistency and Coherency Enhanced Story Generation
• Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
• Can Your Face Detector Do Anti-spoofing? Face Presentation Attack Detection with a Multi-Channel Face Detector
• Learning to discover and localize visual objects with open vocabulary
• Adjusting for Confounding in Unsupervised Latent Representations of Images
• RGB-D Local Implicit Function for Depth Completion of Transparent Objects
• Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning
• DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
• Joint Stream: Malignant Region Learning for Breast Cancer Diagnosis
• A Deep Learning Based Decoder for Concatenated Coding over Deletion Channels
• Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging
• Parametric 3D Convolutional Autoencoder for the Prediction of Flow Fields in a Bed Configuration of Hot Particles
• Scalable Thompson Sampling using Sparse Gaussian Process Models
• Using machine learning to study the kinematics of cold gas in galaxies
• Path-Based Contextualization of Knowledge Graphs for Textual Entailment
• Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examples
• EventNet: Asynchronous Recursive Event Processing
• Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
• Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
• Monocular Real-Time Volumetric Performance Capture
• Known Unknowns: Uncertainty Quality in Bayesian Neural Networks
• Quasi-Monte Carlo sampling for machine-learning partial differential equations
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• DeMIAN: Deep Modality Invariant Adversarial Network
• End-to-end deep metamodeling to calibrate and optimize energy loads
• The lowest-order Neural Approximated Virtual Element Method on polygonal elements
• Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks
• MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning
• Visual Grounding Strategies for Text-Only Natural Language Processing
• Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
• Multi-Grid Graph Neural Networks with Self-Attention for Computational Mechanics
• A comprehensive study on the prediction reliability of graph neural networks for virtual screening
• MMFNet: A Multi-modality MRI Fusion Network for Segmentation of Nasopharyngeal Carcinoma
• Symmetrical Gaussian Error Linear Units (SGELUs)
• Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition
• Nonlinear state-space identification using deep encoder networks
• FCN Approach for Dynamically Locating Multiple Speakers
• Deep Learning-Aided Projected Gradient Detector for Massive Overloaded MIMO Channels
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Evaluating robustness of language models for chief complaint extraction from patient-generated text
• Optimal Mini-Batch Size Selection for Fast Gradient Descent
• Replication-Robust Payoff-Allocation for Machine Learning Data Markets
• Feasibility of Modeling Orthogonal Frequency-Division Multiplexing Communication Signals with Unsupervised Generative Adversarial Networks
• Deep Dimension Reduction for Supervised Representation Learning
• Constraints on OPF Surrogates for Learning Stable Local Volt/Var Controllers
• Generative Semantic Hashing Enhanced via Boltzmann Machines
• SPG-VTON: Semantic Prediction Guidance for Multi-pose Virtual Try-on
• Generating Magnetic Resonance Spectroscopy Imaging Data of Brain Tumours from Linear, Non-Linear and Deep Learning Models
• Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning
• Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems
• A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos
• Self-Supervised Goal-Conditioned Pick and Place
• Pseudo-labeling for Scalable 3D Object Detection
• Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification
• Identifying Model Weakness with Adversarial Examiner
• AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Stochastic Adaptive Line Search for Differentially Private Optimization
• Disentanglement for Discriminative Visual Recognition
• Cultural evolution via iterated learning and communication explains efficient color naming systems
• Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm
• Virtual Adversarial Ladder Networks For Semi-supervised Learning
• MambaFoley: Foley Sound Generation using Selective State-Space Models
• Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
• A physics and learning-based transmission-less attenuation compensation method for SPECT
• Graph Neural Processes: Towards Bayesian Graph Neural Networks
• The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
• Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
• Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning
• Multi-Task Self-Supervised Pre-Training for Music Classification
• Two-stage model and optimal SI-SNR for monaural multi-speaker speech separation in noisy environment
• Taylor Expansion Policy Optimization
• Applications of Machine Learning in Document Digitisation
• Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss
• PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
• H2TF for Hyperspectral Image Denoising: Where Hierarchical Nonlinear Transform Meets Hierarchical Matrix Factorization
• Towards Better Forecasting by Fusing Near and Distant Future Visions
• Reinforcement Learning with Feedback-modulated TD-STDP
• Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars
• Unsupervised Learning of Syntactic Structure with Invertible Neural Projections
• Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network
• Strict Modes Everywhere - Bringing Order Into Dynamics of Mechanical Systems by a Potential Compatible With the Geodesic Flow
• Neural Network Predicts Ion Concentration Profiles under Nanoconfinement
• Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning
• A Unified Framework for Speech Separation
• Probabilistic Software Modeling: A Data-driven Paradigm for Software Analysis
• Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
• Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
• Neural Style Transfer with Twin-Delayed DDPG for Shared Control of Robotic Manipulators
• Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
• Does Head Label Help for Long-Tailed Multi-Label Text Classification
• Residual Networks as Geodesic Flows of Diffeomorphisms
• A Study of Continuous Vector Representationsfor Theorem Proving
• Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
• Equivariant Entity-Relationship Networks
• Neural ODEs for Image Segmentation with Level Sets
• Improving Machine Hearing on Limited Data Sets
• A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images
• Dynamic Attention Based Generative Adversarial Network with Phase Post-Processing for Speech Enhancement
• Residual U-Net for accurate and efficient prediction of hemodynamics in two-dimensional asymmetric stenosis
• Transformative Applications of Machine Learning for Chemical Reactions
• Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting
• DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis
• Nonclosedness of Sets of Neural Networks in Sobolev Spaces
• Incremental Learning for Robot Perception through HRI
• Visually Grounded Continual Learning of Compositional Phrases
• AttnMove: History Enhanced Trajectory Recovery via Attentional Network
• Weakly Supervised Label Learning Flows
• Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
• $\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
• Domain-Adversarial Graph Neural Networks for $\Lambda$ Hyperon Identification with CLAS12
• Surface Recognition for e-Scooter Using Smartphone IMU Sensor
• Text2Poster: Laying out Stylized Texts on Retrieved Images
• Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
• Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence
• Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink
• Direct May Not Be the Best: An Incremental Evolution View of Pose Generation
• Deep Predictive Model Learning with Parametric Bias: Handling Modeling Difficulties and Temporal Model Changes
• Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
• Exploiting Behavioral Consistence for Universal User Representation
• An Element-Wise Weights Aggregation Method for Federated Learning
• Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks
• An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks
• Hyperprior Induced Unsupervised Disentanglement of Latent Representations
• Inductive Bias and Language Expressivity in Emergent Communication
• Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring
• Inference in Multi-Layer Networks with Matrix-Valued Unknowns
• Teaching Machines to Code: Neural Markup Generation with Visual Attention
• Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• Safe Predictors for Enforcing Input-Output Specifications
• Unsupervised Single-Image Reflection Separation Using Perceptual Deep Image Priors
• DeepHIPS: A novel Deep Learning based Hippocampus Subfield Segmentation method
• Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
• Regression Networks for Meta-Learning Few-Shot Classification
• Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning
• AstroClearNet: Deep image prior for multi-frame astronomical image restoration
• Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform
• Neural Stereoscopic Image Style Transfer
• Deep Kernel Survival Analysis and Subject-Specific Survival Time Prediction Intervals
• Unsupervised Detection of Distinctive Regions on 3D Shapes
• Deep learning method to remove chemical, kinetic and electric artifacts on ISEs
• Deep Reinforcement Learning for Crowdsourced Urban Delivery: System States Characterization, Heuristics-guided Action Choice, and Rule-Interposing Integration
• Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
• A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps
• Recursive Estimation for Sparse Gaussian Process Regression
• Explicit Interaction Network for Aspect Sentiment Triplet Extraction
• Bootstrapping Contrastive Learning Enhanced Music Cold-Start Matching
• Towards Movement Generation with Audio Features
• Privacy Enhancing Machine Learning via Removal of Unwanted Dependencies
• Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data
• Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction
• Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction
• A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning
• Multilinear Compressive Learning with Prior Knowledge
• Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty
• Exploration of Convolutional Neural Network Architectures for Large Region Map Automation
• Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
• Streaming Adaptive Nonparametric Variational Autoencoder
• Whole-Body Human Pose Estimation in the Wild
• Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA
• Provable Representation Learning for Imitation Learning via Bi-level Optimization
• Spectral Graph Attention Network with Fast Eigen-approximation
• Dual-stream Maximum Self-attention Multi-instance Learning
• Impact of Traffic Lights on Trajectory Forecasting of Human-driven Vehicles Near Signalized Intersections
• Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
• Sinkhorn Natural Gradient for Generative Models
• Generalized Deep Image to Image Regression
• Hierarchical Optimal Transport for Robust Multi-View Learning
• Predictive Coding for Locally-Linear Control
• Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
• VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images
• Permutohedral-GCN: Graph Convolutional Networks with Global Attention
• Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization
• Chinese User Service Intention Classification Based on Hybrid Neural Network
• Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
• Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds
• Model Monitoring and Dynamic Model Selection in Travel Time-series Forecasting
• An Intelligent Approach to Detecting Novel Fault Classes for Centrifugal Pumps Based on Deep CNNs and Unsupervised Methods
• Attention-based Mixture Density Recurrent Networks for History-based Recommendation
• The use of adversaries for optimal neural network training
• Adapting Pretrained Transformer to Lattices for Spoken Language Understanding
• MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
• Deep reinforcement learning for feedback control in a collective flashing ratchet
• Texture Deformation Based Generative Adversarial Networks for Face Editing
• Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
• Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network
• MixML: A Unified Analysis of Weakly Consistent Parallel Learning
• Statistical Learning of Value-at-Risk and Expected Shortfall
• Deep Neural Network Training with Frank-Wolfe
• Segmentation of Surgical Instruments for Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks
• Adaptive Fusion for RGB-D Salient Object Detection
• Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
• Online Learning to Rank with List-level Feedback for Image Filtering
• ARiA: Utilizing Richard's Curve for Controlling the Non-monotonicity of the Activation Function in Deep Neural Nets
• Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic Data
• MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learning
• Utilizing Domain Knowledge in End-to-End Audio Processing
• A Risk-Sensitive Approach to Policy Optimization
• Robust Chinese Word Segmentation with Contextualized Word Representations
• Spatio-Temporal Variational Gaussian Processes
• RODE-Net: Learning Ordinary Differential Equations with Randomness from Data
• Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
• Curriculum By Smoothing
• Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
• Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
• Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM
• The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification
• Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codes
• Unlabelled Far-field Deeply Subwavelength Superoscillatory Imaging (DSSI)
• PushNet: Efficient and Adaptive Neural Message Passing
• DNN2LR: Interpretation-inspired Feature Crossing for Real-world Tabular Data
• ConCORDe-Net: Cell Count Regularized Convolutional Neural Network for Cell Detection in Multiplex Immunohistochemistry Images
• Basket Recommendation with Multi-Intent Translation Graph Neural Network
• Bookworm continual learning: beyond zero-shot learning and continual learning
• Sharing pattern submodels for prediction with missing values
• Egyptian Sign Language Recognition Using CNN and LSTM
• Feature Interaction-aware Graph Neural Networks
• Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative
• Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
• FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
• Optimizing Multi-Taper Features for Deep Speaker Verification
• Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
• Global Adaptive Filtering Layer for Computer Vision
• Multi-Unit Transformers for Neural Machine Translation
• FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
• Gaussian Process Neurons Learn Stochastic Activation Functions
• Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
• Self-supervised Visual Attribute Learning for Fashion Compatibility
• The Referential Reader: A Recurrent Entity Network for Anaphora Resolution
• Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
• A Batch Normalized Inference Network Keeps the KL Vanishing Away
• Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks
• Detecting Thermodynamic Phase Transition via Explainable Machine Learning of Photoemission Spectroscopy
• Data-Driven Vehicle Trajectory Forecasting
• LeanStereo: A Leaner Backbone based Stereo Network
• CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders
• Identifying magnetic antiskyrmions while they form with convolutional neural networks
• Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
• Lightweight starshade position sensing with convolutional neural networks and simulation-based inference
• 3D Robot Pose Estimation from 2D Images
• Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
• Supervised Deep Neural Networks (DNNs) for Pricing/Calibration of Vanilla/Exotic Options Under Various Different Processes
• Mesh Variational Autoencoders with Edge Contraction Pooling
• Clinically Translatable Direct Patlak Reconstruction from Dynamic PET with Motion Correction Using Convolutional Neural Network
• Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Design
• Parenting: Safe Reinforcement Learning from Human Input
• Learning Guidance Rewards with Trajectory-space Smoothing
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• Dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network
• A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected Layers
• Deep Discriminative Representation Learning with Attention Map for Scene Classification
• Initialisation of Autonomous Aircraft Visual Inspection Systems via CNN-Based Camera Pose Estimation
• Interleaved Multitask Learning for Audio Source Separation with Independent Databases
• Deep Bayesian Multi-Target Learning for Recommender Systems
• Reliable Deep Grade Prediction with Uncertainty Estimation
• Distributed Resource Scheduling for Large-Scale MEC Systems: A Multi-Agent Ensemble Deep Reinforcement Learning with Imitation Acceleration
• Towards an efficient deep learning model for musical onset detection
• Modularity Matters: Learning Invariant Relational Reasoning Tasks
• Exploring Aligned Lyrics-Informed Singing Voice Separation
• A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
• Foresight Social-aware Reinforcement Learning for Robot Navigation
• Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
• Learning to Automatically Generate Fill-In-The-Blank Quizzes
• Continuous Deep Hierarchical Reinforcement Learning for Ground-Air Swarm Shepherding
• k-Space Deep Learning for Parallel MRI: Application to Time-Resolved MR Angiography
• Faster Person Re-Identification
• Intelligence plays dice: Stochasticity is essential for machine learning
• Voice Imitating Text-to-Speech Neural Networks
• Wireless Propagation Parameter Estimation with Convolutional Neural Networks
• Discovering Useful Sentence Representations from Large Pretrained Language Models
• FMHash: Deep Hashing of In-Air-Handwriting for User Identification
• Properties Of Winning Tickets On Skin Lesion Classification
• Iterative Refinement of the Approximate Posterior for Directed Belief Networks
• Have you forgotten? A method to assess if machine learning models have forgotten data
• T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
• Backpropagation for Implicit Spectral Densities
• Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond
• CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection
• IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
• Structure-Aware Generation Network for Recipe Generation from Images
• FLFE: A Communication-Efficient and Privacy-Preserving Federated Feature Engineering Framework
• Anticipatory Human-Robot Path Planning for Search and Rescue
• Style Obfuscation by Invariance
• High-order Semantic Role Labeling
• CARL: Content-Aware Representation Learning for Heterogeneous Networks
• Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model
• Development and evaluation of a deep learning algorithm for German word recognition from lip movements
• Explicit Regularization of Stochastic Gradient Methods through Duality
• Feature Staleness Aware Incremental Learning for CTR Prediction
• On the Out-of-distribution Generalization of Probabilistic Image Modelling
• Named Entities in Medical Case Reports: Corpus and Experiments
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
• Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
• Neural Topic Modeling with Cycle-Consistent Adversarial Training
• Defiltering turbulent flow fields for Lagrangian particle tracking using machine learning techniques
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• The act of remembering: a study in partially observable reinforcement learning
• Efficient Meta Lifelong-Learning with Limited Memory
• Exploiting Unsupervised Data for Emotion Recognition in Conversations
• Wider Networks Learn Better Features
• Relationship Explainable Multi-objective Reinforcement Learning with Semantic Explainability Generation
• A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
• Unsupervised Learning of Intrinsic Structural Representation Points
• Semi-supervised classification by reaching consensus among modalities
• Simple and Effective Paraphrastic Similarity from Parallel Translations
• Incremental processing of noisy user utterances in the spoken language understanding task
• Attaining human-level performance with atlas location autocontext for anatomical landmark detection in 3D CT data
• ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
• Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics
• Portfolio Optimization with Feedback Strategies Based on Artificial Neural Networks
• IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes
• Deep Convolutional AutoEncoder-based Lossy Image Compression
• Speech-to-speech Translation between Untranscribed Unknown Languages
• BasketballGAN: Generating Basketball Play Simulation Through Sketching
• SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition
• NPC: Neural Predictive Control for Fuel-Efficient Autonomous Trucks
• KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
• Curiosity-Driven Recommendation Strategy for Adaptive Learning via Deep Reinforcement Learning
• Emotion Generation and Recognition: A StarGAN Approach
• Weakly Labeled Sound Event Detection Using Tri-training and Adversarial Learning
• Group Anomaly Detection using Deep Generative Models
• Development of Deep Learning Methods for Inflow Turbulence Generation
• End-to-End Cascaded U-Nets with a Localization Network for Kidney Tumor Segmentation
• Audio-Conditioned U-Net for Position Estimation in Full Sheet Images
• Semi-supervised Learning using Adversarial Training with Good and Bad Samples
• Online Learning of Danger Avoidance for Complex Structures of Musculoskeletal Humanoids and Its Applications
• A Unified Multi-scale and Multi-task Learning Framework for Driver Behaviors Reasoning
• BanditRank: Learning to Rank Using Contextual Bandits
• Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases
• CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting
• Vision-Infused Deep Audio Inpainting
• A Capsule Network-based Embedding Model for Search Personalization
• Attenuating Random Noise in Seismic Data by a Deep Learning Approach
• Multilevel Language and Vision Integration for Text-to-Clip Retrieval
• Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
• Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models
• On the Unintended Social Bias of Training Language Generation Models with Data from Local Media
• Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design
• SwapText: Image Based Texts Transfer in Scenes
• Controlling Text Complexity in Neural Machine Translation
• Closing the Training/Inference Gap for Deep Attractor Networks
• Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
• Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models
• Detecting Adversarial Perturbations with Saliency
• Effect of Data Degradation on Motion Re-Identification
• A New Local Transformation Module for Few-shot Segmentation
• A Stable Variational Autoencoder for Text Modelling
• SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks
• Contextual Recurrent Units for Cloze-style Reading Comprehension
• Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion
• A Fully Stochastic Second-Order Trust Region Method
• Adversarial Transformations for Semi-Supervised Learning
• Deep Neural Implicit Representation of Accessibility for Multi-Axis Manufacturing
• Heart Segmentation From MRI Scans Using Convolutional Neural Network
• Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM
• Bi-fidelity Stochastic Gradient Descent for Structural Optimization under Uncertainty
• Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network
• Exploiting Operation Importance for Differentiable Neural Architecture Search
• Adversarially Regularized Policy Learning Guided by Trajectory Optimization
• Convolutional Composer Classification
• Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision
• Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
• Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
• GEqO: ML-Accelerated Semantic Equivalence Detection
• Sampling-Free Learning of Bayesian Quantized Neural Networks
• Learning to Play General Video-Games via an Object Embedding Network
• Towards End-to-End Training of Automatic Speech Recognition for Nigerian Pidgin
• Learning to Wait: Wi-Fi Contention Control using Load-based Predictions
• Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning
• Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimation
• Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition
• Counterfactual Evaluation of Treatment Assignment Functions with Networked Observational Data
• A Robust and Precise ConvNet for small non-coding RNA classification (RPC-snRC)
• One-Shot Imitation Filming of Human Motion Videos
• Cascading Convolutional Color Constancy
• Very Long Natural Scenery Image Prediction by Outpainting
• Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
• Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention
• Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
• Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning
• AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map
• Experimental Demonstration of Millimeter-Wave Radio-over-Fiber System with Convolutional Neural Network (CNN) and Binary Convolutional Neural Network (BCNN)
• Amata: An Annealing Mechanism for Adversarial Training Acceleration
• Recovering Geometric Information with Learned Texture Perturbations
• Learning Multi-instrument Classification with Partial Labels
• Multi-Source Deep Domain Adaptation for Quality Control in Retail Food Packaging
• Learning to Structure Long-term Dependence for Sequential Recommendation
• Encoding-based Memory Modules for Recurrent Neural Networks
• IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
• Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network
• Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
• Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information
• Deepfake Image Generation for Improved Brain Tumor Segmentation
• Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
• Principled Interpolation in Normalizing Flows
• Deep Autotuner: a Pitch Correcting Network for Singing Performances
• A Framework for End-to-End Learning on Semantic Tree-Structured Data
• Preference-based training framework for automatic speech quality assessment using deep neural network
• Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning
• Speech-to-Singing Conversion in an Encoder-Decoder Framework
• Data Augmentation for Copy-Mechanism in Dialogue State Tracking
• Context-Aware 3D Object Localization from Single Calibrated Images: A Study of Basketballs
• Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
• Nonconvex sparse regularization for deep neural networks and its optimality
• Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding
• Stein Variational Inference for Discrete Distributions
• RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
• VQ-DRAW: A Sequential Discrete VAE
• Leveraging Class Similarity to Improve Deep Neural Network Robustness
• Transfer learning from language models to image caption generators: Better models may not transfer better
• Not All Words are Equal: Video-specific Information Loss for Video Captioning
• Logical Reasoning for Revealing the Critical Temperature through Deep Learning of Configuration Ensemble of Statistical Systems
• Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks
• Blind Motion Deblurring with Cycle Generative Adversarial Networks
• Decision Directed Channel Estimation Based on Deep Neural Network k-step Predictor for MIMO Communications in 5G
• A Joint Model for Multimodal Document Quality Assessment
• NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
• Component attention network for multimodal dance improvisation recognition
• Learning Image-Conditioned Dynamics Models for Control of Under-actuated Legged Millirobots
• Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service
• Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning
• Large-scale Cloze Test Dataset Created by Teachers
• Variational Recurrent Neural Networks for Graph Classification
• Online Multi-Object Tracking with Dual Matching Attention Networks
• FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
• Fully Convolutional Neural Network for Semantic Segmentation of Anatomical Structure and Pathologies in Colour Fundus Images Associated with Diabetic Retinopathy
• WSNet: Compact and Efficient Networks Through Weight Sampling
• Contextual Recurrent Neural Networks
• A Continuous Optimisation Benchmark Suite from Neural Network Regression
• Interactive Label Cleaning with Example-based Explanations
• Competitive Experience Replay
• A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification
• A Data-Driven Approach to Coarse-Graining Simple Liquids in Confinement
• ContextVP: Fully Context-Aware Video Prediction
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction
• Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks
• LHC Hadronic Jet Generation Using Convolutional Variational Autoencoders with Normalizing Flows
• Multi-Instance Learning for End-to-End Knowledge Base Question Answering
• Question Answering in Natural Language: the Special Case of Temporal Expressions
• Paradox in Deep Neural Networks: Similar yet Different while Different yet Similar
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
• Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
• UVA: A Universal Variational Framework for Continuous Age Analysis
• Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding
• SNU_IDS at SemEval-2019 Task 3: Addressing Training-Test Class Distribution Mismatch in Conversational Classification
• Reinforcement Mechanism Design for e-commerce
• ntuer at SemEval-2019 Task 3: Emotion Classification with Word and Sentence Representations in RCNN
• Learning Depth With Very Sparse Supervision
• Regularising disparity estimation via multi task learning with structured light reconstruction
• Weight Priors for Learning Identity Relations
• Order embeddings and character-level convolutions for multimodal alignment
• Smart Laptop Bag with Machine Learning for Activity Recognition
• Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation
• Deep Fusion Network for Image Completion
• Generated Loss, Augmented Training, and Multiscale VAE
• Analytical Moment Regularizer for Gaussian Robust Networks
• Evolving Neural Networks in Reinforcement Learning by means of UMDAc
• Learning Semantic Vector Representations of Source Code via a Siamese Neural Network
• Automatic segmentation of spinal multiple sclerosis lesions: How to generalize across MRI contrasts?
• Geological modeling using a recursive convolutional neural networks approach
• Translate-to-Recognize Networks for RGB-D Scene Recognition
• Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data
• Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
• Operation-level Progressive Differentiable Architecture Search
• Perceptual Quality Study on Deep Learning based Image Compression
• Event reconstruction using pattern spectra and convolutional neural networks for the Cherenkov Telescope Array
• Nonlinear Semi-Parametric Models for Survival Analysis
• Estimating Socioeconomic Status via Temporal-Spatial Mobility Analysis -- A Case Study of Smart Card Data
• Generative Adversarial Classification Network with Application to Network Traffic Classification
• Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition
• LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
• Barycentric-alignment and reconstruction loss minimization for domain generalization
• A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation
• Neural Machine Translation via Binary Code Prediction
• Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
• Two-dimensional Multi-fiber Spectrum Image Correction Based on Machine Learning Techniques
• Enhancing Salient Object Segmentation Through Attention
• Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
• Image-to-Image Translation with Multi-Path Consistency Regularization
• Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings
• Deep learning-based classification of high intensity patterns in photorefractive crystals
• Deep Cross Networks with Aesthetic Preference for Cross-domain Recommendation
• Continual Learning of New Sound Classes using Generative Replay
• 3D Magic Mirror: Automatic Video to 3D Caricature Translation
• Context Attentive Document Ranking and Query Suggestion
• Adaptively Preconditioned Stochastic Gradient Langevin Dynamics
• Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
• Automated Cardiac Resting Phase Detection Targeted on the Right Coronary Artery
• Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming
• EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
• Decomposable Neural Paraphrase Generation
• Deep Learning of Compressed Sensing Operators with Structural Similarity Loss
• Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
• Novel Suboptimal approaches for Hyperparameter Tuning of Deep Neural Network [under the shelf of Optical Communication]
• Sequence-level Speaker Change Detection with Difference-based Continuous Integrate-and-fire
• MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources
• Joint Learning of Named Entity Recognition and Entity Linking
• Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video
• Deformable Registration Using Average Geometric Transformations for Brain MR Images
• Arc-swift: A Novel Transition System for Dependency Parsing
• Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization
• Stochastic Sequential Neural Networks with Structured Inference
• Fast Adaptive Weight Noise
• An Optimization and Generalization Analysis for Max-Pooling Networks
• Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning
• Rethinking Skip-thought: A Neighborhood based Approach
• On the Difficulty of Unbiased Alpha Divergence Minimization
• Chord Label Personalization through Deep Learning of Integrated Harmonic Interval-based Representations
• SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
• Score-informed syllable segmentation for a cappella singing voice with convolutional neural networks
• DM${}^2$S${}^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
• Thread Reconstruction in Conversational Data using Neural Coherence Models
• Self-organized Hierarchical Softmax
• Crowdsourced-based Deep Convolutional Networks for Urban Flood Depth Mapping
• Near-Data Processing for Differentiable Machine Learning Models
• Variational autoencoders for tissue heterogeneity exploration from (almost) no preprocessed mass spectrometry imaging data
• Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model
• Evolution of a Web-Scale Near Duplicate Image Detection System
• Why flatness does and does not correlate with generalization for deep neural networks
• Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering
• Understanding the effects of artifacts on automated polyp detection and incorporating that knowledge via learning without forgetting
• Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks
• Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features
• Digital Peter: Dataset, Competition and Handwriting Recognition Methods
• Multimodal End-to-End Sparse Model for Emotion Recognition
• Fisher Task Distance and Its Application in Neural Architecture Search
• Probably Approximately Correct Vision-Based Planning using Motion Primitives
• Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks
• Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support
• Demand Forecasting for Platelet Usage: from Univariate Time Series to Multivariate Models
• Learning Fine-grained Fact-Article Correspondence in Legal Cases
• Defending Against Image Corruptions Through Adversarial Augmentations
• AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems
• Modeling Human Mental States with an Entity-based Narrative Graph
• ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration
• On Catastrophic Interference in Atari 2600 Games
• Persistent Message Passing
• Stronger Baseline for Person Re-Identification
• A Deep Learning Framework for Lifelong Machine Learning
• Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
• Deep Learning-based Physical-Layer Secret Key Generation for FDD Systems
• Concept Drift Monitoring and Diagnostics of Supervised Learning Models via Score Vectors
• Compressing LSTM Networks by Matrix Product Operators
• DP-REC: Private & Communication-Efficient Federated Learning
• Merging Subject Matter Expertise and Deep Convolutional Neural Network for State-Based Online Machine-Part Interaction Classification
• Deep Low-rank plus Sparse Network for Dynamic MR Imaging
• Summary-Oriented Question Generation for Informational Queries
• RDAnet: A Deep Learning Based Approach for Synthetic Aperture Radar Image Formation
• LocoProp: Enhancing BackProp via Local Loss Optimization
• Intelligent Subset Selection of Power Generators for Economic Dispatch
• Randomized Value Functions via Posterior State-Abstraction Sampling
• Stacked Auto Encoder Based Deep Reinforcement Learning for Online Resource Scheduling in Large-Scale MEC Networks
• Deep learning reveals hidden interactions in complex systems
• Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
• Reinforcement Learning with Random Delays
• MIASSR: An Approach for Medical Image Arbitrary Scale Super-Resolution
• Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
• Out-of-Vocabulary Entities in Link Prediction
• CDRNet: Accurate Cup-to-Disc Ratio Measurement with Tight Bounding Box Supervision in Fundus Photography Using Deep Learning
• ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding
• Probabilistic Hierarchical Forecasting with Deep Poisson Mixtures
• High-Capacity Expert Binary Networks
• Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
• On the Interplay Between Fine-tuning and Composition in Transformers
• Understanding Information Spreading Mechanisms During COVID-19 Pandemic by Analyzing the Impact of Tweet Text and User Features for Retweet Prediction
• Automatic Analysis System of Calcaneus Radiograph: Rotation-Invariant Landmark Detection for Calcaneal Angle Measurement, Fracture Identification and Fracture Region Segmentation
• Evaluating Modules in Graph Contrastive Learning
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• Learning Malware Representation based on Execution Sequences
• Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
• Effective Evaluation of Deep Active Learning on Image Classification Tasks
• IrEne: Interpretable Energy Prediction for Transformers
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Tracking Without Re-recognition in Humans and Machines
• Empirical observations on the effects of data transformation in machine learning classification of geological domains
• Predicting Regional Locust Swarm Distribution with Recurrent Neural Networks
• Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes
• Detecting Pulsars with Neural Networks: A Proof of Concept
• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
• A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data
• Finding and Fixing Spurious Patterns with Explanations
• SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
• A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
• Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements
• A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations
• Three-body renormalization group limit cycles based on unsupervised feature learning
• Flow Guided Transformable Bottleneck Networks for Motion Retargeting
• Learning Incident Prediction Models Over Large Geographical Areas for Emergency Response Systems
• Revisiting Deep Architectures for Head Motion Prediction in 360° Videos
• Learning Revenue-Maximizing Auctions With Differentiable Matching
• Distributed Soft Actor-Critic with Multivariate Reward Representation and Knowledge Distillation
• GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction
• CSI Clustering with Variational Autoencoding
• Knowledge Distillation via Instance-level Sequence Learning
• Continuous-Depth Neural Models for Dynamic Graph Prediction
• Goal-Directed Planning by Reinforcement Learning and Active Inference
• Exploring Stronger Feature for Temporal Action Localization
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Towards Error Measures which Influence a Learners Inductive Bias to the Ground Truth
• Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
• Monocular Road Planar Parallax Estimation
• Fine-grained Geolocation Prediction of Tweets with Human Machine Collaboration
• Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
• Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach
• Semi-Supervised Variational Autoencoder for Survival Prediction
• TENT: Tensorized Encoder Transformer for Temperature Forecasting
• Improving the convergence of SGD through adaptive batch sizes
• A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks
• An Asymptotic Analysis of Minibatch-Based Momentum Methods for Linear Regression Models
• DivergentNets: Medical Image Segmentation by Network Ensemble
• Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
• Detecting Outliers with Poisson Image Interpolation
• Impact of deep learning-based image super-resolution on binary signal detection
• MD-split+: Practical Local Conformal Inference in High Dimensions
• Urban Tree Species Classification Using Aerial Imagery
• Probabilistic partition of unity networks: clustering based deep approximation
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• Model selection for deep audio source separation via clustering analysis
• Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
• Neural Machine Translation with 4-Bit Precision and Beyond
• Multi-sense Definition Modeling using Word Sense Decompositions
• Dual Adversarial Co-Learning for Multi-Domain Text Classification
• Memory-Augmented Neural Networks for Machine Translation
• Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay
• Shapley Interpretation and Activation in Neural Networks
• Reinforced Imitation Learning by Free Energy Principle
• Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos
• Learning-based Prediction, Rendering and Transmission for Interactive Virtual Reality in RIS-Assisted Terahertz Networks
• Core Semantic First: A Top-down Approach for AMR Parsing
• Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network
• NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
• Neural Attentive Bag-of-Entities Model for Text Classification
• Inferring Multiple Relationships between ASes using Graph Convolutional Network
• Squeeze-Excitation Convolutional Recurrent Neural Networks for Audio-Visual Scene Classification
• Malware Classification Using Transfer Learning
• Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation
• Momentum Accelerates the Convergence of Stochastic AUPRC Maximization
• Power System Event Identification based on Deep Neural Network with Information Loading
• On Self-Distilling Graph Neural Network
• Improving Neural Question Generation using World Knowledge
• Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• Efficient Deep Feature Calibration for Cross-Modal Joint Embedding Learning
• Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
• Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better
• Incremental Learning for Personalized Recommender Systems
• Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
• Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models
• Lattice PUF: A Strong Physical Unclonable Function Provably Secure against Machine Learning Attacks
• Piecewise Linear Units Improve Deep Neural Networks
• A General Framework for Defending Against Backdoor Attacks via Influence Graph
• Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning
• Investigating the Relationship Between Dropout Regularization and Model Complexity in Neural Networks
• Dense 3D Regression for Hand Pose Estimation
• Hierarchies of Planning and Reinforcement Learning for Robot Navigation
• Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
• Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal
• Continuous Semantic Topic Embedding Model Using Variational Autoencoder
• Efficient Bidirectional Neural Machine Translation
• LFT Representation of a Class of Nonlinear Systems: A Data-Driven Approach
• No Size Fits All: Automated Radio Configuration for LPWANs
• Practical Risk Measures in Reinforcement Learning
• PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
• An Exploratory Analysis of the Latent Structure of Process Data via Action Sequence Autoencoder
• Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
• Distributional Negative Sampling for Knowledge Base Completion
• Learning Predictive and Interpretable Timeseries Summaries from ICU Data
• Temporal Collaborative Ranking Via Personalized Transformer
• Reduced-Lead ECG Classifier Model Trained with DivideMix and Model Ensemble
• How Does Adversarial Fine-Tuning Benefit BERT?
• Combining Deep Learning with Physics Based Features in Explosion-Earthquake Discrimination
• Point Proposal Network: Accelerating Point Source Detection Through Deep Learning
• The self-learning AI controller for adaptive power beaming with fiber-array laser transmitter system
• Spot the Difference: A Novel Task for Embodied Agents in Changing Environments
• Deformable Medical Image Registration Using a Randomly-Initialized CNN as Regularization Prior
• CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentation
• Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
• A Deep Neural Information Fusion Architecture for Textual Network Embeddings
• The impact of memory on learning sequence-to-sequence tasks
• Generating Image Sequence from Description with LSTM Conditional GAN
• Simplify the Usage of Lexicon in Chinese NER
• Neural network for multi-exponential sound energy decay analysis
• Boosting Image Outpainting with Semantic Layout Prediction
• Plexus Convolutional Neural Network (PlexusNet): A novel neural network architecture for histologic image analysis
• Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
• Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
• Data-informed Deep Optimization
• Parameter Prediction for Unseen Deep Architectures
• Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities
• NeRV: Neural Representations for Videos
• Faster Optimization-Based Meta-Learning Adaptation Phase
• A machine learning photon detection algorithm for coherent X-ray ultrafast fluctuation analysis
• Deep Networks with Fast Retraining
• Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements
• A Multi-Task Self-Normalizing 3D-CNN to Infer Tuberculosis Radiological Manifestations
• LapSeg3D: Weakly Supervised Semantic Segmentation of Point Clouds Representing Laparoscopic Scenes
• Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
• Investigating Self-Attention Network for Chinese Word Segmentation
• Learning Eye-in-Hand Camera Calibration from a Single Image
• Variational Optimization Based Reinforcement Learning for Infinite Dimensional Stochastic Systems
• Neural variance reduction for stochastic differential equations
• LSTM for Model-Based Anomaly Detection in Cyber-Physical Systems
• Robust Raw Waveform Speech Recognition Using Relevance Weighted Representations
• ROAM: Recurrently Optimizing Tracking Model
• A comparison of Monte Carlo dropout and bootstrap aggregation on the performance and uncertainty estimation in radiation therapy dose prediction with deep learning neural networks
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
• Synthetic Epileptic Brain Activities Using Generative Adversarial Networks
• Disentangled Relational Representations for Explaining and Learning from Demonstration
• Problems using deep generative models for probabilistic audio source separation
• Hallucinating Beyond Observation: Learning to Complete with Partial Observation and Unpaired Prior Knowledge
• Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
• Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
• Learning Generalizable Physiological Representations from Large-scale Wearable Data
• Fast, Better Training Trick -- Random Gradient
• A step towards neural genome assembly
• Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
• Predicting Discharge Medications at Admission Time Based on Deep Learning
• Product Function Need Recognition via Semi-supervised Attention Network
• Factorized Gaussian Process Variational Autoencoders
• Variance Reduction for Evolution Strategies via Structured Control Variates
• Annotation and Detection of Emotion in Text-based Dialogue Systems with CNN
• MS-PS: A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataset
• SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
• Monitoring of water volume in a porous reservoir using seismic data: A 3D simulation study
• Rethinking the Separation Layers in Speech Separation Networks
• Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes
• Delay Constrained Buffer-Aided Relay Selection in the Internet of Things with Decision-Assisted Reinforcement Learning
• Ultra-Lightweight Speech Separation via Group Communication
• Deep Smartphone Sensors-WiFi Fusion for Indoor Positioning and Tracking
• Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
• RLTM: An Efficient Neural IR Framework for Long Documents
• Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
• Transformer-based Online Speech Recognition with Decoder-end Adaptive Computation Steps
• LASR: Learning Articulated Shape Reconstruction from a Monocular Video
• Transformers as Strong Lens Detectors- From Simulation to Surveys
• Teaching the Machine to Explain Itself using Domain Knowledge
• A Machine with Short-Term, Episodic, and Semantic Memory Systems
• Audio-visual Speech Separation with Adversarially Disentangled Visual Representation
• Specialized Decision Surface and Disentangled Feature for Weakly-Supervised Polyphonic Sound Event Detection
• Removing background and estimating a unit height of atomic steps from a scanning probe microscopy image using a statistical model
• Provable robustness against all adversarial $l_p$-perturbations for $p\ge 1$
• Blending MPC & Value Function Approximation for Efficient Reinforcement Learning
• Fully-Automated Liver Tumor Localization and Characterization from Multi-Phase MR Volumes Using Key-Slice ROI Parsing: A Physician-Inspired Approach
• Combined mechanistic and machine learning method for construction of oil reservoir permeability map consistent with well test measurements
• Piecewise-Velocity Model for Learning Continuous-time Dynamic Node Representations
• Deep Cost-sensitive Learning for Wheat Frost Detection
• Deformable Gabor Feature Networks for Biomedical Image Classification
• LAMP: Label Augmented Multimodal Pretraining
• GRADE: Graph Dynamic Embedding
• Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
• Nonlinear Regression with a Convolutional Encoder-Decoder for Remote Monitoring of Surface Electrocardiograms
• ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting
• MSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish
• Towards localisation of keywords in speech using weak supervision
• Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation
• Adaptive Procedural Task Generation for Hard-Exploration Problems
• Optical Braille Recognition Using Object Detection CNN
• Learning Vehicle Routing Problems using Policy Optimisation
• Robustness, Privacy, and Generalization of Adversarial Training
• Active learning of data-assimilation closures using Graph Neural Networks
• Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh
• Automating Program Structure Classification
• A High Accuracy Electrical Stopping Power Prediction Model based on Deep Learning Algorithm and its Applications
• HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones
• Improved parallel WaveGAN vocoder with perceptually weighted spectrogram loss
• Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning
• Learning Stable and Robust Linear Parameter-Varying State-Space Models
• Efficient Learning of Generative Models via Finite-Difference Score Matching
• Deep Multimodal Learning: Merging Sensory Data for Massive MIMO Channel Prediction
• Neural Composition: Learning to Generate from Multiple Models
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• The Variational Predictive Natural Gradient
• Incrementally Stochastic and Accelerated Gradient Information mixed Optimization for Manipulator Motion Planning
• ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning
• Counterfactual Generation with Knockoffs
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Graph Attention Collaborative Similarity Embedding for Recommender System
• Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
• MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking
• What's in a Name? -- Gender Classification of Names with Character Based Machine Learning Models
• Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations
• Tracking e-cigarette warning label compliance on Instagram with deep learning
• Hyperbolic Generative Adversarial Network
• Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow
• OER: Offline Experience Replay for Continual Offline Reinforcement Learning
• Evaluating Contextualized Language Models for Hungarian
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
• Untrained Neural Network based Bayesian Detector for OTFS Modulation Systems
• Deep Equal Risk Pricing of Financial Derivatives with Multiple Hedging Instruments
• Machine learning a time-local fluctuation theorem for nonequilibrium steady states
• A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations
• Multimodal and Contrastive Learning for Click Fraud Detection
• Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection
• Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks
• Intrinsic alignment from multiple shear estimates: A first application to data and forecasts for Stage IV
• Swing contract pricing: with and without Neural Networks
• Uncertainty-guided Model Generalization to Unseen Domains
• Attention Boosted Sequential Inference Model
• Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis
• Conditional Video Generation Using Action-Appearance Captions
• Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
• The RGNLP Machine Translation Systems for WAT 2018
• Prediction-assistant Frame Super-Resolution for Video Streaming
• Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
• Learned Mappings for Targeted Free Energy Perturbation between Peptide Conformations
• Deep Unfolding of a Proximal Interior Point Method for Image Restoration
• On Learning High Dimensional Structured Single Index Models
• Machine Learning-based Automatic Graphene Detection with Color Correction for Optical Microscope Images
• AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
• VAE-KRnet and its applications to variational Bayes
• CNN-based Discriminative Training for Domain Compensation in Acoustic Event Detection with Frame-wise Classifier
• Halo Properties from Observable Measures of Environment: I. Halo and Subhalo Masses
• Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination
• Machine Learning of coarse-grained Molecular Dynamics Force Fields
• ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
• PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
• On Computation and Generalization of GANs with Spectrum Control
• Event-based Synthetic Aperture Imaging with a Hybrid Network
• Vacaspati: A Diverse Corpus of Bangla Literature
• UFANS: U-shaped Fully-Parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster
• Deep Learned Frame Prediction for Video Compression
• What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning
• Sentence Encoding with Tree-constrained Relation Networks
• Picket: Guarding Against Corrupted Data in Tabular Data during Learning and Inference
• Multi-modal Geolocation Estimation Using Deep Neural Networks
• Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
• Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation
• Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
• High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
• KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
• Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks
• Bias Reduction via End-to-End Shift Learning: Application to Citizen Science
• Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Modality Transfer
• Improved English to Russian Translation by Neural Suffix Prediction
• High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
• Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems
• On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies
• Neural sequence labeling for Vietnamese POS Tagging and NER
• DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
• YASENN: Explaining Neural Networks via Partitioning Activation Sequences
• Word2rate: training and evaluating multiple word embeddings as statistical transitions
• Deep Transformer Networks for Time Series Classification: The NPP Safety Case
• Searching to Sparsify Tensor Decomposition for N-ary Relational Data
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
• ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
• 3D-LaneNet: End-to-End 3D Multiple Lane Detection
• Context-Aware Group Captioning via Self-Attention and Contrastive Features
• Learning Unsplit-field-based PML for the FDTD Method by Deep Differentiable Forest
• A single image deep learning approach to restoration of corrupted remote sensing products
• DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
• Effective Subword Segmentation for Text Comprehension
• 360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception
• Improving Bi-directional Generation between Different Modalities with Variational Autoencoders
• Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models
• CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
• Bringing Old Photos Back to Life
• Deep Segment Attentive Embedding for Duration Robust Speaker Verification
• Decomposed Adversarial Learned Inference
• Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks
• Learning Robust Algorithms for Online Allocation Problems Using Adversarial Training
• ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models
• Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurring
• Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
• Bayesian Learning of Probabilistic Dipole Inversion for Quantitative Susceptibility Mapping
• Semi-Supervised Crowd Counting from Unlabeled Data
• End-to-end NILM System Using High Frequency Data and Neural Networks
• An Auto-Encoder Strategy for Adaptive Image Segmentation
• "The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition
• Learning to Ask Screening Questions for Job Postings
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
• Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
• Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation
• MDD-UNet: Domain Adaptation for Medical Image Segmentation with Theoretical Guarantees, a Proof of Concept
• Learned Block-based Hybrid Image Compression
• Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
• Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning
• Scoring Root Necrosis in Cassava Using Semantic Segmentation
• Effective Data Fusion with Generalized Vegetation Index: Evidence from Land Cover Segmentation in Agriculture
• MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
• Distributed Stochastic Nonconvex Optimization and Learning based on Successive Convex Approximation
• Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
• Improving Sentence Representations with Consensus Maximisation
• Extreme Low-Light Imaging with Multi-granulation Cooperative Networks
• User Constrained Thumbnail Generation using Adaptive Convolutions
• AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition
• Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction
• Uncertainty Quantification of Graph Convolution Neural Network Models of Evolving Processes
• Facial Action Unit Detection using 3D Facial Landmarks
• A Thousand Words are Worth More Than One Recording: NLP Based Speaker Change Point Detection
• Ain't Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language
• Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources
• Learning to Remember, Forget and Ignore using Attention Control in Memory
• Learning-based model augmentation with LFRs
• Improving Self-supervised Pre-training via a Fully-Explored Masked Language Model
• MeshODE: A Robust and Scalable Framework for Mesh Deformation
• InfantNet: A Deep Neural Network for Analyzing Infant Vocalizations
• LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks
• DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn
• BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining
• Upper Bounds on the Generalization Error of Private Algorithms for Discrete Data
• Angular Triplet Loss-based Camera Network for ReID
• Non-blind Image Restoration Based on Convolutional Neural Network
• Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
• Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems
• Cross-Domain Imitation Learning with a Dual Structure
• BaSeNet: A Learning-based Mobile Manipulator Base Pose Sequence Planning for Pickup Tasks
• Distribution Aligned Multimodal and Multi-Domain Image Stylization
• MaLa-ASR: Multimedia-Assisted LLM-Based ASR
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
• Single Image Deraining with Continuous Rain Density Estimation
• Improving generalization of vocal tract feature reconstruction: from augmented acoustic inversion to articulatory feature reconstruction without articulatory data
• Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data
• Learning Invariances for Policy Generalization
• Feature Interaction based Neural Network for Click-Through Rate Prediction
• Multi-Fidelity High-Order Gaussian Processes for Physical Simulation
• Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
• A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts
• A Resolution Independent Neural Operator
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• A Practical Sparse Approximation for Real Time Recurrent Learning
• Branch-Cooperative OSNet for Person Re-Identification
• A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems
• Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment
• Predefined Sparseness in Recurrent Sequence Models
• Deep-ER: Deep Learning ECCENTRIC Reconstruction for fast high-resolution neurometabolic imaging
• Integrated Eojeol Embedding for Erroneous Sentence Classification in Korean Chatbots
• Exploring The Spatial Reasoning Ability of Neural Models in Human IQ Tests
• Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency
• Deep Learning-based Detection of Bacterial Swarm Motion Using a Single Image
• A Multi-channel Network with Image Retrieval for Accurate Brain Tissue Segmentation
• Temporal Information Extraction by Predicting Relative Time-lines
• Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
• Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
• Principal Component Networks: Parameter Reduction Early in Training
• Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks
• Chroma Intra Prediction with attention-based CNN architectures
• Title-Guided Encoding for Keyphrase Generation
• Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification
• Combine Convolution with Recurrent Networks for Text Classification
• Lightweight Gaze Estimation Model Via Fusion Global Information
• Graph Neural Networks Including Sparse Interpretability
• FANAL -- Financial Activity News Alerting Language Modeling Framework
• ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction
• DeepSSM: an emulator of gravitational wave spectra from sound waves during cosmological first-order phase transitions
• Deep Needlet: A CNN based full sky component separation method in Needlet space
• Character-Level Feature Extraction with Densely Connected Networks
• Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy
• MyDigiTwin: A Privacy-Preserving Framework for Personalized Cardiovascular Risk Prediction and Scenario Exploration
• Self-Attentive Neural Collaborative Filtering
• Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
• Zap: Making Predictions Based on Online User Behavior
• Plateau Phenomenon in Gradient Descent Training of ReLU networks: Explanation, Quantification and Avoidance
• Modeling Financial Time Series using LSTM with Trainable Initial Hidden States
• Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI
• DeepDiff: Deep-learning for predicting Differential gene expression from histone modifications
• Barqi Breed Sheep Weight Estimation based on Neural Network with Regression
• MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• Transfer with Model Features in Reinforcement Learning
• Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study
• Wavelet-Based Dual-Branch Network for Image Demoireing
• Learning Personalized Representation for Inverse Problems in Medical Imaging Using Deep Neural Network
• CovidCare: Transferring Knowledge from Existing EMR to Emerging Epidemic for Interpretable Prognosis
• Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
• Deep Global Model Reduction Learning in Porous Media Flow Simulation
• Neural Chaos: A Spectral Stochastic Neural Operator
• CoNES: Convex Natural Evolutionary Strategies
• Adaptive Traffic Control with Deep Reinforcement Learning: Towards State-of-the-art and Beyond
• Learning Hierarchical Review Graph Representations for Recommendation
• FetDTIAlign: A Deep Learning Framework for Affine and Deformable Registration of Fetal Brain dMRI
• SBAT: Video Captioning with Sparse Boundary-Aware Transformer
• Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention
• Interpretable machine learning models: a physics-based view
• Neural Random Projections for Language Modelling
• Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
• A Spatiotemporal Radar-Based Precipitation Model for Water Level Prediction and Flood Forecasting
• Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
• Intra-class variation reduction of speaker representation in disentanglement framework
• Neural ODEs with stochastic vector field mixtures
• Positive-unlabeled Learning for Cell Detection in Histopathology Images with Incomplete Annotations
• Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors
• ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptions
• Controllable Open-ended Question Generation with A New Question Type Ontology
• Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
• Improving Next-Application Prediction with Deep Personalized-Attention Neural Network
• Active 3D Shape Reconstruction from Vision and Touch
• Deep Multi-view Models for Glitch Classification
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• Deep Discriminative Feature Learning for Accent Recognition
• Fooling Computer Vision into Inferring the Wrong Body Mass Index
• FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces
• Path Imputation Strategies for Signature Models of Irregular Time Series
• Efficient Semantic Segmentation using Gradual Grouping
• NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometry
• Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance
• First-Order Preconditioning via Hypergradient Descent
• Deep Learning for the Classification of Quenched Jets
• Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
• Deep learning of parameterized equations with applications to uncertainty quantification
• BCNet: A Deep Convolutional Neural Network for Breast Cancer Grading
• CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
• Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
• Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media
• Drone Path-Following in GPS-Denied Environments using Convolutional Networks
• Light Lies: Optical Adversarial Attack
• A statistically constrained internal method for single image super-resolution
• SA-GD: Improved Gradient Descent Learning Strategy with Simulated Annealing
• Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
• Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
• Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
• Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing
• GraphITE: Estimating Individual Effects of Graph-structured Treatments
• Computer-free, all-optical reconstruction of holograms using diffractive networks
• Looking for change? Roll the Dice and demand Attention
• Numerical approximation of singular Forward-Backward SDEs
• ENCODE: Breaking the Trade-Off Between Performance and Efficiency in Long-Term User Behavior Modeling
• Follow Your Path: a Progressive Method for Knowledge Distillation
• The Seven-League Scheme: Deep learning for large time step Monte Carlo simulations of stochastic differential equations
• Argumentative Relation Classification as Plausibility Ranking
• Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency
• GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
• Rapid Parameter Estimation for Merging Massive Black Hole Binaries Using Continuous Normalizing Flows
• Learning a Hierarchical Latent-Variable Model of 3D Shapes
• Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning
• Supervised Whole DAG Causal Discovery
• Radar Aided mmWave Vehicle-to-InfrastructureLink Configuration Using Deep Learning
• Condition-Transforming Variational AutoEncoder for Conversation Response Generation
• Who Blames Whom in a Crisis? Detecting Blame Ties from News Articles Using Neural Networks
• Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning
• A CNN-RNN Architecture for Multi-Label Weather Recognition
• H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution
• Scalable Gaussian Process Classification with Additive Noise for Various Likelihoods
• DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution
• Discriminative Online Learning for Fast Video Object Segmentation
• White-Box Adversarial Defense via Self-Supervised Data Estimation
• Physics-enhanced Neural Networks in the Small Data Regime
• Rumour Detection via News Propagation Dynamics and User Representation Learning
• Adversarial Stacked Auto-Encoders for Fair Representation Learning
• Channel-Recurrent Autoencoding for Image Modeling
• Model Interpretability and Rationale Extraction by Input Mask Optimization
• Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning
• Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
• Deep Esophageal Clinical Target Volume Delineation using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk
• An Auxiliary Classifier Generative Adversarial Framework for Relation Extraction
• Sliced Wasserstein Generative Models
• Think Visually: Question Answering through Virtual Imagery
• I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition
• Learning Continually from Low-shot Data Stream
• Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition
• Iterative Document Representation Learning Towards Summarization with Polishing
• Attention-Based End-to-End Speech Recognition on Voice Search
• Automatic Detection of Phonological Errors in Child Speech Using Siamese Recurrent Autoencoder
• Automated Search for Configurations of Deep Neural Network Architectures
• Deep Spectral Convolution Network for HyperSpectral Unmixing
• Neural Rays for Occlusion-aware Image-based Rendering
• SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering
• Eco-PiNN: A Physics-informed Neural Network for Eco-toll Estimation
• Error Analysis of the Variational Quantum Eigensolver Algorithm
• A Fast and Robust Method for Global Topological Functional Optimization
• Guiding Extractive Summarization with Question-Answering Rewards
• Towards Explanation of DNN-based Prediction with Guided Feature Inversion
• HENIN: Learning Heterogeneous Neural Interaction Networks for Explainable Cyberbullying Detection on Social Media
• Ontology-based Interpretable Machine Learning for Textual Data
• Benchmarking Tropical Cyclone Rapid Intensification with Satellite Images and Attention-based Deep Models
• Implicit Feedback Deep Collaborative Filtering Product Recommendation System
• A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication
• UIBert: Learning Generic Multimodal Representations for UI Understanding
• Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• Open Compound Domain Adaptation
• Population-based Gradient Descent Weight Learning for Graph Coloring Problems
• Towards Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fields
• Toward the Understanding of Deep Text Matching Models for Information Retrieval
• Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning
• Detection of E-scooter Riders in Naturalistic Scenes
• Post-Train Adaptive U-Net for Image Segmentation
• DESYR: Definition and Syntactic Representation Based Claim Detection on the Web
• End-to-End Balancing for Causal Continuous Treatment-Effect Estimation
• A neural network for beam background decomposition in Belle II at SuperKEKB
• Multi-source weak supervision for saliency detection
• Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking
• Adversarial Learning of Task-Oriented Neural Dialog Models
• Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation
• Mimicking the In-Camera Color Pipeline for Camera-Aware Object Compositing
• Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms
• Using Monolingual Data in Neural Machine Translation: a Systematic Study
• Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
• Improving the generalization of network based relative pose regression: dimension reduction as a regularizer
• The Minimax Complexity of Distributed Optimization
• One-to-one Mapping for Unpaired Image-to-image Translation
• Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
• Multi-task Reinforcement Learning in Reproducing Kernel Hilbert Spaces via Cross-learning
• MULE: Multimodal Universal Language Embedding
• Predicting Multiple Demographic Attributes with Task Specific Embedding Transformation and Attention Network
• Few-Shot Learning-Based Human Activity Recognition
• Audio-Visual Transformer Based Crowd Counting
• Back to the Future -- Sequential Alignment of Text Representations
• Neural Machine Translation with Characters and Hierarchical Encoding
• Answering questions by learning to rank -- Learning to rank by answering questions
• Autoencoders as Tools for Program Synthesis
• Meta-Embeddings Based On Self-Attention
• Neural Networked Assisted Tree Search for the Personnel Rostering Problem
• Document Hashing with Mixture-Prior Generative Models
• Learning DFT
• Telling Left from Right: Learning Spatial Correspondence of Sight and Sound
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• Automated Fashion Size Normalization
• RefineCap: Concept-Aware Refinement for Image Captioning
• ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation
• Machine-Learning the Classification of Spacetimes
• An Unsupervised Deep-Learning Method for Fingerprint Classification: the CCAE Network and the Hybrid Clustering Strategy
• Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
• Differential-Critic GAN: Generating What You Want by a Cue of Preferences
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation
• Leveraging Activation Maximization and Generative Adversarial Training to Recognize and Explain Patterns in Natural Areas in Satellite Imagery
• XFlow: Cross-modal Deep Neural Networks for Audiovisual Classification
• Sparse Factorization of Large Square Matrices
• Securing Tag-based recommender systems against profile injection attacks: A comparative study
• Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge
• Manifold-preserved GANs
• Neural Ranking Models with Multiple Document Fields
• Evolutionary Cell Aided Design for Neural Network Architectures
• Reducing Artificial Neural Network Complexity: A Case Study on Exoplanet Detection
• HATNet: An End-to-End Holistic Attention Network for Diagnosis of Breast Biopsy Images
• Dense Light Field Reconstruction From Sparse Sampling Using Residual Network
• Incorporating Broad Phonetic Information for Speech Enhancement
• Long Document Ranking with Query-Directed Sparse Transformer
• Bi-Skip: A Motion Deblurring Network Using Self-paced Learning
• Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
• Learning to Play Two-Player Perfect-Information Games without Knowledge
• Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains
• CMR motion artifact correction using generative adversarial nets
• Sequence-to-Sequence ASR Optimization via Reinforcement Learning
• Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning
• Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
• Timing techniques with picosecond-order accuracy for novel gaseous detectors
• Making Curiosity Explicit in Vision-based RL
• Deep-learning inversion: a next generation seismic velocity-model building method
• Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation
• Geometry-Entangled Visual Semantic Transformer for Image Captioning
• Toward Fast and Accurate Neural Discourse Segmentation
• Automatic Labeled LiDAR Data Generation based on Precise Human Model
• Self-adaptive Single and Multi-illuminant Estimation Framework based on Deep Learning
• DeepTag: inferring all-cause diagnoses from clinical notes in under-resourced medical domain
• Hybrid Low-order and Higher-order Graph Convolutional Networks
• Stability Preserving Data-driven Models With Latent Dynamics
• Dialogue Act Classification in Group Chats with DAG-LSTMs
• Semantic Matching Against a Corpus: New Applications and Methods
• Tribuo: Machine Learning with Provenance in Java
• Paraphrase Generation as Unsupervised Machine Translation
• Hunting for vampires and other unlikely forms of parity violation at the Large Hadron Collider
• Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models
• An Ensemble Dialogue System for Facts-Based Sentence Generation
• Rotation Equivariant CNNs for Digital Pathology
• ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification
• Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
• Little Motion, Big Results: Using Motion Magnification to Reveal Subtle Tremors in Infants
• Hierarchical Photo-Scene Encoder for Album Storytelling
• Natural and Effective Obfuscation by Head Inpainting
• CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
• Generalization Error Analysis of Neural networks with Gradient Based Regularization
• A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
• RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
• simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
• Multi-task problems are not multi-objective
• Deep Markov Spatio-Temporal Factorization
• Quantifying the Task-Specific Information in Text-Based Classifications
• Network reconstruction may not mean dynamics prediction
• Symmetry constrained neural networks for detection and localization of damage in metal plates
• Automatic artifact removal of resting-state fMRI with Deep Neural Networks
• Exploring Contextualized Neural Language Models for Temporal Dependency Parsing
• A study of the effect of the illumination model on the generation of synthetic training datasets
• CLOUD: Contrastive Learning of Unsupervised Dynamics
• Wide and Narrow: Video Prediction from Context and Motion
• COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching
• Promoting Diversity for End-to-End Conversation Response Generation
• Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization
• Adaptive Differentially Private Empirical Risk Minimization
• Federated Survival Analysis with Discrete-Time Cox Models
• Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans
• From Image to Imuge: Immunized Image Generation
• STAR NRE: Solving supernova selection effects with set-based truncated auto-regressive neural ratio estimation
• Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network
• Cortico-cerebellar networks as decoupling neural interfaces
• Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
• HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation
• Task-Adaptive Feature Transformer for Few-Shot Segmentation
• NASirt: AutoML based learning with instance-level complexity information
• Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learning
• A transfer learning metamodel using artificial neural networks applied to natural convection flows in enclosures
• Joint Blind Room Acoustic Characterization From Speech And Music Signals Using Convolutional Recurrent Neural Networks
• Variable-Order Approach to Nonlocal Elasticity: Theoretical Formulation and Order Identification via Deep Learning Techniques
• Smooth Imitation Learning via Smooth Costs and Smooth Policies
• Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
• Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment
• Deep Learning for Joint MIMO Detection and Channel Decoding
• Batch Normalization in the final layer of generative networks
• On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamics
• A neural network based post-filter for speech-driven head motion synthesis
• Optimizing Deep Neural Networks with Multiple Search Neuroevolution
• Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation
• Domain Camera Adaptation and Collaborative Multiple Feature Clustering for Unsupervised Person Re-ID
• Data-driven Hedging of Stock Index Options via Deep Learning
• Gravilon: Applications of a New Gradient Descent Method to Machine Learning
• Identifying High-Quality Chinese News Comments Based on Multi-Target Text Matching Model
• Gradient Normalization & Depth Based Decay For Deep Learning
• Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 3.1$\times$ Faster Inference
• Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
• Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications
• Using fuzzy bits and neural networks to partially invert few rounds of some cryptographic hash functions
• A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability
• Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
• PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons
• Histogram Layers for Synthetic Aperture Sonar Imagery
• Leveraging Sound Source Trajectories for Universal Sound Separation
• Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023
• Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatments
• Structure-Invariant Testing for Machine Translation
• Personalized Multimodal Feedback Generation in Education
• Joint Sampling and Optimisation for Inverse Rendering
• Dense U-net for super-resolution with shuffle pooling layer
• Video Question Generation via Cross-Modal Self-Attention Networks Learning
• Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
• FP-NAS: Fast Probabilistic Neural Architecture Search
• Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks
• Learning Symmetry Consistent Deep CNNs for Face Completion
• Very Power Efficient Neural Time-of-Flight
• Effective Feature Learning with Unsupervised Learning for Improving the Predictive Models in Massive Open Online Courses
• Using dynamic loss weighting to boost improvements in forecast stability
• A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
• Applying Tensor Decomposition to image for Robustness against Adversarial Attack
• Uncertainty Aware Deep Neural Network for Multistatic Localization with Application to Ultrasonic Structural Health Monitoring
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation
• Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
• Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions
• Regression via Implicit Models and Optimal Transport Cost Minimization
• Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
• Generative Inverse Deep Reinforcement Learning for Online Recommendation
• Collaborative Training of GANs in Continuous and Discrete Spaces for Text Generation
• Momentum Accelerates Evolutionary Dynamics
• A Bregman Learning Framework for Sparse Neural Networks
• $(1+\epsilon )$-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets
• Towards Generative Ray Path Sampling for Faster Point-to-Point Ray Tracing
• HalalNet: A Deep Neural Network that Classifies the Halalness Slaughtered Chicken from their Images
• Making Asynchronous Stochastic Gradient Descent Work for Transformers
• GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studies
• Learning to Make Chemical Predictions: the Interplay of Feature Representation, Data, and Machine Learning Algorithms
• Grounded and Controllable Image Completion by Incorporating Lexical Semantics
• A spectrum of complexity uncovers Dunbar's number and other leaps in social structure
• Concatenated Attention Neural Network for Image Restoration
• Measuring Performance of Generative Adversarial Networks on Devanagari Script
• A Free-Energy Principle for Representation Learning
• Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction
• Neural Architectures for Named Entity Recognition
• Zero-Shot Clinical Acronym Expansion via Latent Meaning Cells
• Universal Embeddings for Spatio-Temporal Tagging of Self-Driving Logs
• Detecting Adversarial Patches with Class Conditional Reconstruction Networks
• TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog
• Unsupervised Explanation Generation for Machine Reading Comprehension
• CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation
• A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection
• Dependent Gated Reading for Cloze-Style Question Answering
• Deep Sequence Learning with Auxiliary Information for Traffic Prediction
• FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
• ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks
• SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback
• An analytical diabolo model for robotic learning and control
• Active localization of multiple targets using noisy relative measurements
• Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation
• Improving Fair Predictions Using Variational Inference In Causal Models
• A New Unified Deep Learning Approach with Decomposition-Reconstruction-Ensemble Framework for Time Series Forecasting
• Optimal Transport using GANs for Lineage Tracing
• Network Cooperation with Progressive Disambiguation for Partial Label Learning
• SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
• DmifNet:3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion
• Stochastic Runge-Kutta methods and adaptive SGD-G2 stochastic gradient descent
• Balance Regularized Neural Network Models for Causal Effect Estimation
• Information Condensing Active Learning
• Automatic Recognition of the Supraspinatus Tendinopathy from Ultrasound Images using Convolutional Neural Networks
• Learning Pregrasp Manipulation of Objects from Ungraspable Poses
• Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
• Tackling Imbalanced Data in Cybersecurity with Transfer Learning: A Case with ROP Payload Detection
• Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
• Facial Emotion Recognition with Noisy Multi-task Annotations
• STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification
• Neural Text Classification by Jointly Learning to Cluster and Align
• Automated Coronary Arteries Labeling Via Geometric Deep Learning
• FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge
• The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
• Modeling Edge Features with Deep Bayesian Graph Networks
• An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
• A Zero-Shot based Fingerprint Presentation Attack Detection System
• Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning
• NewsDialogues: Towards Proactive News Grounded Conversation
• LCA-Net: Light Convolutional Autoencoder for Image Dehazing
• Intra-clip Aggregation for Video Person Re-identification
• NPLIC: A Machine Learning Approach to Piecewise Linear Interface Construction
• PoseGAN: A Pose-to-Image Translation Framework for Camera Localization
• Normalization Before Shaking Toward Learning Symmetrically Distributed Representation Without Margin in Speech Emotion Recognition
• Efficient Object Embedding for Spliced Image Retrieval
• FasTer: Fast Tensor Completion with Nonconvex Regularization
• Face-Cap: Image Captioning using Facial Expression Analysis
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Learned Lossless Image Compression with a HyperPrior and Discretized Gaussian Mixture Likelihoods
• Convolutional Hypercomplex Embeddings for Link Prediction
• LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery
• 3D Shape Segmentation with Geometric Deep Learning
• AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
• REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
• Beyond Exponentially Discounted Sum: Automatic Learning of Return Function
• A Qualitative Evaluation of Language Models on Automatic Question-Answering for COVID-19
• Discriminator Soft Actor Critic without Extrinsic Rewards
• Represent, Aggregate, and Constrain: A Novel Architecture for Machine Reading from Noisy Sources
• Video Segmentation Learning Using Cascade Residual Convolutional Neural Network
• Aggregative Self-Supervised Feature Learning from a Limited Sample
• Deep-CR MTLR: a Multi-Modal Approach for Cancer Survival Prediction with Competing Risks
• Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments
• DeepIso: A Deep Learning Model for Peptide Feature Detection
• Grasp State Assessment of Deformable Objects Using Visual-Tactile Fusion Perception
• Towards Interlingua Neural Machine Translation
• Relational Learning for Skill Preconditions
• MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution
• Guided Exploration with Proximal Policy Optimization using a Single Demonstration
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• On the Role of Receptive Field in Unsupervised Sim-to-Real Image Translation
• Neural Generative Models for Global Optimization with Gradients
• Rotation-Invariant Autoencoders for Signals on Spheres
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation
• RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
• Scalable Metric Learning via Weighted Approximate Rank Component Analysis
• Density Matching for Bilingual Word Embedding
• A New Registration Approach for Dynamic Analysis of Calcium Signals in Organs
• Benchmarking Deep Learning Methods for Irradiance Estimation from Sky Images with Applications to Video Prediction-Based Irradiance Nowcasting
• A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
• Recurrent Point Review Models
• Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks
• Dual Averaging is Surprisingly Effective for Deep Learning Optimization
• Automated ultrasound doppler angle estimation using deep learning
• PAC-Bayesian Soft Actor-Critic Learning
• Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss
• Ensemble Learning for Vietnamese Scene Text Spotting in Urban Environments
• Deep Optimized Priors for 3D Shape Modeling and Reconstruction
• A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer
• Scenario-aware and Mutual-based approach for Multi-scenario Recommendation in E-Commerce
• Learning to Sample with Local and Global Contexts in Experience Replay Buffer
• Time-Continuous Energy-Conservation Neural Network for Structural Dynamics Analysis
• Recognition of Acoustic Events Using Masked Conditional Neural Networks
• Deep Kernelized Autoencoders
• Convolutional Dictionary Pair Learning Network for Image Representation Learning
• Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning
• MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
• Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry
• Ordinary Differential Equation-based CNN for Channel Extrapolation over RIS-assisted Communication
• Reconstructing the Noise Manifold for Image Denoising
• CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning
• Enhanced Neural Machine Translation by Learning from Draft
• Design of Capacity-Approaching Low-Density Parity-Check Codes using Recurrent Neural Networks
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics
• Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
• Incremental Embedding Learning via Zero-Shot Translation
• Tensor-Train Networks for Learning Predictive Modeling of Multidimensional Data
• Variational Inference for Deep Probabilistic Canonical Correlation Analysis
• DeepConfig: Automating Data Center Network Topologies Management with Machine Learning
• CT respiratory motion synthesis using joint supervised and adversarial learning
• Self-supervised Visual-LiDAR Odometry with Flip Consistency
• Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
• Good practices for Bayesian Optimization of high dimensional structured spaces
• Faster Convergence for Transformer Fine-tuning with Line Search Methods
• On Spectrogram Analysis in a Multiple Classifier Fusion Framework for Power Grid Classification Using Electric Network Frequency
• Semantic Is Enough: Only Semantic Information For NeRF Reconstruction
• StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
• On the Calibration and Uncertainty of Neural Learning to Rank Models
• Time-Reversal Symmetric ODE Network
• Learning Neural Activations
• Enhanced Information Fusion Network for Crowd Counting
• Nonlocal Thresholds for Improving the Spatial Resolution of Pixel Detectors
• Assisted Perception: Optimizing Observations to Communicate State
• Training Learned Optimizers with Randomly Initialized Learned Optimizers
• Neural Networks for Lorenz Map Prediction: A Trip Through Time
• Blockchain-Enabled Variational Information Bottleneck for IoT Networks
• Application of Graph Networks to a wide-field Water-Cherenkov-based Gamma-Ray Observatory
• Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images
• Ensemble Methods for Multi-Organ Segmentation in CT Series
• Efficient Parameter Sampling for Neural Network Construction
• Expansional Retrofitting for Word Vector Enrichment
• The Effectiveness of Multitask Learning for Phenotyping with Electronic Health Records Data
• Learning based signal detection for MIMO systems with unknown noise statistics
• Spatial--spectral FFPNet: Attention-Based Pyramid Network for Segmentation and Classification of Remote Sensing Images
• Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
• Joint Visual and Wireless Signal Feature based Approach for High-Precision Indoor Localization
• Slot Self-Attentive Dialogue State Tracking
• Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning
• Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?
• HpRNet : Incorporating Residual Noise Modeling for Violin in a Variational Parametric Synthesizer
• CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization
• A new approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms
• Pseudo-Encoded Stochastic Variational Inference
• Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation
• Curriculum Learning Strategies for IR: An Empirical Study on Conversation Response Ranking
• One-Shot Segmentation in Clutter
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• Deep High-Resolution Network for Low Dose X-ray CT Denoising
• Attention augmented differentiable forest for tabular data
• Combining Bayesian and Deep Learning Methods for the Delineation of the Fan in Ultrasound Images
• Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks
• Uncertainty Quantification From Scaling Laws in Deep Neural Networks
• Improving CFD simulations by local machine-learned correction
• Deep Contrastive Multiview Network Embedding
• Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
• Machine learning delta-T noise for temperature bias estimation
• Riemannian stochastic recursive momentum method for non-convex optimization
• DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals
• Safety and Robustness in Decision Making: Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer
• Modeling Item Response Theory with Stochastic Variational Inference
• Frame Difference-Based Temporal Loss for Video Stylization
• Collaborative Sampling in Generative Adversarial Networks
• Understanding Chat Messages for Sticker Recommendation in Messaging Apps
• Understanding and Controlling Memory in Recurrent Neural Networks
• Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features
• Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
• Hacking Neural Networks: A Short Introduction
• Mobility-based prediction of SARS-CoV-2 spreading
• Deep Object Co-segmentation via Spatial-Semantic Network Modulation
• Error bounds for PDE-regularized learning
• Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability
• A Differential Geometry Perspective on Orthogonal Recurrent Models
• On the Intrinsic Dimensionality of Image Representations
• Dynamic curriculum learning via data parameters for noise robust keyword spotting
• Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
• Optimization of a Triangular Delaunay Mesh Generator using Reinforcement Learning
• Reproducible Evaluation of Neural Network Based Channel Estimators And Predictors Using A Generic Dataset
• Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization
• Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
• Supported-BinaryNet: Bitcell Array-based Weight Supports for Dynamic Accuracy-Latency Trade-offs in SRAM-based Binarized Neural Network
• Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
• Semi-supervised Quality Evaluation of Colonoscopy Procedures
• Relevance-Promoting Language Model for Short-Text Conversation
• Anaphora Resolution in Dialogue Systems for South Asian Languages
• Multi-task Learning by Leveraging the Semantic Information
• DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
• Linearized Multi-Sampling for Differentiable Image Transformation
• An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy
• Learned Proximal Networks for Quantitative Susceptibility Mapping
• Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning
• Separate and Attend in Personal Email Search
• Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions
• Target Consistency for Domain Adaptation: when Robustness meets Transferability
• Learning from Imperfect Demonstrations from Agents with Varying Dynamics
• Deep-seismic-prior-based reconstruction of seismic data using convolutional neural networks
• Deep Learning based Dimple Segmentation for Quantitative Fractography
• Regularization of the ensemble Kalman filter using a non-parametric, non-stationary spatial model
• Table-Of-Contents generation on contemporary documents
• Automatic Grouping of Redundant Sensors and Actuators Using Functional and Spatial Connections: Application to Muscle Grouping for Musculoskeletal Humanoids
• Multi${}^3$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
• Learning a Distributed Control Scheme for Demand Flexibility in Thermostatically Controlled Loads
• All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
• Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
• Decompressing Knowledge Graph Representations for Link Prediction
• Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification
• Fairness-aware Personalized Ranking Recommendation via Adversarial Learning
• Multi-Zone Unit for Recurrent Neural Networks
• Deep Consensus Learning
• Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time
• EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation
• Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
• Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
• Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
• Future Frame Prediction for Robot-assisted Surgery
• Long-range Prediction of Vital Signs Using Generative Boosting via LSTM Networks
• Diverse feature visualizations reveal invariances in early layers of deep neural networks
• Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
• Human De-occlusion: Invisible Perception and Recovery for Humans
• Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image
• Characterizing dynamically varying acoustic scenes from egocentric audio recordings in workplace setting
• Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload
• Analyzing Bias in Sensitive Personal Information Used to Train Financial Models
• Neural Networks for Predicting Human Interactions in Repeated Games
• Probing Contextualized Sentence Representations with Visual Awareness
• Some manifold learning considerations towards explicit model predictive control
• Video Captioning with Text-based Dynamic Attention and Step-by-Step Learning
• GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
• Adversarial Learning of Semantic Relevance in Text to Image Synthesis
• EmotionGIF-Yankee: A Sentiment Classifier with Robust Model Based Ensemble Methods
• q-Neurons: Neuron Activations based on Stochastic Jackson's Derivative Operators
• UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation
• SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
• MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
• Signal-background separation and energy reconstruction of gamma rays using pattern spectra and convolutional neural networks for the Small-Sized Telescopes of the Cherenkov Telescope Array
• Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
• Learning to Caption Images through a Lifetime by Asking Questions
• Scaling up machine learning-based chemical plant simulation: A method for fine-tuning a model to induce stable fixed points
• On Hyperparameter Search in Cluster Ensembles
• The sound of my voice: speaker representation loss for target voice separation
• Adversarial Robustness Guarantees for Random Deep Neural Networks
• Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
• ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References
• Learning to generate classifiers
• Machine-Learning for Nonintrusive Model Order Reduction of the Parametric Inviscid Transonic Flow past an airfoil
• Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations
• Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
• Approximated Orthonormal Normalisation in Training Neural Networks
• TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
• Completing Spatial Transcriptomics Data for Gene Expression Prediction Benchmarking
• Dynamic Video Segmentation Network
• Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction
• DRST: Deep Residual Shearlet Transform for Densely Sampled Light Field Reconstruction
• Dense xUnit Networks
• Developing a Bubble Chamber Particle Discriminator Using Semi-Supervised Learning
• To Whom are You Talking? A Deep Learning Model to Endow Social Robots with Addressee Estimation Skills
• Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech
• A machine learning approach to predict near-optimal meshes for turbulent compressible flow simulations
• Textual Data for Time Series Forecasting
• ADINE: An Adaptive Momentum Method for Stochastic Gradient Descent
• Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition
• Person image generation with semantic attention network for person re-identification
• Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
• Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?
• Temperature-transferable tight-binding model using a hybrid-orbital basis
• Attention Based Natural Language Grounding by Navigating Virtual Environment
• Revisiting the Application of Feature Selection Methods to Speech Imagery BCI Datasets
• Quantized Adam with Error Feedback
• Inherent Weight Normalization in Stochastic Neural Networks
• Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
• Color Sails: Discrete-Continuous Palettes for Deep Color Exploration
• Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
• Identification of the nonlinear steering dynamics of an autonomous vehicle
• Policy Optimization with Model-based Explorations
• Content-Aware Personalised Rate Adaptation for Adaptive Streaming via Deep Video Analysis
• ReShader: View-Dependent Highlights for Single Image View-Synthesis
• Go with the Flow: Adaptive Control for Neural ODEs
• Deep Learning Parametrization for B-Spline Curve Approximation
• SalGaze: Personalizing Gaze Estimation Using Visual Saliency
• SAM-GCNN: A Gated Convolutional Neural Network with Segment-Level Attention Mechanism for Home Activity Monitoring
• Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
• Contextual HyperNetworks for Novel Feature Adaptation
• Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
• Targeted Adversarial Training for Natural Language Understanding
• Learning Segmentation Masks with the Independence Prior
• Convergence Analysis of Decentralized ASGD
• Scaling of hardware-compatible perturbative training algorithms
• Quantum Circuit Optimization through Iteratively Pre-Conditioned Gradient Descent
• Development of a Whole-body Work Imitation Learning System by a Biped and Bi-armed Humanoid
• Long Short-Term Memory with Dynamic Skip Connections
• MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation
• Model-Agnostic Meta-Learning using Runge-Kutta Methods
• T-Rep: Representation Learning for Time Series using Time-Embeddings
• Learning a Probabilistic Strategy for Computational Imaging Sensor Selection
• Promising Accurate Prefix Boosting for sequence-to-sequence ASR
• Knowledge-aware Method for Confusing Charge Prediction
• Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective
• Geometry encoding for numerical simulations
• A Survey on Large-scale Machine Learning
• Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
• Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English
• New Advances in Body Composition Assessment with ShapedNet: A Single Image Deep Regression Approach
• Semi-Supervised Confidence Network aided Gated Attention based Recurrent Neural Network for Clickbait Detection
• Probably Approximately Correct Constrained Learning
• Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions
• Adversarial Numerical Analysis for Inverse Problems
• Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction
• Real-time Data Driven Precision Estimator for RAVEN-II Surgical Robot End Effector Position
• Deep neural network based speech separation optimizing an objective estimator of intelligibility for low latency applications
• Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
• Ensembles of GANs for synthetic training data generation
• Deep Learning Super-Diffusion in Multiplex Networks
• Visual-information-driven model for crowd simulation using temporal convolutional network
• Contextualized Keyword Representations for Multi-modal Retinal Image Captioning
• Event Argument Extraction using Causal Knowledge Structures
• Neural Memory Plasticity for Anomaly Detection
• An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients
• Meta-Learning for Few-Shot NMT Adaptation
• Geometrically Principled Connections in Graph Neural Networks
• Semantic Image Manipulation Using Scene Graphs
• ExcitNet vocoder: A neural excitation model for parametric speech synthesis systems
• Query-controllable Video Summarization
• TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model
• Online unsupervised deep unfolding for MIMO channel estimation
• ParasNet: Fast Parasites Detection with Neural Networks
• Learning of Discrete Graphical Models with Neural Networks
• A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems
• Singer Identification Using Convolutional Acoustic Motif Embeddings
• Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances
• Blind Adversarial Training: Balance Accuracy and Robustness
• Deep Domain Decomposition Method: Elliptic Problems
• Real time Traffic Flow Parameters Prediction with Basic Safety Messages at Low Penetration of Connected Vehicles
• G-DARTS-A: Groups of Channel Parallel Sampling with Attention
• Defective samples simulation through Neural Style Transfer for automatic surface defect segment
• Algorithmic Probability-guided Supervised Machine Learning on Non-differentiable Spaces
• Intention Oriented Image Captions with Guiding Objects
• DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
• Learning View Priors for Single-view 3D Reconstruction
• Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification
• Scan2Mesh: From Unstructured Range Scans to 3D Meshes
• Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine
• Quantum Approximation for Wireless Scheduling
• ICTSurF: Implicit Continuous-Time Survival Functions with Neural Networks
• Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution
• Implementation of the Emulator-based Component Analysis
• Streaming Probabilistic Deep Tensor Factorization
• Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders
• CRAM: Clued Recurrent Attention Model
• Representation Learning of Entities and Documents from Knowledge Base Descriptions
• Heterogeneous Causal Learning for Effectiveness Optimization in User Marketing
• RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
• Differentiable Greedy Networks
• Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention
• Few-Shot Object Recognition from Machine-Labeled Web Images
• Deep Lifetime Clustering
• MIM: Mutual Information Machine
• A Practical Framework for Relation Extraction with Noisy Labels Based on Doubly Transitional Loss
• Multi-Stage Reinforcement Learning For Object Detection
• Fine-grained Video Categorization with Redundancy Reduction Attention
• HAR-Net:Fusing Deep Representation and Hand-crafted Features for Human Activity Recognition
• Energy-Inspired Models: Learning with Sampler-Induced Distributions
• Entity Candidate Network for Whole-Aware Named Entity Recognition
• Textually Guided Ranking Network for Attentional Image Retweet Modeling
• HairNet: Single-View Hair Reconstruction using Convolutional Neural Networks
• Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
• CAggNet: Crossing Aggregation Network for Medical Image Segmentation
• Using deep neural networks to improve the precision of fast-sampled particle timing detectors
• A Missing Information Loss function for implicit feedback datasets
• JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans
• Retrieval-based Goal-Oriented Dialogue Generation
• Transformers in Unsupervised Structure-from-Motion
• SODA: Detecting Covid-19 in Chest X-rays with Semi-supervised Open Set Domain Adaptation
• A Nesterov's Accelerated quasi-Newton method for Global Routing using Deep Reinforcement Learning
• Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training
• Learning to Optimize Non-Rigid Tracking
• Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networks
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
• Iterative Domain-Repaired Back-Translation
• Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control
• Progress in deep Markov State Modeling: Coarse graining and experimental data restraints
• Automated Discovery of Jet Substructure Analyses
• Goal-oriented Trajectories for Efficient Exploration
• Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
• A Distillation-based Future-aware Graph Neural Network for Stock Trend Prediction
• Exploiting Contextual Information via Dynamic Memory Network for Event Detection
• Learning Discriminators as Energy Networks in Adversarial Learning
• Alternative Learning Paradigms for Image Quality Transfer
• Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
• PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
• Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
• Uniform Priors for Data-Efficient Transfer
• Rotational Unit of Memory
• MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
• Point-of-Interest Type Inference from Social Media Text
• Celeganser: Automated Analysis of Nematode Morphology and Age
• Keen2Act: Activity Recommendation in Online Social Collaborative Platforms
• Invertible Image Rescaling
• Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
• Large Scale Font Independent Urdu Text Recognition System
• Boosting radiotherapy dose calculation accuracy with deep learning
• Interactive Mars Image Content-Based Search with Interpretable Machine Learning
• Automatic Inference of Cross-modal Connection Topologies for X-CNNs
• A Differential Game Theoretic Neural Optimizer for Training Residual Networks
• Graph Neural Networks with Composite Kernels
• Sequential Reinforced 360-Degree Video Adaptive Streaming with Cross-user Attentive Network
• Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision
• Deep Curiosity Loops in Social Environments
• Data Driven Aircraft Trajectory Prediction with Deep Imitation Learning
• Detecting Forged Facial Videos using convolutional neural network
• Doubly Semi-Implicit Variational Inference
• Differentiable Particle Filtering using Optimal Placement Resampling
• Dimensional emotion recognition using visual and textual cues
• Semi-Supervised Learning for In-Game Expert-Level Music-to-Dance Translation
• DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
• One-Shot Domain Incremental Learning
• Reply with Sticker: New Dataset and Model for Sticker Retrieval
• Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition
• Accent Estimation of Japanese Words from Their Surfaces and Romanizations for Building Large Vocabulary Accent Dictionaries
• Deep HMResNet Model for Human Activity-Aware Robotic Systems
• AutoML Segmentation for 3D Medical Image Data: Contribution to the MSD Challenge 2018
• Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
• Learn distributed GAN with Temporary Discriminators
• Latent Space-Based Likelihood Estimation Using a Single Observation for Bayesian Updating of a Nonlinear Hysteretic Model
• Data Augmentation Imbalance For Imbalanced Attribute Classification
• A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception
• PMVOS: Pixel-Level Matching-Based Video Object Segmentation
• Learning Filter Banks Using Deep Learning For Acoustic Signals
• Towards Music Captioning: Generating Music Playlist Descriptions
• Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions
• Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!
• Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings
• Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
• Quantitative Parametric Mapping of Tissues Properties from Standard Magnetic Resonance Imaging Enabled by Deep Learning
• FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
• BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation
• Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement
• Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
• Acceleration via Fractal Learning Rate Schedules
• Equivariant Imaging: Learning Beyond the Range Space
• Implicit Regularization in Tensor Factorization
• Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks
• CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays
• Multimodal Representation Learning via Maximization of Local Mutual Information
• Generation For Adaption: A GAN-Based Approach for 3D Domain Adaption with Point Cloud Data
• Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks
• iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging
• Constrained Exploration and Recovery from Experience Shaping
• Recursive Training for Zero-Shot Semantic Segmentation
• ASR-Free Pronunciation Assessment
• UniKW-AT: Unified Keyword Spotting and Audio Tagging
• Signed Distance Function Computation from an Implicit Surface
• Supervised deep learning of elastic SRV distances on the shape space of curves
• A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
• Adversarially Learned Mixture Model
• Adversarial Monte Carlo Meta-Learning of Optimal Prediction Procedures
• Soft Expectation and Deep Maximization for Image Feature Detection
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• Structured Dropout Variational Inference for Bayesian Neural Networks
• Lessons learned in multilingual grounded language learning
• Segmentation of EM showers for neutrino experiments with deep graph neural networks
• Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks
• X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications
• Efficient Designs of SLOPE Penalty Sequences in Finite Dimension
• One "Ruler" for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning
• Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
• From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
• Learning Temporal Dynamics from Cycles in Narrated Video
• Reasoning about Fine-grained Attribute Phrases using Reference Games
• Location-Aware Feature Selection Text Detection Network
• Multi-task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs
• Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization
• Ensembling with Deep Generative Views
• Pre-training of Deep RL Agents for Improved Learning under Domain Randomization
• Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph
• Zero-resource Machine Translation by Multimodal Encoder-decoder Network with Multimedia Pivot
• EmpLite: A Lightweight Sequence Labeling Model for Emphasis Selection of Short Texts
• Gym-$\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
• Guitar Effects Recognition and Parameter Estimation with Convolutional Neural Networks
• Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
• Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation
• Live Trojan Attacks on Deep Neural Networks
• FCN+RL: A Fully Convolutional Network followed by Refinement Layers to Offline Handwritten Signature Segmentation
• Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments
• Cross-Modal Generative Augmentation for Visual Question Answering
• Graph Attention Networks with Positional Embeddings
• Multi-Level Temporal Pyramid Network for Action Detection
• Scalable Cross Validation Losses for Gaussian Process Models
• Woodbury Transformations for Deep Generative Flows
• Full Workspace Generation of Serial-link Manipulators by Deep Learning based Jacobian Estimation
• Quantitative analysis of the prediction performance of a Convolutional Neural Network evaluating the surface elastic energy of a strained film
• Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
• Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
• A Binded VAE for Inorganic Material Generation
• Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks
• OmniPrint: A Configurable Printed Character Synthesizer
• The Role of Pleura and Adipose in Lung Ultrasound AI
• Real-time Short Video Recommendation on Mobile Devices
• Label uncertainty-guided multi-stream model for disease screening
• CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
• Semantic Parsing with Dual Learning
• Detection of Sleep Oxygen Desaturations from Electroencephalogram Signals
• Model-agnostic out-of-distribution detection using combined statistical tests
• Learning Embedding of 3D models with Quadric Loss
• NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generation
• Deep Convolutional Neural Networks for Molecular Subtyping of Gliomas Using Magnetic Resonance Imaging
• Using clarification questions to improve software developers' Web search
• End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
• Estimating Nonlinear Dynamics with the ConvNet Smoother
• Forward-Backward Decoding for Regularizing End-to-End TTS
• Verification of Sigmoidal Artificial Neural Networks using iSAT
• Single-view 3D Body and Cloth Reconstruction under Complex Poses
• Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
• Practical Deep Raw Image Denoising on Mobile Devices
• Incorporating the Barzilai-Borwein Adaptive Step Size into Sugradient Methods for Deep Network Training
• Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment
• Physics-informed Spline Learning for Nonlinear Dynamics Discovery
• A Goal-Based Movement Model for Continuous Multi-Agent Tasks
• Learning Approximate and Exact Numeral Systems via Reinforcement Learning
• Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
• Multimodal neural pronunciation modeling for spoken languages with logographic origin
• Semi-supervised Breast Lesion Detection in Ultrasound Video Based on Temporal Coherence
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Restoring Eye Contact to the Virtual Classroom with Machine Learning
• Deep Fault Analysis and Subset Selection in Solar Power Grids
• On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
• Grammatical facial expression recognition using customized deep neural network architecture
• Weakly- and Semi-Supervised Probabilistic Segmentation and Quantification of Ultrasound Needle-Reverberation Artifacts to Allow Better AI Understanding of Tissue Beneath Needles
• Data-driven Policy on Feasibility Determination for the Train Shunting Problem
• Guided Hyperparameter Tuning Through Visualization and Inference
• Smile Like You Mean It: Driving Animatronic Robotic Face with Learned Models
• Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
• Applying Deep Machine Learning for psycho-demographic profiling of Internet users using O.C.E.A.N. model of personality
• Neural Variational Inference and Learning in Undirected Graphical Models
• Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability
• What's wrong with this video? Comparing Explainers for Deepfake Detection
• Incremental Concept Learning via Online Generative Memory Recall
• Believe It or Not, We Know What You Are Looking at!
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
• Dynamical Wasserstein Barycenters for Time-series Modeling
• Inversion of Integral Models: a Neural Network Approach
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
• Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
• Learning to refer informatively by amortizing pragmatic reasoning
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation
• Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
• Neural Lyapunov Model Predictive Control: Learning Safe Global Controllers from Sub-optimal Examples
• Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
• Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks
• Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
• Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks
• Towards one-shot learning for rare-word translation with external experts
• Multi-view Subspace Clustering Networks with Local and Global Graph Information
• Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
• A Novel Framework for Selection of GANs for an Application
• Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
• Uncertainty quantification in medical image segmentation with normalizing flows
• NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
• Learning velocity model for complex media with deep convolutional neural networks
• Classification of Audio Segments in Call Center Recordings using Convolutional Recurrent Neural Networks
• Learning Slice-Aware Representations with Mixture of Attentions
• A comparison of apartment rent price prediction using a large dataset: Kriging versus DNN
• Reverse engineering learned optimizers reveals known and novel mechanisms
• Learning Stable Classifiers by Transferring Unstable Features
• Aerial Height Prediction and Refinement Neural Networks with Semantic and Geometric Guidance
• Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning
• Parallel and distributed asynchronous adaptive stochastic gradient methods
• Machine Learning on sWeighted Data
• Policy Optimization Reinforcement Learning with Entropy Regularization
• SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching
• Emulation with uncertainty quantification of regional sea-level change caused by the Antarctic Ice Sheet
• Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding
• PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning
• Peek Inside the Closed World: Evaluating Autoencoder-Based Detection of DDoS to Cloud
• Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation
• Self-Improved Retrosynthetic Planning
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• FlowChroma -- A Deep Recurrent Neural Network for Video Colorization
• Antonym-Synonym Classification Based on New Sub-space Embeddings
• Learning to Dynamically Coordinate Multi-Robot Teams in Graph Attention Networks
• Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Noise2Blur: Online Noise Extraction and Denoising
• Dynamic Shape Modeling to Analyze Modes ofMigration During Cell Motility
• Deep Learning-Based Decoding of Constrained Sequence Codes
• Assessing the Effectiveness of Syntactic Structure to Learn Code Edit Representations
• NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigation
• Deep 3D Portrait from a Single Image
• Correcting Exposure Bias for Link Recommendation
• Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
• Radial Prediction Layer
• Tutorial on Answering Questions about Images with Deep Learning
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
• Towards Learning Universal Audio Representations
• Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis
• Radon Sobolev Variational Auto-Encoders
• Latent Space Representation for Shape Analysis and Learning
• Kernelized Capsule Networks
• CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis
• Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• Transient Stability Analysis with Physics-Informed Neural Networks
• Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows
• Efficient Video Transformers with Spatial-Temporal Token Selection
• On Neural Inertial Classification Networks for Pedestrian Activity Recognition
• A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
• Detecting Kissing Scenes in a Database of Hollywood Films
• Neural Likelihoods for Multi-Output Gaussian Processes
• Convolutional neural networks for segmentation and object detection of human semen
• Volumetric Capture of Humans with a Single RGBD Camera via Semi-Parametric Learning
• Unsupervised Domain Adaptation on Reading Comprehension
• Normalized Gradient Descent for Variational Quantum Algorithms
• MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences
• Combining AI Control Systems and Human Decision Support via Robustness and Criticality
• One-Class SVM on siamese neural network latent space for Unsupervised Anomaly Detection on brain MRI White Matter Hyperintensities
• Deconfusing intensity maps with neural networks
• Loss Functions for Discrete Contextual Pricing with Observational Data
• Voice Activity Detection in presence of background noise using EEG
• Geometric Operator Convolutional Neural Network
• Merging Deterministic Policy Gradient Estimations with Varied Bias-Variance Tradeoff for Effective Deep Reinforcement Learning
• Guiding Variational Response Generator to Exploit Persona
• End-to-End Argument Mining for Discussion Threads Based on Parallel Constrained Pointer Architecture
• Graph Neural Networks with Feature and Structure Aware Random Walk
• A Stochastic Variance Reduced Nesterov's Accelerated Quasi-Newton Method
• Limits of Multilayer Diffusion Network Inference in Social Media Research
• Revelio: ML-Generated Debugging Queries for Distributed Systems
• Generalized Embedding Machines for Recommender Systems
• Reliable and Fast Recurrent Neural Network Architecture Optimization
• End-to-end 3D face reconstruction with deep neural networks
• Generalizing Complex/Hyper-complex Convolutions to Vector Map Convolutions
• Context-aware Heterogeneous Graph Attention Network for User Behavior Prediction in Local Consumer Service Platform
• Training Artificial Neural Networks by Coordinate Search Algorithm
• Unsupervised Object Matching for Relational Data
• Real-Time Limited-View CT Inpainting and Reconstruction with Dual Domain Based on Spatial Information
• ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes
• Emotion Profile Refinery for Speech Emotion Classification
• Solving deep-learning density functional theory via variational autoencoders
• Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation
• Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias
• Pretrained Language Models for Dialogue Generation with Multiple Input Sources
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• CardioCaps: Attention-based Capsule Network for Class-Imbalanced Echocardiogram Classification
• The Profiling Machine: Active Generalization over Knowledge
• Reconstruct high-resolution multi-focal plane images from a single 2D wide field image
• Gaze Estimation using Transformer
• Cluster Activation Mapping with Applications to Medical Imaging
• Cascaded Head-colliding Attention
• Neural paraphrasing by automatically crawled and aligned sentence pairs
• Visual Question Answering based on Local-Scene-Aware Referring Expression Generation
• Bounded logit attention: Learning to explain image classifiers
• Bimanual Shelf Picking Planner Based on Collapse Prediction
• Multi-Level Contextual Network for Biomedical Image Segmentation
• Scalable Facial Image Compression with Deep Feature Reconstruction
• Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling
• A Deeper Look at 3D Shape Classifiers
• Beyond Textual Data: Predicting Drug-Drug Interactions from Molecular Structure Images using Siamese Neural Networks
• CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
• DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog
• A Comparative Exploration of ML Techniques for Tuning Query Degree of Parallelism
• Learning task-agnostic representation via toddler-inspired learning
• Adaptive Online Learning with Momentum for Contingency-based Voltage Stability Assessment
• End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning
• Angular Learning: Toward Discriminative Embedded Features
• Detecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs
• GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
• PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes
• Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
• Meta ordinal weighting net for improving lung nodule classification
• A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units
• Recurrent convolutional neural networks for mandible segmentation from computed tomography
• Towards Good Practices for Multi-modal Fusion in Large-scale Video Classification
• Sensitivity Analysis of Lift and Drag Coefficients for Flow over Elliptical Cylinders of Arbitrary Aspect Ratio and Angle of Attack using Neural Network
• Adaptive Text Recognition through Visual Matching
• Rapid Generation of Stochastic Signals with Specified Statistics
• Tomography Based Learning for Load Distribution through Opaque Networks
• Detecting Bias in Transfer Learning Approaches for Text Classification
• Segmentation of Drosophila Heart in Optical Coherence Microscopy Images Using Convolutional Neural Networks
• A Distributionally Robust Optimization Method for Adversarial Multiple Kernel Learning
• Duet at TREC 2019 Deep Learning Track
• A Generative Neural Network Framework for Automated Software Testing
• A Supervised Speech enhancement Approach with Residual Noise Control for Voice Communication
• DJCM: A Deep Joint Cascade Model for Singing Voice Separation and Vocal Pitch Estimation
• Learning dynamical systems from data: Gradient-based dictionary optimization
• Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
• Progressive Multi-stage Feature Mix for Person Re-Identification
• Laplacian Denoising Autoencoder
• Deep Unfolding for Fast Linear Massive MIMO Precoders under a PA Consumption Model
• Secure and Differentially Private Bayesian Learning on Distributed Data
• Compare and Select: Video Summarization with Multi-Agent Reinforcement Learning
• Dyna: A Method of Momentum for Stochastic Optimization
• End-to-end Speech Recognition with Adaptive Computation Steps
• End-to-End Multi-Channel Transformer for Speech Recognition
• Cascaded Mutual Modulation for Visual Reasoning
• Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR
• Sufficiently Accurate Model Learning
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Balanced Order Batching with Task-Oriented Graph Clustering
• Improving Formality Style Transfer with Context-Aware Rule Injection
• FSD: Fully-Specialized Detector via Neural Architecture Search
• A Self-Attention-Driven Deep Denoiser Model for Real Time Lung Sound Denoising in Noisy Environments
• An Exploration of Mimic Architectures for Residual Network Based Spectral Mapping
• Localized Distributional Robustness in Submodular Multi-Task Subset Selection
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• Kernel Self-Attention in Deep Multiple Instance Learning
• Structure Learning with Similarity Preserving
• Latent Space Arc Therapy Optimization
• Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
• PitchNet: Unsupervised Singing Voice Conversion with Pitch Adversarial Network
• Physics-enhanced neural networks for equation-of-state calculations
• Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations
• Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
• Lift-the-flap: what, where and when for context reasoning
• Binary Stochastic Filtering: a Method for Neural Network Size Minimization and Supervised Feature Selection
• Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection
• A Hybrid 2-stage Neural Optimization for Pareto Front Extraction
• Knowledge Transfer for Few-shot Segmentation of Novel White Matter Tracts
• Learning Individualized Cardiovascular Responses from Large-scale Wearable Sensors Data
• Single-particle-exact density functional theory
• Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
• Reversible and irreversible bracket-based dynamics for deep graph neural networks
• Measurement-based Evaluation of CNN-based Detection and Estimation for ISAC Systems
• Cluster optical depth and pairwise velocity estimation using machine learning
• Learning 3D Face Reconstruction with a Pose Guidance Network
• Variational Inference for Shrinkage Priors: The R package vir
• PairConnect: A Compute-Efficient MLP Alternative to Attention
• Out-of-Distribution Detection for Adaptive Computer Vision
• Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directions
• Global optimization in variational quantum algorithms via dynamic tunneling method
• Hierarchical Similarity Learning for Language-based Product Image Retrieval
• Residual Squeeze-and-Excitation Network for Fast Image Deraining
• Detecting anthropogenic cloud perturbations with deep learning
• Recurrent Multimodal Interaction for Referring Image Segmentation
• Individualized Context-Aware Tensor Factorization for Online Games Predictions
• Deep Sensing of Urban Waterlogging
• Uncertainty-aware Generalized Adaptive CycleGAN
• Neural Discriminant Analysis for Deep Speaker Embedding
• Towards the Characterization of Representations Learned via Capsule-based Network Architectures
• TraceCaps: A Capsule-based Neural Network for Semantic Segmentation
• Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player
• A Quantitative Metric for Privacy Leakage in Federated Learning
• Modeling Autonomous Shifts Between Focus State and Mind-Wandering Using a Predictive-Coding-Inspired Variational RNN Model
• Configuration, Performance, and Commissioning of the ATLAS $b$-jet Triggers for the 2022 and 2023 LHC data-taking periods
• Fast Hierarchical Neural Network for Feature Learning on Point Cloud
• Variational Auto-Encoder Based Approximate Bayesian Computation Uncertian Inverse Method for Sheet Metal Forming Problem
• Advanced Machine Learning Framework for Efficient Plant Disease Prediction
• A Learning-Based Computational Impact Time Guidance
• Continuous Monitoring of Blood Pressure with Evidential Regression
• Deep learning improved by biological activation functions
• Reward-Reinforced Reinforcement Learning for Multi-agent Systems
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• PoCaPNet: A Novel Approach for Surgical Phase Recognition Using Speech and X-Ray Images
• Learning and Reasoning for Robot Sequential Decision Making under Uncertainty
• Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotations
• A Spectral Enabled GAN for Time Series Data Generation
• Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections
• Segmenting Medical MRI via Recurrent Decoding Cell
• DCoM: A Deep Column Mapper for Semantic Data Type Detection
• Patent Citation Dynamics Modeling via Multi-Attention Recurrent Networks
• NeuroTrainer: An Intelligent Memory Module for Deep Learning Training
• Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
• Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction
• Anomaly Detection Based on Selection and Weighting in Latent Space
• Active Slices for Sliced Stein Discrepancy
• Deep inference of simulated strong lenses in ground-based surveys
• Saliency Driven Perceptual Image Compression
• Learning Image and Video Compression through Spatial-Temporal Energy Compaction
• Neural Network Based Nonlinear Weighted Finite Automata
• D3p -- A Python Package for Differentially-Private Probabilistic Programming
• Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing
• Neural Neighborhood Encoding for Classification
• Machine Learning Prediction of Time-Varying Rayleigh Channels
• Astronomical Classification of Light Curves with an Ensemble of Gated Recurrent Units
• Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies
• Building Context-aware Clause Representations for Situation Entity Type Classification
• Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction
• Revisiting Modularized Multilingual NMT to Meet Industrial Demands
• Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge
• Regularly Updated Deterministic Policy Gradient Algorithm
• Generative Creativity: Adversarial Learning for Bionic Design
• Expert Knowledge-Guided Length-Variant Hierarchical Label Generation for Proposal Classification
• A Deep and Wide Neural Network-based Model for Rajasthan Summer Monsoon Rainfall (RSMR) Prediction
• On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery
• CRAUM-Net: Contextual Recursive Attention with Uncertainty Modeling for Salient Object Detection
• Cross-Validation and Uncertainty Determination for Randomized Neural Networks with Applications to Mobile Sensors
• Action Redundancy in Reinforcement Learning
• Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion
• Computational Graph Approach for Detection of Composite Human Activities
• Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
• Boosting Resource-Constrained Federated Learning Systems with Guessed Updates
• Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation
• Neuromodulated Learning in Deep Neural Networks
• A proof of concept study for machine learning application to stenosis detection
• CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning
• Sequence-Aware Factorization Machines for Temporal Predictive Analytics
• SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Metal Forming Stress Field with Attention Mechanism and Perceptual Features
• A Face-to-Face Neural Conversation Model
• Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos
• Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems
• The ART of Conversation: Measuring Phonetic Convergence and Deliberate Imitation in L2-Speech with a Siamese RNN
• Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
• Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction
• Arbitrary Conditional Distributions with Energy
• Gradient-based Filter Design for the Dual-tree Wavelet Transform
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network
• HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
• Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer
• Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Human Correspondence Consensus for 3D Object Semantic Understanding
• A labeled dataset of cloud types using data from GOES-16 and CloudSat
• Learning Representations of Social Media Users
• Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits
• Information theoretic analysis of computational models as a tool to understand the neural basis of behaviors
• An Efficient Method for the Classification of Croplands in Scarce-Label Regions
• Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task
• Learning Discriminative Prototypes with Dynamic Time Warping
• Understanding the Disharmony between Weight Normalization Family and Weight Decay: $\epsilon -$shifted $L_2$ Regularizer
• A Camera free fiber speckle wavemeter
• Efficient Multimodal Sampling via Tempered Distribution Flow
• MLOD: A multi-view 3D object detection based on robust feature fusion method
• A simulator-based autoencoder for focal plane wavefront sensing
• Bringing Semantic Structures to User Intent Detection in Online Medical Queries
• Unsupervised Class-Incremental Learning Through Confusion
• Exploring the Naturalness of Buggy Code with Recurrent Neural Networks
• Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• Learning Compressible 360° Video Isomers
• Relative Transfer Function Inverse Regression from Low Dimensional Manifold
• Handwriting styles: benchmarks and evaluation metrics
• 3D medical image segmentation with labeled and unlabeled data using autoencoders at the example of liver segmentation in CT images
• An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information
• Where and When: Space-Time Attention for Audio-Visual Explanations
• Learning Conjoint Attentions for Graph Neural Nets
• Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning
• Learning and Interpreting Gravitational-Wave Features from CNNs with a Random Forest Approach
• Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• Modeling the Severity of Complaints in Social Media
• Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
• Informative Sample-Aware Proxy for Deep Metric Learning
• Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
• A neural joint model for Vietnamese word segmentation, POS tagging and dependency parsing
• Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation
• Deep PDF: Probabilistic Surface Optimization and Density Estimation
• Hands-On: Segmenting Individual Signs from Continuous Sequences
• Tools for Unbinned Unfolding
• Functorial Language Models
• Deep Transfer Learning for Thermal Dynamics Modeling in Smart Buildings
• Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
• Vision-Based Lane-Changing Behavior Detection Using Deep Residual Neural Network
• Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages
• Towards a Unified Approach to Single Image Deraining and Dehazing
• Grammar-based Ordinary Differential Equation Discovery
• Practical Bayesian Optimization of Objectives with Conditioning Variables
• LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity
• Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB
• Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution
• Clipping free attacks against artificial neural networks
• OpenCSI: An Open-Source Dataset for Indoor Localization Using CSI-Based Fingerprinting
• DeepBlindness: Fast Blindness Map Estimation and Blindness Type Classification for Outdoor Scene from Single Color Image
• Neural Twins Talk
• Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries
• Analyzing Architectures for Neural Machine Translation Using Low Computational Resources
• FastVentricle: Cardiac Segmentation with ENet
• Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT
• The art of defense: letting networks fool the attacker
• Gaussian Process Regression for Improved Underwater Navigation
• Embedding Similarity Guided License Plate Super Resolution
• Resource-Enhanced Neural Model for Event Argument Extraction
• Less Memory, Faster Speed: Refining Self-Attention Module for Image Reconstruction
• Toward Open-domain Slot Filling via Self-supervised Co-training
• Accurate and Reliable Forecasting using Stochastic Differential Equations
• Search in Imperfect Information Games
• EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion
• Learning to Optimize with Dynamic Mode Decomposition
• ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE
• Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations
• Causal Mediation Analysis with Hidden Confounders
• Deep Contextual Embeddings for Address Classification in E-commerce
• Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction
• Learning to Model Opponent Learning
• Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning
• BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
• Memory and attention in deep learning
• Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
• Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels
• Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
• Learning to Optimize via Wasserstein Deep Inverse Optimal Control
• Random Function Priors for Correlation Modeling
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
• On The Distribution of Penultimate Activations of Classification Networks
• Large-Scale Meta-Learning with Continual Trajectory Shifting
• Deeper or Wider Networks of Point Clouds with Self-attention?
• Interpretable Foreground Object Search As Knowledge Distillation
• Causal affect prediction model using a facial image sequence
• Machine learning dynamics of phase separation in correlated electron magnets
• A hybrid machine-learning algorithm for designing quantum experiments
• Seven Basic Expression Recognition Using ResNet-18
• Deep Kernel Learning for Mortality Prediction in the Face of Temporal Shift
• Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features
• Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance
• When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models
• Learning Generalized Gumbel-max Causal Mechanisms
• Reducing the Model Order of Deep Neural Networks Using Information Theory
• MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer
• Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
• One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
• Learning Resilient Behaviors for Navigation Under Uncertainty
• DeepCore: Convolutional Neural Network for high $p_T$ jet tracking
• Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
• Geometric Enclosing Networks
• Federated Learning with Dynamic Transformer for Text to Speech
• Augmented KRnet for density estimation and approximation
• Survey of Deep Learning Methods for Inverse Problems
• Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering
• Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation
• Data efficiency in graph networks through equivariance
• Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation
• Zero-shot Adversarial Quantization
• Simulating CRF with CNN for CNN
• ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
• Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
• Collaborative Filtering using Denoising Auto-Encoders for Market Basket Data
• HYPE: A High Performing NLP System for Automatically Detecting Hypoglycemia Events from Electronic Health Record Notes
• Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules
• Lockout: Sparse Regularization of Neural Networks
• Operational Support Estimator Networks
• A Hierarchical User Intention-Habit Extract Network for Credit Loan Overdue Risk Detection
• Characterizing the Temporal Dynamics of Information in Visually Guided Predictive Control Using LSTM Recurrent Neural Networks
• Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
• A Bi-Encoder LSTM Model For Learning Unstructured Dialogs
• HuCurl: Human-induced Curriculum Discovery
• Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
• Semi-supervised Learning for Marked Temporal Point Processes
• Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks
• Reliable uncertainty estimate for antibiotic resistance classification with Stochastic Gradient Langevin Dynamics
• Single-Layer Graph Convolutional Networks For Recommendation
• An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation
• Unsupervised Embedding Learning from Uncertainty Momentum Modeling
• Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches
• Deep Learning Assisted Calibrated Beam Training for Millimeter-Wave Communication Systems
• Sensor Transformation Attention Networks
• Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
• KeystoneDepth: Visualizing History in 3D
• Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network
• Conditional Adversarial Camera Model Anonymization
• Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction
• Unique Properties of Flat Minima in Deep Networks
• High-Quality Real Time Facial Capture Based on Single Camera
• Guide Actor-Critic for Continuous Control
• Towards neural reinforcement learning for large deviations in nonequilibrium systems with memory
• Multi Resolution LSTM For Long Term Prediction In Neural Activity Video
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Adma: A Flexible Loss Function for Neural Networks
• Machine Learning for Classification of Protein Helix Capping Motifs
• Deep Mouse: An End-to-end Auto-context Refinement Framework for Brain Ventricle and Body Segmentation in Embryonic Mice Ultrasound Volumes
• Speech Recognition using EEG signals recorded using dry electrodes
• DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates
• Neural Text Generation from Rich Semantic Representations
• Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions
• Dropping Networks for Transfer Learning
• Any-gram Kernels for Sentence Classification: A Sentiment Analysis Case Study
• The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
• ClaiRE at SemEval-2018 Task 7 - Extended Version
• Joint ptycho-tomography with deep generative priors
• Parameter-Based Value Functions
• Nowcasting the turbulence at the Paranal Observatory
• Joint RNN Model for Argument Component Boundary Detection
• Adversarial Dropout for Recurrent Neural Networks
• NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21
• Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder
• Revisiting SGD with Increasingly Weighted Averaging: Optimization and Generalization Perspectives
• Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding
• Neural Fixed-Point Acceleration for Convex Optimization
• Disentangled Representation Learning with Information Maximizing Autoencoder
• CALC2.0: Combining Appearance, Semantic and Geometric Information for Robust and Efficient Visual Loop Closure
• Text Classification and Clustering with Annealing Soft Nearest Neighbor Loss
• Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
• ST-DETR: Spatio-Temporal Object Traces Attention Detection Transformer
• Practical Wide-Angle Portraits Correction with Deep Structured Models
• A Unified Framework for Training Neural Networks
• Towards Controlled and Diverse Generation of Article Comments
• Saliency Detection With Fully Convolutional Neural Network
• IMU-Assisted Learning of Single-View Rolling Shutter Correction
• Classification of Visual Perception and Imagery based EEG Signals Using Convolutional Neural Networks
• RDPD: Rich Data Helps Poor Data via Imitation
• Global Robustness Verification Networks
• Tactile-Based Insertion for Dense Box-Packing
• Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks
• VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network
• Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
• Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering
• Sound2Sight: Generating Visual Dynamics from Sound and Context
• 3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
• PDWN: Pyramid Deformable Warping Network for Video Interpolation
• Neural Networks as Functional Classifiers
• Deep disentangled representations for volumetric reconstruction
• AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos
• Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21
• Deep Learning Based Antenna Selection for Channel Extrapolation in FDD Massive MIMO
• A Deep Signed Directional Distance Function for Object Shape Representation
• Transfer Reward Learning for Policy Gradient-Based Text Generation
• Rapid Probabilistic Interest Learning from Domain-Specific Pairwise Image Comparisons
• Neural Gaussian Copula for Variational Autoencoder
• The Trumpiest Trump? Identifying a Subject's Most Characteristic Tweets
• Nonparametric signal separation in very-high-energy gamma ray observations with probabilistic neural networks
• Adversarial Policy Gradient for Deep Learning Image Augmentation
• Hierarchical Video Generation for Complex Data
• Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition
• Efficient Neural Network Approximation of Robust PCA for Automated Analysis of Calcium Imaging Data
• Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data
• Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features
• Bridging the ELBO and MMD
• Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
• Optimization of Wireless Sensor Network Deployment for Spatiotemporal Reconstruction and Prediction
• A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding
• Hierarchical Multitask Learning Approach for BERT
• Stochastic Block-ADMM for Training Deep Networks
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network
• Autoencoding Under Normalization Constraints
• Estimation of mitral valve hinge point coordinates -- deep neural net for echocardiogram segmentation
• Learning Dynamic Context Augmentation for Global Entity Linking
• PaLM: A Hybrid Parser and Language Model
• A Deep Learning Framework for Classification of in vitro Multi-Electrode Array Recordings
• Evaluating the Apperception Engine
• Fairness-aware Summarization for Justified Decision-Making
• Text2Node: a Cross-Domain System for Mapping Arbitrary Phrases to a Taxonomy
• Investigating Retrieval Method Selection with Axiomatic Features
• MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
• Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants
• HyperHyperNetworks for the Design of Antenna Arrays
• Imagination-Augmented Deep Learning for Goal Recognition
• Modeling Disease Progression In Retinal OCTs With Longitudinal Self-Supervised Learning
• Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform
• Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles
• NaviGAN: A Generative Approach for Socially Compliant Navigation
• Image Augmentation Using a Task Guided Generative Adversarial Network for Age Estimation on Brain MRI
• Boltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment
• Automated Meta-Analysis: A Causal Learning Perspective
• Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
• Surface Normal Reconstruction Using Polarization-Unet
• Federated Learning using Smart Contracts on Blockchains, based on Reward Driven Approach
• Tensor Network for Supervised Learning at Finite Temperature
• Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling
• Efficient Decompositional Rule Extraction for Deep Neural Networks
• Optimizing Neural Network Scale for ECG Classification
• Encoder-Powered Generative Adversarial Networks
• Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents
• A Study on Decoupled Probabilistic Linear Discriminant Analysis
• Semi- and Self-Supervised Multi-View Fusion of 3D Microscopy Images using Generative Adversarial Networks
• Federated Dynamic Neural Network for Deep MIMO Detection
• Elephant Search with Deep Learning for Microarray Data Analysis
• Image Style Transfer and Content-Style Disentanglement
• BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
• Deep Multi-class Adversarial Specularity Removal
• Classifying Topological Charge in SU(3) Yang-Mills Theory with Machine Learning
• Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration
• Detection of Glottal Closure Instants from Raw Speech using Convolutional Neural Networks
• LA3: Efficient Label-Aware AutoAugment
• Distribution Discrepancy Maximization for Image Privacy Preserving
• Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware Fusion
• Maximal Information Leakage based Privacy Preserving Data Disclosure Mechanisms
• Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation
• On-Device Tag Generation for Unstructured Text
• Constructing Explainable Opinion Graphs from Review
• Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
• Multi-Source Neural Variational Inference
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration
• Deep Learning-based Time-varying Channel Estimation for RIS Assisted Communication
• A Matrix Autoencoder Framework to Align the Functional and Structural Connectivity Manifolds as Guided by Behavioral Phenotypes
• Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?
• A Dual Camera System for High Spatiotemporal Resolution Video Acquisition
• An Interpretable Algorithm for Uveal Melanoma Subtyping from Whole Slide Cytology Images
• Strawman: an Ensemble of Deep Bag-of-Ngrams for Sentiment Analysis
• Adaptive Braking for Mitigating Gradient Delay
• Incorporating Symbolic Sequential Modeling for Speech Enhancement
• Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational $N$-body Problem
• Context-aware Cascade Attention-based RNN for Video Emotion Recognition
• Audio to score matching by combining phonetic and duration information
• Finding essential parts of the brain in rs-fMRI can improve diagnosing ADHD by Deep Learning
• Foresee: Attentive Future Projections of Chaotic Road Environments with Online Training
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
• Computing Steiner Trees using Graph Neural Networks
• Geodesics in fibered latent spaces: A geometric approach to learning correspondences between conditions
• Learning to Embed Sentences Using Attentive Recursive Trees
• A Unified Framework for Cross-Domain and Cross-System Recommendations
• Multi-scale Alignment and Contextual History for Attention Mechanism in Sequence-to-sequence Model
• LMVP: Video Predictor with Leaked Motion Information
• Trainable Projected Gradient Detector for Sparsely Spread Code Division Multiple Access
• A Contactless Fingerprint Recognition System
• Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
• Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
• Learning Sentence Embeddings for Coherence Modelling and Beyond
• Volume of hyperintense inflammation (VHI): a deep learning-enabled quantitative imaging biomarker of inflammation load in spondyloarthritis
• Memory-guided Unsupervised Image-to-image Translation
• Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
• Noise Conditional Flow Model for Learning the Super-Resolution Space
• A Stochastic Objective-Function-Free Adaptive Regularization Method with Optimal Complexity
• Noisy-Labeled NER with Confidence Estimation
• The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
• LassoLayer: Nonlinear Feature Selection by Switching One-to-one Links
• Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures
• Learning Shared Encoding Representation for End-to-End Speech Recognition Models
• A Convolutional Neural Network-based Approach to Field Reconstruction
• Dance Dance Generation: Motion Transfer for Internet Videos
• 3D Organ Shape Reconstruction from Topogram Images
• Do Context-Aware Translation Models Pay the Right Attention?
• On Local Aggregation in Heterophilic Graphs
• Unsupervised Learning of Neurosymbolic Encoders
• Principled Parallel Mean-Field Inference for Discrete Random Fields
• Dense-Resolution Network for Point Cloud Classification and Segmentation
• Unsupervised Monocular Depth Perception: Focusing on Moving Objects
• Modeling Deep Learning Based Privacy Attacks on Physical Mail
• VCWE: Visual Character-Enhanced Word Embeddings
• Matching Distributions via Optimal Transport for Semi-Supervised Learning
• Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection
• Efficient wavefront sensing for space-based adaptive optics
• Video-based Person Re-identification without Bells and Whistles
• On the Downstream Performance of Compressed Word Embeddings
• Prediction of the Facial Growth Direction is Challenging
• A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
• Semantic Graph Convolutional Network for Implicit Discourse Relation Classification
• Interpreting Undesirable Pixels for Image Classification on Black-Box Models
• Reasoning-Modulated Representations
• Robust Question Answering Through Sub-part Alignment
• Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation
• Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts
• Universal Marginalizer for Amortised Inference and Embedding of Generative Models
• Updating the generator in PPGN-h with gradients flowing through the encoder
• Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
• Stochastic Gradient Variance Reduction by Solving a Filtering Problem
• Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss
• ReDecode Framework for Iterative Improvement in Paraphrase Generation
• Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
• A Daily Tourism Demand Prediction Framework Based on Multi-head Attention CNN: The Case of The Foreign Entrant in South Korea
• On Semi-Supervised Multiple Representation Behavior Learning
• Learning from Demonstration with Weakly Supervised Disentanglement
• Explicit Cross-lingual Pre-training for Unsupervised Machine Translation
• An Open Source Software Stack for Tuning the Dynamical Behavior of Complex Power Systems
• SANet:Superpixel Attention Network for Skin Lesion Attributes Detection
• Node Feature Kernels Increase Graph Convolutional Network Robustness
• TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning
• Attack Assessment and Augmented Identity Recognition for Human Skeleton Data
• Patient ADE Risk Prediction through Hierarchical Time-Aware Neural Network Using Claim Codes
• Learning Bijective Feature Maps for Linear ICA
• Physics-oriented learning of nonlinear Schrödinger equation: optical fiber loss and dispersion profile identification
• STS Classification with Dual-stream CNN
• Robustifying automatic speech recognition by extracting slowly varying features
• Transfer Learning for Node Regression Applied to Spreading Prediction
• Neural Logic Networks
• Surrogate-data-enriched Physics-Aware Neural Networks
• Adversarial Edit Attacks for Tree Data
• Applying SoftTriple Loss for Supervised Language Model Fine Tuning
• An Optical physics inspired CNN approach for intrinsic image decomposition
• Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices
• Inference of cell dynamics on perturbation data using adjoint sensitivity
• Signal-domain representation of symbolic music for learning embedding spaces
• Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation
• GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
• You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
• Predicting the Gender of Indonesian Names
• Estimating Stochastic Poisson Intensities Using Deep Latent Models
• A Sketch Based 3D Shape Retrieval Approach Based on Efficient Deep Point-to-Subspace Metric Learning
• Estimating Individual Advertising Effect in E-Commerce
• Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
• Subtractive Mixture Models via Squaring: Representation and Learning
• Discover the Mysteries of the Maya: Selected Contributions from the Machine Learning Challenge & The Discovery Challenge Workshop at ECML PKDD 2021
• Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning
• Energy Aligning for Biased Models
• When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence
• EMA: Auditing Data Removal from Trained Models
• Neutral Face Game Character Auto-Creation via PokerFace-GAN
• Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees
• Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks
• Using neural networks to predict icephobic performance
• Deep Learning for Prostate Pathology
• Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking
• Continuous Silent Speech Recognition using EEG
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
• End-to-end analysis using image classification
• Quaternion Convolutional Neural Networks
• MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
• Real-Time Cleaning and Refinement of Facial Animation Signals
• Multi Target Tracking by Learning from Generalized Graph Differences
• Financial Market Trend Forecasting and Performance Analysis Using LSTM
• Correcting Momentum in Temporal Difference Learning
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
• Does Vision-and-Language Pretraining Improve Lexical Grounding?
• A Probabilistic Generative Model of Linguistic Typology
• Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
• The NiuTrans Machine Translation Systems for WMT21
• Progressive Learning Algorithm for Efficient Person Re-Identification
• News Meets Microblog: Hashtag Annotation via Retriever-Generator
• Differentiable Multiple Shooting Layers
• Group Affect Prediction Using Multimodal Distributions
• Mining Commonsense Facts from the Physical World
• 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
• Autoencoders, Kernels, and Multilayer Perceptrons for Electron Micrograph Restoration and Compression
• Nonlinear Collaborative Scheme for Deep Neural Networks
• Preserving New Physics while Simultaneously Unfolding All Observables
• Dual-View Distilled BERT for Sentence Embedding
• A Deep, Information-theoretic Framework for Robust Biometric Recognition
• Learning and Exploiting Interclass Visual Correlations for Medical Image Classification
• Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training
• Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation
• Improving Label Quality by Jointly Modeling Items and Annotators
• Complete 3D Scene Parsing from an RGBD Image
• A Two-stage Deep Network for High Dynamic Range Image Reconstruction
• On Higher-order Moments in Adam
• Towards End-to-end Car License Plate Location and Recognition in Unconstrained Scenarios
• SkelCap: Automated Generation of Descriptive Text from Skeleton Keypoint Sequences
• Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance
• Structural Recurrent Neural Network for Traffic Speed Prediction
• Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
• LSTM-based Flow Prediction
• Artificial Neural Networks for Galaxy Clustering. Learning from the two-point correlation function of BOSS galaxies
• Egocentric 6-DoF Tracking of Small Handheld Objects
• Neural Networks for Learning Counterfactual G-Invariances from Single Environments
• A Grid-Structured Model of Tubular Reactors
• Mass Segmentation in Automated 3-D Breast Ultrasound Using Dual-Path U-net
• Efficiently applying attention to sequential data with the Recurrent Discounted Attention unit
• PAC${}^m$-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime
• Learning Functions in Large Networks requires Modularity and produces Multi-Agent Dynamics
• Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue
• Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization
• A Projectional Ansatz to Reconstruction
• End-to-End Image Compression with Probabilistic Decoding
• Optic Disc Segmentation using Disk-Centered Patch Augmentation
• torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
• Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
• Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech
• CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
• Manifestation of Image Contrast in Deep Networks
• Sensorless Freehand 3D Ultrasound Reconstruction via Deep Contextual Learning
• Geodesic-HOF: 3D Reconstruction Without Cutting Corners
• Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• A Domain Generalization Perspective on Listwise Context Modeling
• Tandem Blocks in Deep Convolutional Neural Networks
• Quasi-Newton Quasi-Monte Carlo for variational Bayes
• Deep Lucas-Kanade Homography for Multimodal Image Alignment
• Enabling Incremental Knowledge Transfer for Object Detection at the Edge
• Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction
• Privacy-preserving Neural Representations of Text
• Neuron Segmentation Using Deep Complete Bipartite Networks
• On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations
• CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement
• Multi-stage Suture Detection for Robot Assisted Anastomosis based on Deep Learning
• Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists
• Speaker-adaptive neural vocoders for parametric speech synthesis systems
• PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling
• Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment
• Extracting Halo Independent Information from Dark Matter Electron Scattering Data
• Neural Conditional Event Time Models
• A Model You Can Hear: Audio Identification with Playable Prototypes
• Submodular Batch Selection for Training Deep Neural Networks
• Scalable Multi-Class Bayesian Support Vector Machines for Structured and Unstructured Data
• Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization
• Wasserstein Introspective Neural Networks
• Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos
• Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Faces
• Learning Cluster Structured Sparsity by Reweighting
• Explicit CSI Feedback Compression via Learned Approximate Message Passing
• Identification of Attack-Specific Signatures in Adversarial Examples
• Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh
• Speaking Speed Control of End-to-End Speech Synthesis using Sentence-Level Conditioning
• The Deep Poincaré Map: A Novel Approach for Left Ventricle Segmentation
• Using convolutional neural networks for the classification of breast cancer images
• Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
• CuisineNet: Food Attributes Classification using Multi-scale Convolution Network
• Top-K Ranking Deep Contextual Bandits for Information Selection Systems
• Cosmological parameter estimation from large-scale structure deep learning
• 3D Human Pose Estimation for Free-form Activity Using WiFi Signals
• A Generative Map for Image-based Camera Localization
• Explanations for Temporal Recommendations
• Indoor Distance Estimation using LSTMs over WLAN Network
• Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
• Dating Documents using Graph Convolution Networks
• Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
• Soccer Team Vectors
• Differentiable Electron Microscopy Simulation: Methods and Applications for Visualization
• Exploring layerwise decision making in DNNs
• Interactive Machine Comprehension with Information Seeking Agents
• A Multi-Turn Emotionally Engaging Dialog Model
• Drug-drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers
• How Do You Act? An Empirical Study to Understand Behavior of Deep Reinforcement Learning Agents
• Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
• R${}^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning
• Variationally Inferred Sampling Through a Refined Bound for Probabilistic Programs
• Shaking Acoustic Spectral Sub-bands Can Better Regularize Learning in Affective Computing
• Layout Sequence Prediction From Noisy Mobile Modality
• Boosting Invisible Higgs Searches by Tagging a Gluon Jet for Gluon Fusion Process
• 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
• Audio-Visual Decision Fusion for WFST-based and seq2seq Models
• PIPO-Net: A Penalty-based Independent Parameters Optimization Deep Unfolding Network
• Spherical Sliced-Wasserstein
• Detection of Alzheimers Disease from MRI using Convolutional Neural Networks, Exploring Transfer Learning And BellCNN
• ICLR Reproducibility Challenge Report (Padam : Closing The Generalization Gap Of Adaptive Gradient Methods in Training Deep Neural Networks)
• Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback
• A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration
• Out-of-Sample Testing for GANs
• Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images
• Multi-Image Summarization: Textual Summary from a Set of Cohesive Images
• SPI-Optimizer: an integral-Separated PI Controller for Stochastic Optimization
• Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
• Autoregressive Diffusion Models
• Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric
• G3AN: Disentangling Appearance and Motion for Video Generation
• Visual Radial Basis Q-Network
• An Automated Bandwidth Division for the LHCb Upgrade Trigger
• Effective Representation for Easy-First Dependency Parsing
• Question Answering based Clinical Text Structuring Using Pre-trained Language Model
• Model Agnostic Combination for Ensemble Learning
• Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks
• Image Enhancement Network Trained by Using HDR images
• Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout
• Language Transfer for Early Warning of Epidemics from Social Media
• Differentiate Everything with a Reversible Embeded Domain-Specific Language
• Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System
• Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
• Convergent Graph Solvers
• Enhanced Image Reconstruction From Quarter Sampling Measurements Using An Adapted Very Deep Super Resolution Network
• Semantic Matching by Weakly Supervised 2D Point Set Registration
• Dissecting a Small Artificial Neural Network
• Learning Joint Acoustic-Phonetic Word Embeddings
• Deeply-Learned Generalized Linear Models with Missing Data
• From Rain Generation to Rain Removal
• Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
• Cross-attention conformer for context modeling in speech enhancement for ASR
• A Machine-Learning-Based Importance Sampling Method to Compute Rare Event Probabilities
• Single Image Super-Resolution Using Lightweight CNN with Maxout Units
• Deep Within-Class Covariance Analysis for Robust Audio Representation Learning
• Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds
• Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach
• Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
• Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder
• Towards Universal End-to-End Affect Recognition from Multilingual Speech by ConvNets
• Adversarial Self-Supervised Data-Free Distillation for Text Classification
• ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
• Knowledge Transfer with Medical Language Embeddings
• Adapting Convolutional Neural Networks for Geographical Domain Shift
• Knowledge-based end-to-end memory networks
• Detecting Logical Relation In Contract Clauses
• DeepEmo: Learning and Enriching Pattern-Based Emotion Representations
• Fine-grained Conversational Decoding via Isotropic and Proximal Search
• Conceptualize and Infer User Needs in E-commerce
• Potential-Based Advice for Stochastic Policy Learning
• Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
• Reconstructing faces from voices
• Meta-Learner with Linear Nulling
• An Interactive Machine Translation Framework for Modernizing Historical Documents
• Resampling and super-resolution of hexagonally sampled images using deep learning
• Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
• Variational Bayesian Dropout with a Hierarchical Prior
• Transfer-Learning-Aware Neuro-Evolution for Diseases Detection in Chest X-Ray Images
• Disentangling Video with Independent Prediction
• Learning Autonomous Exploration and Mapping with Semantic Vision
• The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
• Weakly Supervised Action Selection Learning in Video
• Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
• Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video
• Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation
• Image-based Detection of Surface Defects in Concrete during Construction
• Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
• Time Series Deinterleaving of DNS Traffic
• A Relational Model for One-Shot Classification
• Deformable Part Networks
• Multi-Granular Text Encoding for Self-Explaining Categorization
• Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
• DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement
• Discovering Generalizable Skills via Automated Generation of Diverse Tasks
• One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
• Learning Fast Approximations of Sparse Nonlinear Regression
• TempNodeEmb:Temporal Node Embedding considering temporal edge influence matrix
• A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
• Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler
• On Label Shift in Domain Adaptation via Wasserstein Distance
• Low-Shot Learning from Imaginary 3D Model
• Phase Aware Speech Enhancement using Realisation of Complex-valued LSTM
• Questions to Guide the Future of Artificial Intelligence Research
• VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Camera
• Compressing Sign Information in DCT-based Image Coding via Deep Sign Retrieval
• Simulating dysarthric speech for training data augmentation in clinical speech applications
• A short note on the decision tree based neural turing machine
• Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization
• A Variational Topological Neural Model for Cascade-based Diffusion in Networks
• AI-Enhanced Self-Triggering for Extensive Air Showers: Performance and FPGA Feasibility
• OadTR: Online Action Detection with Transformers
• Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
• Machine Learning based Simulation Optimisation for Trailer Management
• Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
• Efficient CNN with uncorrelated Bag of Features pooling
• Deep Unfolded Multicast Beamforming
• Carathéodory Sampling for Stochastic Gradient Descent
• Predicting Ground-Level Scene Layout from Aerial Imagery
• Efficient Arabic emotion recognition using deep neural networks
• Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks
• Modeling Conceptual Characteristics of Virtual Machines for CPU Utilization Prediction
• Image Captioning based on Deep Reinforcement Learning
• Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification
• An RNN-Survival Model to Decide Email Send Times
• CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
• Deception Detection by 2D-to-3D Face Reconstruction from Videos
• Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
• Adaptive Divergence for Rapid Adversarial Optimization
• A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks
• Cross-Correlated Attention Networks for Person Re-Identification
• Using a New Nonlinear Gradient Method for Solving Large Scale Convex Optimization Problems with an Application on Arabic Medical Text
• Deep Learning Assisted mmWave Beam Prediction with Prior Low-frequency Information
• Multi-layered tensor networks for image classification
• Genetic-algorithm-optimized neural networks for gravitational wave classification
• Parallelized Interactive Machine Learning on Autonomous Vehicles
• NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks
• Prioritized Guidance for Efficient Multi-Agent Reinforcement Learning Exploration
• LMKL-Net: A Fast Localized Multiple Kernel Learning Solver via Deep Neural Networks
• Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts
• Mack-Net model: Blending Mack's model with Recurrent Neural Networks
• Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
• Deep learning based track reconstruction on CEPC luminometer
• Lifting 2D StyleGAN for 3D-Aware Face Generation
• Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
• HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks
• Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
• DAN: A Deformation-Aware Network for Consecutive Biomedical Image Interpolation
• From Stars to Molecules: AI Guided Device-Agnostic Super-Resolution Imaging
• Artificial ASMR: A Cyber-Psychological Approach
• pix2rule: End-to-end Neuro-symbolic Rule Learning
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• Event-Related Bias Removal for Real-time Disaster Events
• Picking Apart Story Salads
• InSPECtor: an end-to-end design framework for compressive pixelated hyperspectral instruments
• An Approximation Algorithm for Optimal Subarchitecture Extraction
• Deep generative demixing: Recovering Lipschitz signals from noisy subgaussian mixtures
• Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
• Adaptive Techniques in Practical Quantum Key Distribution
• Multimodal Data Fusion based on the Global Workspace Theory
• Bio-inspired visual relative localization for large swarms of UAVs
• Unsupervised Neural Universal Denoiser for Finite-Input General-Output Noisy Channel
• Pathwise Derivatives for Multivariate Distributions
• Global Pixel Transformers for Virtual Staining of Microscopy Images
• Exclusion and Inclusion -- A model agnostic approach to feature importance in DNNs
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• NullSpaceNet: Nullspace Convoluional Neural Network with Differentiable Loss Function
• Experiential Robot Learning with Accelerated Neuroevolution
• The Effects of Image Pre- and Post-Processing, Wavelet Decomposition, and Local Binary Patterns on U-Nets for Skin Lesion Segmentation
• "You eat with your eyes first": Optimizing Yelp Image Advertising
• GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
• Model Order Selection with Variational Autoencoding
• When Shall I Be Empathetic? The Utility of Empathetic Parameter Estimation in Multi-Agent Interactions
• Short-time deep-learning based source separation for speech enhancement in reverberant environments with beamforming
• Stay On-Topic: Generating Context-specific Fake Restaurant Reviews
• Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspective
• DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification
• Quantifying Intimacy in Language
• Diverse and Styled Image Captioning Using SVD-Based Mixture of Recurrent Experts
• Channel-Directed Gradients for Optimization of Convolutional Neural Networks
• ADWPNAS: Architecture-Driven Weight Prediction for Neural Architecture Search
• Towards Real-Time Advancement of Underwater Visual Quality with GAN
• Naturalization of Text by the Insertion of Pauses and Filler Words
• Cross-Modal Progressive Comprehension for Referring Segmentation
• Virtual Codec Supervised Re-Sampling Network for Image Compression
• GrabQC: Graph based Query Contextualization for automated ICD coding
• Scalable Unidirectional Pareto Optimality for Multi-Task Learning with Constraints
• Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data
• A Self-Supervised Learning Approach to Rapid Path Planning for Car-Like Vehicles Maneuvering in Urban Environment
• Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling
• Efficient Knowledge Graph Validation via Cross-Graph Representation Learning
• Distributed deep learning on edge-devices: feasibility via adaptive compression
• Depth-Adaptive Graph Recurrent Network for Text Classification
• Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
• Deep Bayesian Nonparametric Factor Analysis
• Targeted Adversarial Perturbations for Monocular Depth Prediction
• Univariate Long-Term Municipal Water Demand Forecasting
• Convolutional Spectral Kernel Learning
• DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning
• LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
• RNN-based Online Learning: An Efficient First-Order Optimization Algorithm with a Convergence Guarantee
• Excavate Condition-invariant Space by Intrinsic Encoder
• PIAVE: A Pose-Invariant Audio-Visual Speaker Extraction Network
• Advances in Collaborative Filtering and Ranking
• Structural Optimization of Factor Graphs for Symbol Detection via Continuous Clustering and Machine Learning
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
• Interpretable Deep Learning applied to Plant Stress Phenotyping
• Close-Proximity Underwater Terrain Mapping Using Learning-based Coarse Range Estimation
• Towards Head Motion Compensation Using Multi-Scale Convolutional Neural Networks
• Can Deep Learning Relax Endomicroscopy Hardware Miniaturization Requirements?
• Natural Language Processing to Detect Cognitive Concerns in Electronic Health Records Using Deep Learning
• A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph
• Working Memory Graphs
• Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
• DisenE: Disentangling Knowledge Graph Embeddings
• Machine learning based data retrieval for inverse scattering problems with incomplete data
• A Recurrent Neural Network Approach to the Answering Machine Detection Problem
• Guided Labeling using Convolutional Neural Networks
• Glioma Classification Using Multimodal Radiology and Histology Data
• Neural Abstract Reasoner
• A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning
• Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning
• An Autonomous Approach to Measure Social Distances and Hygienic Practices during COVID-19 Pandemic in Public Open Spaces
• Distortion-controlled Training for End-to-end Reverberant Speech Separation with Auxiliary Autoencoding Loss
• Periodic Q-Learning
• Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
• MT: Multi-Perspective Feature Learning Network for Scene Text Detection
• Improved low-count quantitative PET reconstruction with an iterative neural network
• Stylized Neural Painting
• Data-driven Estimation of Sinusoid Frequencies
• Modularized and Scalable Compilation for Double Quantum Dot Quatum Computing
• Adversarial training applied to Convolutional Neural Network for photometric redshift predictions
• Sports Camera Pose Refinement Using an Evolution Strategy
• Understanding effect of speech perception in EEG based speech recognition systems
• Investigating the Working of Text Classifiers
• Fast Model Editing at Scale
• Learning Image Matching by Simply Watching Video
• DGC-Net: Dense Geometric Correspondence Network
• HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
• Learning to estimate label uncertainty for automatic radiology report parsing
• Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices
• Language Modeling with Highway LSTM
• Implicit Filter-and-sum Network for Multi-channel Speech Separation
• Lenses In VoicE (LIVE): Searching for strong gravitational lenses in the VOICE@VST survey using Convolutional Neural Networks
• 5G Air-to-Ground Network Design and Optimization: A Deep Learning Approach
• DIABLO: Dictionary-based Attention Block for Deep Metric Learning
• Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach
• An Efficient Integration of Disentangled Attended Expression and Identity FeaturesFor Facial Expression Transfer andSynthesis
• Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness
• Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction
• Data-driven Accelerogram Synthesis using Deep Generative Models
• Symmetrical Synthesis for Deep Metric Learning
• Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
• Towards Good Practices for Video Object Segmentation
• Simultaneously forecasting global geomagnetic activity using Recurrent Networks
• Black-Box Inference for Non-Linear Latent Force Models
• Ensemble of Neural Classifiers for Scoring Knowledge Base Triples
• Efficient and Phase-aware Video Super-resolution for Cardiac MRI
• Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
• Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism
• Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks
• Feature Selection on Lyme Disease Patient Survey Data
• Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners
• Robot Object Retrieval with Contextual Natural Language Queries
• Tangent-Space Regularization for Neural-Network Models of Dynamical Systems
• Exploring Optimal DNN Architecture for End-to-End Beamformers Based on Time-frequency References
• MAC for Machine Type Communications in Industrial IoT -- Part II: Scheduling and Numerical Results
• A Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification
• Task-Guided Pair Embedding in Heterogeneous Network
• Generating the Cloud Motion Winds Field from Satellite Cloud Imagery Using Deep Learning Approach
• DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories
• A Controller-Recognizer Framework: How necessary is recognition for control?
• Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
• Monte Carlo Tree Search in the Presence of Transition Uncertainty
• Universal Perceptual Grouping
• Amended Cross Entropy Cost: Framework For Explicit Diversity Encouragement
• Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss
• Machine Learning for Model Order Selection in MIMO OFDM Systems
• Deep Latent-Variable Kernel Learning
• The Nipple-Areola Complex for Criminal Identification
• A Markov Decision Process Approach to Active Meta Learning
• Automatic, Personalized, and Flexible Playlist Generation using Reinforcement Learning
• Lite Audio-Visual Speech Enhancement
• Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding
• EigenEmo: Spectral Utterance Representation Using Dynamic Mode Decomposition for Speech Emotion Classification
• Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations
• HOPF: Higher Order Propagation Framework for Deep Collective Classification
• Advancing Multiple Instance Learning with Attention Modeling for Categorical Speech Emotion Recognition
• DeepSIC: Deep Semantic Image Compression
• AWE: Asymmetric Word Embedding for Textual Entailment
• DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants
• Neural-network-based level-1 trigger upgrade for the SuperCDMS experiment at SNOLAB
• Continuous Histogram Loss: Beyond Neural Similarity
• Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions
• Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms
• The Outer Product Structure of Neural Network Derivatives
• Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics
• On Compression Principle and Bayesian Optimization for Neural Networks
• Predicting Performance for Natural Language Processing Tasks
• Bayesian posterior approximation via greedy particle optimization
• Efficient Covariance Estimation from Temporal Data
• Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• POLO: a POLicy-based Optimization library
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining
• Can't Boil This Frog: Robustness of Online-Trained Autoencoder-Based Anomaly Detectors to Adversarial Poisoning Attacks
• Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
• Unsupervised Person Re-identification by Deep Learning Tracklet Association
• Pseudo-Bidirectional Decoding for Local Sequence Transduction
• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
• Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
• Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification
• Sim2Real for Self-Supervised Monocular Depth and Segmentation
• Deep Bayesian Unsupervised Lifelong Learning
• AGNet: Weighing Black Holes with Machine Learning
• Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
• Neural Stream Functions
• Adaptive Region Embedding for Text Classification
• DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
• Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis
• AMII: Adaptive Multimodal Inter-personal and Intra-personal Model for Adapted Behavior Synthesis
• Modelling the development of counting with memory-augmented neural networks
• Distributed Map Classification using Local Observations
• Semantic Correspondence: A Hierarchical Approach
• Skin-MIMO: Vibration-based MIMO Communication over Human Skin
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation
• Disentangling semantic features of macromolecules in Cryo-Electron Tomography
• Keyword-Guided Neural Conversational Model
• NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image
• Financial Time Series Analysis and Forecasting with HHT Feature Generation and Machine Learning
• The Indian Chefs Process
• Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
• Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer
• TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data
• On Constraint Definability in Tractable Probabilistic Models
• Generic 3D Convolutional Fusion for image restoration
• Ground States of Quantum Many Body Lattice Models via Reinforcement Learning
• Constructing Deep Neural Networks with a Priori Knowledge of Wireless Tasks
• Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers
• Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks
• Fast-reactive probabilistic motion planning for high-dimensional robots
• Boosting Cloud Data Analytics using Multi-Objective Optimization
• Predict joint angle of body parts based on sequence pattern recognition
• Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping
• Mapping high-performance RNNs to in-memory neuromorphic chips
• Cubic Spline Smoothing Compensation for Irregularly Sampled Sequences
• Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System
• Deep-Temporal LSTM for Daily Living Action Recognition
• Variational Inference with Mixture Model Approximation: Robotic Applications
• Progressively-Growing AmbientGANs For Learning Stochastic Object Models From Imaging Measurements
• CounterExample Guided Neural Synthesis
• ProMask: Probability Mask for Skeleton Detection
• 3D Human Shape Reconstruction from a Polarization Image
• iSPA-Net: Iterative Semantic Pose Alignment Network
• Two-Level K-FAC Preconditioning for Deep Learning
• The Role of Regularization in Shaping Weight and Node Pruning Dependency and Dynamics
• DDR-Net: Dividing and Downsampling Mixed Network for Diffeomorphic Image Registration
• Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning
• Efficient and Scalable Structure Learning for Bayesian Networks: Algorithms and Applications
• Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT
• Learning Preference-Based Similarities from Face Images using Siamese Multi-Task CNNs
• MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations
• Deep Networks to Automatically Detect Late-activating Regions of the Heart
• Multicell Power Control under Rate Constraints with Deep Learning
• Online Detection of Action Start in Untrimmed, Streaming Videos
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
• A Variational Auto-Encoder for Reservoir Monitoring
• End-to-End Interpretation of the French Street Name Signs Dataset
• An Understanding-Oriented Robust Machine Reading Comprehension Model
• Scale Aware Adaptation for Land-Cover Classification in Remote Sensing Imagery
• Sheaf Neural Networks
• Human-centric Relation Segmentation: Dataset and Solution
• Case-Base Neural Networks: survival analysis with time-varying, higher-order interactions
• Neural fidelity warping for efficient robot morphology design
• NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning
• Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
• Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
• PowerNet: Neural Power Demand Forecasting in Smart Grid
• Gaussian Embedding of Temporal Networks
• InteractionNet: Modeling and Explaining of Noncovalent Protein-Ligand Interactions with Noncovalent Graph Neural Network and Layer-Wise Relevance Propagation
• LSTM recurrent neural network assisted aircraft stall prediction for enhanced situational awareness
• Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network
• RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval
• Deformable Kernel Convolutional Network for Video Extreme Super-Resolution
• Universal Online Convex Optimization Meets Second-order Bounds
• Knowledge-aware Pronoun Coreference Resolution
• Recurrent neural network analysis of single trajectories switching between anomalous diffusion states
• Image-Graph-Image Translation via Auto-Encoding
• Bregman Gradient Policy Optimization
• Transfer Learning using Neural Ordinary Differential Equations
• Neural Group Actions
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Iterative Multi-document Neural Attention for Multiple Answer Prediction
• Deeply Equal-Weighted Subset Portfolios
• Learning and Inference in Imaginary Noise Models
• InterpoNet, A brain inspired neural network for optical flow dense interpolation
• Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
• Enriched Annotations for Tumor Attribute Classification from Pathology Reports with Limited Labeled Data
• Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning
• A Memory-Augmented Neural Network Model of Abstract Rule Learning
• Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning
• Masking schemes for universal marginalisers
• Reannealing of Decaying Exploration Based On Heuristic Measure in Deep Q-Network
• 25 years of CNNs: Can we compare to human abstraction capabilities?
• Adaptive Weighting Depth-variant Deconvolution of Fluorescence Microscopy Images with Convolutional Neural Network
• Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
• Deep Learning Estimation of Absorbed Dose for Nuclear Medicine Diagnostics
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data
• Differentiable Feature Aggregation Search for Knowledge Distillation
• LenNet: Direct Detection and Localization of Strong Gravitational Lenses in Wide-Field Sky Survey Images
• Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation
• Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention
• Detection and classification of vocal productions in large scale audio recordings
• A Multi-Modal States based Vehicle Descriptor and Dilated Convolutional Social Pooling for Vehicle Trajectory Prediction
• Learning Interclass Relations for Image Classification
• Self-Supervised Multimodal Opinion Summarization
• On-the-fly Prediction of Protein Hydration Densities and Free Energies using Deep Learning
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• Neural Enhanced Belief Propagation for Cooperative Localization
• Gestalt: a Stacking Ensemble for SQuAD2.0
• Correspondence-free online human motion retargeting
• Learning Simpler Language Models with the Differential State Framework
• Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
• Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction
• Generative Deep Learning Model for a Multi-level Nano-Optic Broadband Power Splitter
• In Vitro Electron Density Refinement from Solution X-ray Scattering in the Wide-Angle Regime
• Aggressive Perception-Aware Navigation using Deep Optical Flow Dynamics and PixelMPC
• Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost Functions
• Feature-Aided Adaptive-Tuning Deep Learning for Massive Device Detection
• ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification
• Suppression of accidental backgrounds with deep neural networks in the PandaX-II experiment
• Pacos: Modeling Users' Interpretable and Context-Dependent Choices in Preference Reversals
• Femtosecond pulse parameter estimation from photoelectron momenta using machine learning
• Learning to Rank with Variable Result Presentation Lengths
• Bayesian Attention Modules
• On the Bias Against Inductive Biases
• Semantically Selective Augmentation for Deep Compact Person Re-Identification
• EQ-Net: A Unified Deep Learning Framework for Log-Likelihood Ratio Estimation and Quantization
• An iterative K-FAC algorithm for Deep Learning
• Pixel-wise Crowd Understanding via Synthetic Data
• Confidence Inference for Focused Learning in Stereo Matching
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• Construction Cost Index Forecasting: A Multi-feature Fusion Approach
• Local Methods with Adaptivity via Scaling
• Attentive Tree-structured Network for Monotonicity Reasoning
• Data Augmentation for Text Generation Without Any Augmented Data
• Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation
• Multi-Scale Time-Frequency Attention for Acoustic Event Detection
• Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks
• Cross-modal supervised learning for better acoustic representations
• Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach
• LEED: Label-Free Expression Editing via Disentanglement
• BiDet: An Efficient Binarized Object Detector
• Meta Matrix Factorization for Federated Rating Predictions
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• HIVE-Net: Centerline-Aware HIerarchical View-Ensemble Convolutional Network for Mitochondria Segmentation in EM Images
• Text classification with pixel embedding
• Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
• HypervolGAN: An efficient approach for GAN with multi-objective training function
• NEJM-enzh: A Parallel Corpus for English-Chinese Translation in the Biomedical Domain
• Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations
• Supervised and Unsupervised Learning of Parameterized Color Enhancement
• Deep Learning Based RIS Channel Extrapolation with Element-grouping
• Pushing the boundaries of parallel Deep Learning -- A practical approach
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction
• Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categories
• A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
• Provably Correct Learning Algorithms in the Presence of Time-Varying Features Using a Variational Perspective
• Neuro-Reachability of Networked Microgrids
• Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search
• A Data-Driven Approach to Smooth Pitch Correction for Singing Voice in Pop Music
• Self-Supervised Learning for Visual Summary Identification in Scientific Publications
• Highly Accelerated Multishot EPI through Synergistic Machine Learning and Joint Reconstruction
• Continuous Speech Recognition using EEG and Video
• A New Artificial Neuron Proposal with Trainable Simultaneous Local and Global Activation Function
• Motion-Based Handwriting Recognition and Word Reconstruction
• A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks
• Training Image Selection using Recurrent Neural Networks: An Application in Hydrogeology
• Options Discovery with Budgeted Reinforcement Learning
• GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning
• Distribution Preserving Source Separation With Time Frequency Predictive Models
• Unsupervised Data Selection for Supervised Learning
• Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting
• Deep Preset: Blending and Retouching Photos with Color Style Transfer
• Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training
• ChainNet: Neural Network-Based Successive Spectral Analysis
• TAG: Task-based Accumulated Gradients for Lifelong learning
• EXoN: EXplainable encoder Network
• Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods
• Regularizing Explanations in Bayesian Convolutional Neural Networks
• Domain-adaptive Fall Detection Using Deep Adversarial Training
• Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery
• Exploiting Group-level Behavior Pattern forSession-based Recommendation
• Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
• Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
• Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention
• Apply Artificial Neural Network to Solving Manpower Scheduling Problem
• MTNet: A Multi-Task Neural Network for On-Field Calibration of Low-Cost Air Monitoring Sensors
• Parameter-free Gradient Temporal Difference Learning
• Visual Perspective Taking for Opponent Behavior Modeling
• Benchmarking down-scaled (not so large) pre-trained language models
• CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changes
• Interval Deep Learning for Uncertainty Quantification in Safety Applications
• Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study
• Exploiting Aliasing for Manga Restoration
• Partitioned Deep Learning of Fluid-Structure Interaction
• SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising
• Ant Colony Inspired Machine Learning Algorithm for Identifying and Emulating Virtual Sensors
• Permutation invariance and uncertainty in multitemporal image super-resolution
• Predictions For Pre-training Language Models
• EWareNet: Emotion Aware Human Intent Prediction and Adaptive Spatial Profile Fusion for Social Robot Navigation
• N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
• KL Guided Domain Adaptation
• MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
• Quality-Aware Network for Face Parsing
• Input Invex Neural Network
• Variational Laplace for Bayesian neural networks
• Audiovisual transfer learning for audio tagging and sound event detection
• Self-Supervision is All You Need for Solving Rubik's Cube
• Continuous representations of intents for dialogue systems
• A variational approximate posterior for the deep Wishart process
• Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans
• Co-embedding of Nodes and Edges with Graph Neural Networks
• Recurrent Neural Based Electricity Load Forecasting of G-20 Members
• Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting
• Data-driven modeling of time-domain induced polarization
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• Learning to Summarize Long Texts with Memory Compression and Transfer
• Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
• Dense Dual-Path Network for Real-time Semantic Segmentation
• Adaptive Gradient Method with Resilience and Momentum
• When should agents explore?
• Explorable Tone Mapping Operators
• Unsupervised Local Discrimination for Medical Images
• GAMesh: Guided and Augmented Meshing for Deep Point Networks
• Imitation with Neural Density Models
• A Unified Model for Recommendation with Selective Neighborhood Modeling
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
• Deep Dive into Semi-Supervised ELBO for Improving Classification Performance
• Adaptive Gradient Descent Methods for Computing Implied Volatility
• Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data
• GoPRONTO: a Feedback-based Framework for Nonlinear Optimal Control
• Generating Diverse Translation from Model Distribution with Dropout
• Predicting Census Survey Response Rates With Parsimonious Additive Models and Structured Interactions
• Fixed-Length Protein Embeddings using Contextual Lenses
• RNN Training along Locally Optimal Trajectories via Frank-Wolfe Algorithm
• Learning Propagation Rules for Attribution Map Generation
• Attacks against Ranking Algorithms with Text Embeddings: a Case Study on Recruitment Algorithms
• Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds
• Variational embedding of protein folding simulations using gaussian mixture variational autoencoders
• Predicting Clinical Trial Results by Implicit Evidence Integration
• Using a Neural Network Classifier to Select Galaxies with the Most Accurate Photometric Redshifts
• Controllable Multi-Character Psychology-Oriented Story Generation
• Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings
• Converting the Point of View of Messages Spoken to Virtual Assistants
• Large Product Key Memory for Pretrained Language Models
• Improving Multilingual Translation by Representation and Gradient Regularization
• Neighbourhood Distillation: On the benefits of non end-to-end distillation
• CD-UAP: Class Discriminative Universal Adversarial Perturbation
• Learning to Superoptimize Real-world Programs
• STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++
• IGLU: Efficient GCN Training via Lazy Updates
• Predicting Classification Accuracy When Adding New Unobserved Classes
• Optimizing Quantum Variational Circuits with Deep Reinforcement Learning
• Learning to Actively Learn: A Robust Approach
• GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
• MCMC-Interactive Variational Inference
• Identifying partial mouse brain microscopy images from Allen reference atlas using a contrastively learned semantic space
• Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
• A Framework to Learn with Interpretation
• Visibility Optimization for Surveillance-Evasion Games
• POAR: Efficient Policy Optimization via Online Abstract State Representation Learning
• Dual Correction Strategy for Ranking Distillation in Top-N Recommender System
• Analogical and Relational Reasoning with Spiking Neural Networks
• Capturing Structural Locality in Non-parametric Language Models
• Explainability-Aware One Point Attack for Point Cloud Neural Networks
• Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
• STN4DST: A Scalable Dialogue State Tracking based on Slot Tagging Navigation
• Learning disentangled representation for classical models
• Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
• Graph Representation Learning for Spatial Image Steganalysis
• Towards Low-Resource StarGAN Voice Conversion using Weight Adaptive Instance Normalization
• Fast learning from label proportions with small bags
• Batch size-invariance for policy optimization
• Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks
• Mining for Potent Inhibitors through Artificial Intelligence and Physics: A Unified Methodology for Ligand Based and Structure Based Drug Design
• Physics-Informed Deep Learning Characterizes Morphodynamics of Asian Soybean Rust Disease
• GSEP: A robust vocal and accompaniment separation system using gated CBHG module and loudness normalization
• Data-Based Models for Hurricane Evolution Prediction: A Deep Learning Approach
• Reducing the Long Tail Losses in Scientific Emulations with Active Learning
• Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances
• StylePart: Image-based Shape Part Manipulation
• FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond
• Improving the Perceptual Quality of 2D Animation Interpolation
• A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
• Piece-wise Matching Layer in Representation Learning for ECG Classification
• Pedestrian Detection by Exemplar-Guided Contrastive Learning
• MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing
• Solving time-dependent parametric PDEs by multiclass classification-based reduced order model
• A transfer learning based approach for pronunciation scoring
• PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding
• Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
• Improving Graph Property Prediction with Generalized Readout Functions
• Discovering Latent Representations of Relations for Interacting Systems
• Learning Term Weights for Ad-hoc Retrieval
• Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
• Meta-Forecasting by combining Global Deep Representations with Local Adaptation
• iWash: A Smartwatch Handwashing Quality Assessment and Reminder System with Real-time Feedback in the Context of Infectious Disease
• Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation
• QK Iteration: A Self-Supervised Representation Learning Algorithm for Image Similarity
• Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• STAN: Synthetic Network Traffic Generation with Generative Neural Models
• Towards Generating Real-World Time Series Data
• Learning Provably Robust Motion Planners Using Funnel Libraries
• Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures
• Training neural networks with synthetic electrocardiograms
• An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment Analysis
• Full-Body Visual Self-Modeling of Robot Morphologies
• Invexifying Regularization of Non-Linear Least-Squares Problems
• Label-Based Diversity Measure Among Hidden Units of Deep Neural Networks: A Regularization Method
• The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line
• Variance Reduction in Deep Learning: More Momentum is All You Need
• ReGroup: Recursive Neural Networks for Hierarchical Grouping of Vector Graphic Primitives
• Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
• Event-level variables for semivisible jets using anomalous jet tagging
• Phenomenological classification of the Zwicky Transient Facility astronomical event alerts
• Meta Mask Correction for Nuclei Segmentation in Histopathological Image
• FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding
• Action based Network for Conversation Question Reformulation
• Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks
• Impact of Three-Dimensional Video Scalability on Multi-View Activity Recognition using Deep Learning
• Molecular Attributes Transfer from Non-Parallel Data
• E(2) Equivariant Self-Attention for Radio Astronomy
• Unsupervised Domain Adaptation: A Reality Check
• A benchmark with decomposed distribution shifts for 360 monocular depth estimation
• Deep Measurement Updates for Bayes Filters
• Camera Motion Agnostic 3D Human Pose Estimation
• Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours
• Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
• Deep Learning for Constrained Utility Maximisation
• A Functional Perspective on Learning Symmetric Functions with Neural Networks
• Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation
• Interactive Imitation Learning in State-Space
• Evolving Differentiable Gene Regulatory Networks
• Neuroevolutionary Feature Representations for Causal Inference
• 1-Point RANSAC-Based Method for Ground Object Pose Estimation
• Error Autocorrelation Objective Function for Improved System Modeling
• Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP
• E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
• DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning
• From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*
• Tensor Decompositions for Count Data that Leverage Stochastic and Deterministic Optimization
• Spectrum and Prosody Conversion for Cross-lingual Voice Conversion with CycleGAN
• Training robust anomaly detection using ML-Enhanced simulations
• Source-Aware Neural Speech Coding for Noisy Speech Compression
• Learning to Actively Reduce Memory Requirements for Robot Control Tasks
• Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity
• Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
• Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors
• Comparative Snippet Generation
• Differentiable Projection from Optical Coherence Tomography B-Scan without Retinal Layer Segmentation Supervision
• Water Quality Prediction on a Sigfox-compliant IoT Device: The Road Ahead of WaterS
• Deep learning for gradient flows using the Brezis-Ekeland principle
• GL-BLSTM: a novel structure of bidirectional long-short term memory for disulfide bonding state prediction
• Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning
• Identifying latent distances with Finslerian geometry
• Supervised machine learning techniques for data matching based on similarity metrics
• Energy-Based Spherical Sparse Coding
• Joint cortical registration of geometry and function using semi-supervised learning
• Explaining Fast Improvement in Online Imitation Learning
• Solving morphological analogies: from retrieval to generation
• Context Normalization Layer with Applications
• Network of Recurrent Neural Networks
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Synthetic-to-Real Domain Adaptation for Lane Detection
• Fisher Auto-Encoders
• Approximation Based Variance Reduction for Reparameterization Gradients
• Rethinking PointNet Embedding for Faster and Compact Model
• Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning
• Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches
• Least-Squares Neural Network (LSNN) Method For Linear Advection-Reaction Equation: Non-constant Jumps
• Deep Learning Meets SAR
• Context selectivity with dynamic availability enables lifelong continual learning
• The Limits to Learning a Diffusion Model
• Deep Learning in Target Space
• Neural Bradley-Terry Rating: Quantifying Properties from Comparisons
• Where Did the President Visit Last Week? Detecting Celebrity Trips from News Articles
• Semantic-driven Colorization
• A pre-training deep learning method for simulating the large bending deformation of bilayer plates
• Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization
• A general framework for defining and optimizing robustness
• An optimal transport approach for the multiple quantile hedging problem
• Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning
• Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
• STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
• Logical Team Q-learning: An approach towards factored policies in cooperative MARL
• Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods
• Can neural networks count digit frequency?
• Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks
• Boosting Summarization with Normalizing Flows and Aggressive Training
• Reconstruction of electromagnetic showers in calorimeters using Deep Learning
• Towards Faster k-Nearest-Neighbor Machine Translation
• Patient-Adaptive and Learned MRI Data Undersampling Using Neighborhood Clustering
• GDN: A Stacking Network Used for Skin Cancer Diagnosis
• Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
• Traffic Load Prediction and Power Consumption Reduction for Multi-band Networks
• Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects
• Multi-view user representation learning for user matching without personal information
• Searches for Compact Binary Coalescence Events Using Neural Networks in LIGO/Virgo Third Observation Period
• One of these (Few) Things is Not Like the Others
• On-device Filtering of Social Media Images for Efficient Storage
• Minimum Description Feature Selection for Complexity Reduction in Machine Learning-based Wireless Positioning
• Normalized Convolutional Neural Network
• Tamed Warping Network for High-Resolution Semantic Video Segmentation
• Regex Queries over Incomplete Knowledge Bases
• Unveiling the Potential: Harnessing Deep Metric Learning to Circumvent Video Streaming Encryption
• Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection
• DDU-Net: A Domain Decomposition-Based CNN for High-Resolution Image Segmentation on Multiple GPUs
• Sines, Transient, Noise Neural Modeling of Piano Notes
• Residual Neural Networks for Digital Predistortion
• Towards Robustness against Unsuspicious Adversarial Examples
• Verifiable cloud-based variational quantum algorithms
• Siamese networks for Poincaré embeddings and the reconstruction of evolutionary trees
• Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?
• Pruned Wasserstein Index Generation Model and wigpy Package
• Assessing the impact of external factors on the occurrence of emergencies
• Corpus-level and Concept-based Explanations for Interpretable Document Classification
• CRISP: A Framework for Cryo-EM Image Segmentation and Processing with Conditional Random Field
• Learning neural trans-dimensional random field language models with noise-contrastive estimation
• Simple Multi-Resolution Representation Learning for Human Pose Estimation
• An Efficient Agreement Mechanism in CapsNets By Pairwise Product
• Joint Embedding of Words and Category Labels for Hierarchical Multi-label Text Classification
• Transforming physics-informed machine learning to convex optimization
• Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
• Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning
• Characterizing Online Criticism of Partisan News Media Using Weakly Supervised Learning
• Modeling turbulent and self-gravitating fluids with Fourier neural operators
• Analysis of the Compaction Behavior of Textile Reinforcements in Low-Resolution In-Situ CT Scans via Machine-Learning and Descriptor-Based Methods
• Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method
• Exploring the variational method for thermodynamic models
• Enhanced Rolling Horizon Evolution Algorithm with Opponent Model Learning: Results for the Fighting Game AI Competition
• SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency
• Exploration in Action Space
• Efficient attention guided 5G power amplifier digital predistortion
• OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis
• Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care
• Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision
• Differentially Private Synthetic Data Release for Topics API Outputs
• Unsupervised Deep Learning for MR Angiography with Flexible Temporal Resolution
• PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes
• Coping With Simulators That Don't Always Return
• CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images
• P $\approx$ NP, at least in Visual Question Answering
• Improving $t\bar{t}$ reconstruction in the dilepton channel at future lepton colliders
• Dividing Deep Learning Model for Continuous Anomaly Detection of Inconsistent ICT Systems
• High-Dimensional Data Set Simplification by Laplace-Beltrami Operator
• Over-the-Air Multi-Sensor Inference with Neural Networks Using Memristor-Based Analog Computing
• Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks
• Interpretable Multimodal Out-of-context Detection with Soft Logic Regularization
• Statistical Models of Top-$k$ Partial Orders
• Quality Control of Neuron Reconstruction Based on Deep Learning
• A Content Transformation Block For Image Style Transfer
• Synthesizing human-like sketches from natural images using a conditional convolutional decoder
• DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
• Label-free Monitoring of Self-Supervised Learning Progress
• Investigating Semi-Supervised Learning Algorithms in Text Datasets
• Discretization-Dependent Dissolution of (Dis)Continuous Gliders: Non-Platonic Self-Organization in Complex Systems
• An Explicit Scheme for Pathwise XVA Computations
• Computationally efficient cardiac views projection using 3D Convolutional Neural Networks
• The Variational InfoMax Learning Objective
• Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information
• MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network
• mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization
• Flexible numerical optimization with ensmallen
• Complete and separate: Conditional separation with missing target source attribute completion
• Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction
• Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction
• RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation
• Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning
• FDLS: A Deep Learning Approach to Production Quality, Controllable, and Retargetable Facial Performances
• Image Cropping under Design Constraints
• Unlocking Metasurface Practicality for B5G Networks: AI-assisted RIS Planning
• TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
• Outlier Detection Using Generative Models with Theoretical Performance Guarantees
• A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
• Co-Training Realized Volatility Prediction Model with Neural Distributional Transformation
• An EEG-based Image Annotation System
• ScopeIt: Scoping Task Relevant Sentences in Documents
• Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights
• Machine Learning for Nanohertz Gravitational Wave Detection and Parameter Estimation with Pulsar Timing Array
• Corella: A Private Multi Server Learning Approach based on Correlated Queries
• Prediction with Spatio-temporal Point Processes with Self Organizing Decision Trees
• Multi-modal Dense Video Captioning
• Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
• Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
• Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?
• Gradient scarcity with Bilevel Optimization for Graph Learning
• UNGOML: Automated Classification of unsafe Usages in Go
• Riemannian Laplace approximations for Bayesian neural networks
• Criteria for the numerical constant recognition
• EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation
• T-Net: Learning Feature Representation with Task-specific Supervision for Biomedical Image Analysis
• AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query
• ARMA Nets: Expanding Receptive Field for Dense Prediction
• Test-Time Adaptation with Principal Component Analysis
• Will there be a construction? Predicting road constructions based on heterogeneous spatiotemporal data
• Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
• Sparse tree-based initialization for neural networks
• Training with Streaming Annotation
• Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors
• Network Pruning via Annealing and Direct Sparsity Control
• Multi-Task Neural Processes
• How BPE Affects Memorization in Transformers
• Towards Robust and Automatic Hyper-Parameter Tunning
• Docking-based Virtual Screening with Multi-Task Learning
• Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive Convolution
• DSNet: Dynamic Skin Deformation Prediction by Recurrent Neural Network
• Reducing the Representation Error of GAN Image Priors Using the Deep Decoder
• Learning spatial hearing via innate mechanisms
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• Learning in Sparse Rewards settings through Quality-Diversity algorithms
• Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling
• Deep Learning Enabled Real-Time Photoacoustic Tomography System via Single Data Acquisition Channel
• An Application to Generate Style Guided Compatible Outfit
• Direct optimization of BPX preconditioners
• Improving AMD diagnosis by the simultaneous identification of associated retinal lesions
• Shared and Private VAEs with Generative Replay for Continual Learning
• Trust Region Method for Coupled Systems of PDE Solvers and Deep Neural Networks
• Autoencoding Undirected Molecular Graphs With Neural Networks
• Font Style that Fits an Image -- Font Generation Based on Image Context
• Weakly Supervised Visual Semantic Parsing
• Balancing Robustness and Sensitivity using Feature Contrastive Learning
• CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues
• Modelling DVFS and UFS for Region-Based Energy Aware Tuning of HPC Applications
• HRFA: High-Resolution Feature-based Attack
• Nonlinear Hawkes Process with Gaussian Process Self Effects
• Towards Automatic Sizing for PPE with a Point Cloud Based Variational Autoencoder
• Automated Knee X-ray Report Generation
• Estimating the Uncertainty of Neural Network Forecasts for Influenza Prevalence Using Web Search Activity
• Unsupervised Part Segmentation through Disentangling Appearance and Shape
• FINNger -- Applying artificial intelligence to ease math learning for children
• Symmetry-driven graph neural networks
• Learning to Extend Program Graphs to Work-in-Progress Code
• Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation
• Visualizing Representations of Adversarially Perturbed Inputs
• Depth Assisted Full Resolution Network for Single Image-based View Synthesis
• Neural Mode Jump Monte Carlo
• Learning Graphon Autoencoders for Generative Graph Modeling
• SyReNets: Symbolic Residual Neural Networks
• Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
• Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
• DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation
• Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
• Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels
• Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling
• On the Generative Utility of Cyclic Conditionals
• Dynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes
• belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification
• DNA-GCN: Graph convolutional networks for predicting DNA-protein binding
• Drivers' Manoeuvre Modelling and Prediction for Safe HRI
• Neural Architecture Search via Bregman Iterations
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
• Exploring Adversarial Learning for Deep Semi-Supervised Facial Action Unit Recognition
• Visual Reaction: Learning to Play Catch with Your Drone
• Interferometric Graph Transform for Community Labeling
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
• Lightweight Dual-channel Target Speaker Separation for Mobile Voice Communication
• Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories
• Automation for Interpretable Machine Learning Through a Comparison of Loss Functions to Regularisers
• Improving Social Welfare While Preserving Autonomy via a Pareto Mediator
• \emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks
• Automatically Differentiable Random Coefficient Logistic Demand Estimation
• Spatio-Temporal Dual-Stream Neural Network for Sequential Whole-Body PET Segmentation
• Recovering AES Keys with a Deep Cold Boot Attack
• Generative Memorize-Then-Recall framework for low bit-rate Surveillance Video Compression
• Timestamping Documents and Beliefs
• Structure-Regularized Attention for Deformable Object Representation
• Sample Drop Detection for Distant-speech Recognition with Asynchronous Devices Distributed in Space
• Pressure-Informed Velocity Estimation in a Subsonic Jet
• Conditionally Learn to Pay Attention for Sequential Visual Task
• RCURRENCY: Live Digital Asset Trading Using a Recurrent Neural Network-based Forecasting System
• Nearest Neighbor Sampling of Point Sets using Rays
• Learning-Aided Heuristics Design for Storage System
• Sparsely Activated Networks: A new method for decomposing and compressing data
• A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
• Learning to Generalize to Unseen Tasks with Bilevel Optimization
• Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
• DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions
• Detection of Consonant Errors in Disordered Speech Based on Consonant-vowel Segment Embedding
• Multi-scale Neural ODEs for 3D Medical Image Registration
• Aging Memories Generate More Fluent Dialogue Responses with Memory Augmented Neural Networks
• Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes
• Training or Architecture? How to Incorporate Invariance in Neural Networks
• JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
• Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
• Attack to Fool and Explain Deep Networks
• Data Optimisation for a Deep Learning Recommender System
• ADCC: An Effective and Intelligent Attention Dense Color Constancy System for Studying Images in Smart Cities
• Graph Routing between Capsules
• Mutual-Information Based Few-Shot Classification
• Nonlinear Matrix Approximation with Radial Basis Function Components
• Feature Completion for Occluded Person Re-Identification
• MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
• Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
• Deep Clustering of Compressed Variational Embeddings
• OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems
• Prediction of Hereditary Cancers Using Neural Networks
• Power Law Graph Transformer for Machine Translation and Representation Learning
• Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
• Poisoning the Search Space in Neural Architecture Search
• Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder
• Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech
• Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit
• Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis
• Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs
• Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification
• Towards Utilitarian Combinatorial Assignment with Deep Neural Networks and Heuristic Algorithms
• Multi-task Learning with Cross Attention for Keyword Spotting
• TargetNet: Functional microRNA Target Prediction with Deep Neural Networks
• WisdomNet: Prognosis of COVID-19 with Slender Prospect of False Negative Cases and Vaticinating the Probability of Maturation to ARDS using Posteroanterior Chest X-Rays
• Scene-aware Learning Network for Radar Object Detection
• Sentence-level Online Handwritten Chinese Character Recognition
• Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
• Form2Seq : A Framework for Higher-Order Form Structure Extraction
• Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
• Fast Portrait Segmentation with Highly Light-weight Network
• STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction
• AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data
• Detection of Abnormal Behavior with Self-Supervised Gaze Estimation
• End-to-end Ultrasound Frame to Volume Registration
• Interpreting Criminal Charge Prediction and Its Algorithmic Bias via Quantum-Inspired Complex Valued Networks
• Multi-Channel Auto-Encoders and a Novel Dataset for Learning Domain Invariant Representations of Histopathology Images
• Surgical Instruction Generation with Transformers
• Self Training with Ensemble of Teacher Models
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• Residual Tree Aggregation of Layers for Neural Machine Translation
• Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
• High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm
• CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots
• Memorization in Deep Neural Networks: Does the Loss Function matter?
• Generative Dialog Policy for Task-oriented Dialog Systems
• 3D Deep Affine-Invariant Shape Learning for Brain MR Image Segmentation
• Deep equal risk pricing of financial derivatives with non-translation invariant risk measures
• Wavelet Design in a Learning Framework
• Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel
• Constellation: Learning relational abstractions over objects for compositional imagination
• Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs
• $360^o$ Surface Regression with a Hyper-Sphere Loss
• FLAG n' FLARE: Fast Linearly-Coupled Adaptive Gradient Methods
• Neural Differential Equations for Inverse Modeling in Model Combustors
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• A deep learning-based method for relative location prediction in CT scan images
• Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems
• Ranker-agnostic Contextual Position Bias Estimation
• Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System
• Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings
• Recognizing Emotions evoked by Movies using Multitask Learning
• Unsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo Multilabel
• Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation
• Structured DropConnect for Uncertainty Inference in Image Classification
• Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents
• The Properties of Average Gradient in Local Region
• Bidirectional Long Short-Term Memory (BLSTM) neural networks for reconstruction of top-quark pair decay kinematics
• Semantic Segmentation of Panoramic Images Using a Synthetic Dataset
• The Bias-Variance Tradeoff of Doubly Robust Estimator with Targeted $L_1$ regularized Neural Networks Predictions
• Subword Language Model for Query Auto-Completion
• A Dynamic Head Importance Computation Mechanism for Neural Machine Translation
• Efficient Hardware Realizations of Feedforward Artificial Neural Networks
• Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D
• Decoupled Transformer for Scalable Inference in Open-domain Question Answering
• SLoClas: A Database for Joint Sound Localization and Classification
• Fully Neural Network Mode Based Intra Prediction of Variable Block Size
• Neural Twins Talk & Alternative Calculations
• Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio Sequences
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• One-Shot Object Affordance Detection in the Wild
• Saliency-Associated Object Tracking
• COVID-view: Diagnosis of COVID-19 using Chest CT
• Fully Hyperbolic Graph Convolution Network for Recommendation
• Road Mapping and Localization using Sparse Semantic Visual Features
• The Contextual Appointment Scheduling Problem
• Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding
• Structured Outdoor Architecture Reconstruction by Exploration and Classification
• Learning to Search for MIMO Detection
• Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
• Predicting Vehicles' Longitudinal Trajectories and Lane Changes on Highway On-Ramps
• Adaptation-Agnostic Meta-Training
• TransSent: Towards Generation of Structured Sentences with Discourse Marker
• Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
• Learning to Give Checkable Answers with Prover-Verifier Games
• Scalable Kernel Learning via the Discriminant Information
• Multi-Channel Transformer Transducer for Speech Recognition
• Don't cross that stop line: Characterizing Traffic Violations in Metropolitan Cities
• Communication-Computation Efficient Device-Edge Co-Inference via AutoML
• Agon: A Scalable Competitive Scheduler for Large Heterogeneous Systems
• Edge-featured Graph Neural Architecture Search
• Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment
• Frustratingly Simple Pretraining Alternatives to Masked Language Modeling
• A Discriminative Neural Model for Cross-Lingual Word Alignment
• Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network
• Learning with Noisy Labels for Sentence-level Sentiment Classification
• Intelligent Motion Planning for a Cost-effective Object Follower Mobile Robotic System with Obstacle Avoidance
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows
• On Second-order Optimization Methods for Federated Learning
• Context Aware Road-user Importance Estimation (iCARE)
• Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
• Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning
• Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
• Feature Selection on Thermal-stress Dataset
• Deriving Explanation of Deep Visual Saliency Models
• Stationary Density Estimation of Itô Diffusions Using Deep Learning
• Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset
• Machine-learning enables Image Reconstruction and Classification in a "see-through" camera
• An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment
• Panoptic Narrative Grounding
• Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
• Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds
• Image Colorization By Capsule Networks
• Task-adaptive Pre-training of Language Models with Word Embedding Regularization
• reproducing "ner and pos when nothing is capitalized"
• DEM Super-Resolution with EfficientNetV2
• Deep Bayesian Estimation for Dynamic Treatment Regimes with a Long Follow-up Time
• Context-aware Tree-based Deep Model for Recommender Systems
• Adversarial Networks for Prostate Cancer Detection
• Spatial Information Refinement for Chroma Intra Prediction in Video Coding
• A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification
• Recognizing Part Attributes with Insufficient Data
• Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation
• Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
• Training Automatic View Planner for Cardiac MR Imaging via Self-Supervision by Spatial Relationship between Views
• An embarrassingly simple comparison of machine learning algorithms for indoor scene classification
• Unconstrained Foreground Object Search
• Bayesian deep learning of affordances from RGB images
• ReINTEL Challenge 2020: A Comparative Study of Hybrid Deep Neural Network for Reliable Intelligence Identification on Vietnamese SNSs
• Instance-Based Neural Dependency Parsing
• Dynamic Regret Analysis for Online Meta-Learning
• Is artificial data useful for biomedical Natural Language Processing algorithms?
• Adaptive Weight Decay for Deep Neural Networks
• Deep Embedded K-Means Clustering
• Q-Net: A Quantitative Susceptibility Mapping-based Deep Neural Network for Differential Diagnosis of Brain Iron Deposition in Hemochromatosis
• Unsupervised Learning of Depth and Deep Representation for Visual Odometry from Monocular Videos in a Metric Space
• Fast Line Search for Multi-Task Learning
• Optimizing Neural Network for Computer Vision task in Edge Device
• Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages
• Classification of entities via their descriptive sentences
• Revisiting SVD to generate powerful Node Embeddings for Recommendation Systems
• Disentangling deep neural networks with rectified linear units using duality
• No-Press Diplomacy from Scratch
• Meta Internal Learning
• Pacer: Comprehensive Network Side-Channel Mitigation in the Cloud
• Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
• Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model
• Self-Supervised 3D Face Reconstruction via Conditional Estimation
• Fitting large mixture models using stochastic component selection
• Multi-task Learning for Low-resource Second Language Acquisition Modeling
• Controllable Recommenders using Deep Generative Models and Disentanglement
• Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition
• Hiding Images into Images with Real-world Robustness
• Hyperlink Regression via Bregman Divergence
• Learning Stable Koopman Embeddings
• NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
• MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
• Body Part Regression for CT Images
• Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory
• Who calls the shots? Rethinking Few-Shot Learning for Audio
• Sk-Unet Model with Fourier Domain for Mitosis Detection
• Center Loss Regularization for Continual Learning
• Bayesian Meta-Learning Through Variational Gaussian Processes
• PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation
• Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
• Generative Residual Attention Network for Disease Detection
• SgSum: Transforming Multi-document Summarization into Sub-graph Selection
• Deep Kernel Learning for Clustering
• Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
• A Closer Look at Reference Learning for Fourier Phase Retrieval
• The Value of Information When Deciding What to Learn
• Few-Shot Meta-Denoising
• Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation
• Multilayer Lookahead: a Nested Version of Lookahead
• Dream to Explore: Adaptive Simulations for Autonomous Systems
• Entropy-based adaptive Hamiltonian Monte Carlo
• How to boost autoencoders?
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning
• SVGD: A Virtual Gradients Descent Method for Stochastic Optimization
• Relevance Proximity Graphs for Fast Relevance Retrieval
• MSnet: A BERT-based Network for Gendered Pronoun Resolution
• Aligned Multi-Task Gaussian Process
• Deep Keyphrase Completion
• Adaptive Hierarchical Similarity Metric Learning with Noisy Labels
• PIE: Pseudo-Invertible Encoder
• Transfer Learning with Binary Neural Networks
• Safe Augmentation: Learning Task-Specific Transformations from Data
• Silhouette Guided Point Cloud Reconstruction beyond Occlusion
• Self-Verification in Image Denoising
• Scalable Object Detection for Stylized Objects
• Zero-Shot Translation using Diffusion Models
• Deep Learning for CSI Feedback Based on Superimposed Coding
• Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation
• Unsupervised Learning Framework of Interest Point Via Properties Optimization
• Semantic Deep Intermodal Feature Transfer: Transferring Feature Descriptors Between Imaging Modalities
• Cross Attention Network for Semantic Segmentation
• A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation
• Bootstrap Your Object Detector via Mixed Training
• Context-Aware Transformer Transducer for Speech Recognition
• High-order joint embedding for multi-level link prediction
• Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets
• Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation
• Efficient estimates of optimal transport via low-dimensional embeddings
• Dynamic Parameterized Network for CTR Prediction
• Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification
• Deep generative factorization for speech signal
• Embedding Dynamic Attributed Networks by Modeling the Evolution Processes
• UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models
• On The Convergence of First Order Methods for Quasar-Convex Optimization
• Autoregressive Knowledge Distillation through Imitation Learning
• Ink Marker Segmentation in Histopathology Images Using Deep Learning
• LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks
• DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
• CR-Fill: Generative Image Inpainting with Auxiliary Contexutal Reconstruction
• Facial Keypoint Sequence Generation from Audio
• MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis
• Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition
• Semi-supervised Autoencoding Projective Dependency Parsing
• Asynchronous Parallel Stochastic Quasi-Newton Methods
• DeepDrawing: A Deep Learning Approach to Graph Drawing
• Decoupling entrainment from consistency using deep neural networks
• Cross-lingual Word Embeddings beyond Zero-shot Machine Translation
• Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features
• Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization
• Human-Like Active Learning: Machines Simulating the Human Learning Process
• Set Augmented Triplet Loss for Video Person Re-Identification
• Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
• Two-Stream Appearance Transfer Network for Person Image Generation
• Localising In Complex Scenes Using Balanced Adversarial Adaptation
• CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling
• Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model
• Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion
• E.T.: Entity-Transformers. Coreference augmented Neural Language Model for richer mention representations via Entity-Transformer blocks
• A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
• Fact Checking via Path Embedding and Aggregation
• Manual-Label Free 3D Detection via An Open-Source Simulator
• Adaptive Future Frame Prediction with Ensemble Network
• FPAENet: Pneumonia Detection Network Based on Feature Pyramid Attention Enhancement
• Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing
• Pixel-wise Dense Detector for Image Inpainting
• Transducer Adaptive Ultrasound Volume Reconstruction
• Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet Vocoder
• Per-Pixel Feedback for improving Semantic Segmentation
• We don't Need Thousand Proposals$:$ Single Shot Actor-Action Detection in Videos
• Image Score: How to Select Useful Samples
• Adversarial Refinement Network for Human Motion Prediction
• User-Device Authentication in Mobile Banking using APHEN for Paratuck2 Tensor Decomposition
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning
• Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning
• Better Knowledge Retention through Metric Learning
• Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping
• Unsupervised Depth Completion from Visual Inertial Odometry
• TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
• Accelerating Distributed SGD for Linear Regression using Iterative Pre-Conditioning
• Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies
• Maximin Optimization for Binary Regression
• Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample
• Non-autoregressive electron flow generation for reaction prediction
• Cross-Correlation Based Discriminant Criterion for Channel Selection in Motor Imagery BCI Systems
• Depth estimation on embedded computers for robot swarms in forest
• What Makes a Star Teacher? A Hierarchical BERT Model for Evaluating Teacher's Performance in Online Education
• Conditional Generative Adversarial Networks for Optimal Path Planning
• Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
• Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
• Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
• SpotTune: Leveraging Transient Resources for Cost-efficient Hyper-parameter Tuning in the Public Cloud
• Fine-scale Surface Normal Estimation using a Single NIR Image
• Meta Learning-based MIMO Detectors: Design, Simulation, and Experimental Test
• Data-driven Algorithm Selection and Parameter Tuning: Two Case studies in Optimization and Signal Processing
• Multiscale Phase Retrieval
• Vision-based Price Suggestion for Online Second-hand Items
• Price Suggestion for Online Second-hand Items with Texts and Images
• TADO: Time-varying Attention with Dual-Optimizer Model
• Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints
• Human Pose Transfer by Adaptive Hierarchical Deformation
• FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems
• Time-Aware Tensor Decomposition for Missing Entry Prediction
• Understood in Translation, Transformers for Domain Understanding
• Regularized Attentive Capsule Network for Overlapped Relation Extraction
• End-to-end Learning from Spectrum Data: A Deep Learning approach for Wireless Signal Identification in Spectrum Monitoring applications
• Uncertainty-Aware Label Refinement for Sequence Labeling
• Learning to Localize Through Compressed Binary Maps
• Multi-Faceted Representation Learning with Hybrid Architecture for Time Series Classification
• EmotionGIF-IITP-AINLPML: Ensemble-based Automated Deep Neural System for predicting category(ies) of a GIF response
• Vehicle Re-identification Based on Dual Distance Center Loss
• LO-Net: Deep Real-time Lidar Odometry
• Stochastic Action Prediction for Imitation Learning
• Scene Text Detection for Augmented Reality -- Character Bigram Approach to reduce False Positive Rate
• Multi-Instance Aware Localization for End-to-End Imitation Learning
• Generalized Categorisation of Digital Pathology Whole Image Slides using Unsupervised Learning
• Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network
• NeuralMagicEye: Learning to See and Understand the Scene Behind an Autostereogram
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Video Captioning in Compressed Video
• A Tutorial on the Mathematical Model of Single Cell Variational Inference
• Exploiting Deep Learning for Secure Transmission in an Underlay Cognitive Radio Network
• Novel View Synthesis via Depth-guided Skip Connections
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• Learning to Segment Rigid Motions from Two Frames
• Neural News Recommendation with Negative Feedback
• CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy
• A Novel Cluster Classify Regress Model Predictive Controller Formulation; CCR-MPC
• AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy
• Continuous Multi-objective Zero-touch Network Slicing via Twin Delayed DDPG and OpenAI Gym
• Understanding in Artificial Intelligence
• Joint Perception and Control as Inference with an Object-based Implementation
• Narration Generation for Cartoon Videos
• Mitigating the Position Bias of Transformer Models in Passage Re-Ranking
• Non-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving
• TATi-Thermodynamic Analytics ToolkIt: TensorFlow-based software for posterior sampling in machine learning applications
• Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS
• Improving the Certified Robustness of Neural Networks via Consistency Regularization
• Bridging the gap between Human Action Recognition and Online Action Detection
• Model-based Policy Search for Partially Measurable Systems
• Crowding in humans is unlike that in convolutional neural networks
• "Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
• Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution
• Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series
• Few-Shot Semantic Parsing for New Predicates
• Variational Information Bottleneck Model for Accurate Indoor Position Recognition
• Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia
• Intelligent Frame Selection as a Privacy-Friendlier Alternative to Face Recognition
• Microwave Tomography with phaseless data on the calcaneus by means of artificial neural networks
• GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention
• SNR-adaptive deep joint source-channel coding for wireless image transmission
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder
• Alternating Synthetic and Real Gradients for Neural Language Modeling
• Hawkes Processes on Graphons
• Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling
• Model-Augmented Q-learning
• A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
• A Deep Learning-Based Approach to Extracting Periosteal and Endosteal Contours of Proximal Femur in Quantitative CT Images
• Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
• Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
• An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels
• Concept Formation and Dynamics of Repeated Inference in Deep Generative Models
• Structural Information Preserving for Graph-to-Text Generation
• Learning deep multiresolution representations for pansharpening
• Dynamic Virtual Graph Significance Networks for Predicting Influenza
• Meta-Path-Free Representation Learning on Heterogeneous Networks
• Twin Augmented Architectures for Robust Classification of COVID-19 Chest X-Ray Images
• Weakly-supervised multi-class object localization using only object counts as labels
• Dual-Path Modeling for Long Recording Speech Separation in Meetings
• IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
• Continuous Face Aging Generative Adversarial Networks
• Achieving Competitive Play Through Bottom-Up Approach in Semantic Segmentation
• Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection
• Modeling Multi-Destination Trips with Sketch-Based Model
• Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction
• Training artificial neural networks for precision orientation and strain mapping using 4D electron diffraction datasets
• Deep Transfer Learning for WiFi Localization
• Approximate Optimal Filter for Linear Gaussian Time-invariant Systems
• Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting
• A Multi-resolution Approach to Expression Recognition in the Wild
• Montage based 3D Medical Image Retrieval from Traumatic Brain Injury Cohort using Deep Convolutional Neural Network
• Self-Learning for Zero Shot Neural Machine Translation
• PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data
• Gated Attentive-Autoencoder for Content-Aware Recommendation
• A Multi-Modal Transformer-based Code Summarization Approach for Smart Contracts
• Traversing Latent Space using Decision Ferns
• MURAUER: Mapping Unlabeled Real Data for Label AUstERity
• An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls
• Time-Sequence Channel Inference for Beam Alignment in Vehicular Networks
• MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays
• Mean Field Game GAN
• Discriminative models for multi-instance problems with tree-structure
• DHASP: Differentiable Hearing Aid Speech Processing
• Enhancing Perceptual Attributes with Bayesian Style Generation
• Modeling Multivariate Cyber Risks: Deep Learning Dating Extreme Value Theory
• Non-Asymptotic Performance Guarantees for Neural Estimation of $\mathsf{f}$-Divergences
• Improved and Robust Controversy Detection in General Web Pages Using Semantic Approaches under Large Scale Conditions
• Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
• Maximum Entropy Reinforcement Learning with Mixture Policies
• Modular Continual Learning in a Unified Visual Environment
• Self-Supervised Adaptation for Video Super-Resolution
• Keywords Guided Method Name Generation
• Modelling Identity Rules with Neural Networks
• DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
• Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
• Using stochastic computation graphs formalism for optimization of sequence-to-sequence model
• ACRE: Abstract Causal REasoning Beyond Covariation
• Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder
• An Introduction to Robust Graph Convolutional Networks
• Self-Constructing Neural Networks Through Random Mutation
• Action Quality Assessment Across Multiple Actions
• Towards Visual Feature Translation
• Robust Reinforcement Learning under model misspecification
• Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation
• Deep Multimodal Learning: An Effective Method for Video Classification
• Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
• Asymmetric CNN for image super-resolution
• Multi-Scale Distributed Representation for Deep Learning and its Application to b-Jet Tagging
• PAUL: Procrustean Autoencoder for Unsupervised Lifting
• Spatial Content Alignment For Pose Transfer
• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
• Automatic Liver Segmentation with Adversarial Loss and Convolutional Neural Network
• Fast Jacobian-Vector Product for Deep Networks
• TradeR: Practical Deep Hierarchical Reinforcement Learning for Trade Execution
• Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information
• Sequential Variational Autoencoders for Collaborative Filtering
• Planning in Dynamic Environments with Conditional Autoregressive Models
• Polar Decoding on Sparse Graphs with Deep Learning
• Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
• Searching Efficient Model-guided Deep Network for Image Denoising
• Low Complexity Joint Impairment Mitigation of I/Q Modulator and PA Using Neural Networks
• Weakly Supervised Video Salient Object Detection
• Convergence Analysis of Gradient Descent Algorithms with Proportional Updates
• Regularized adversarial examples for model interpretability
• Efficient transfer learning for NLP with ELECTRA
• LI-Net: Large-Pose Identity-Preserving Face Reenactment Network
• Exact Stochastic Second Order Deep Learning
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• Reinforced Attention for Few-Shot Learning and Beyond
• Indoor GeoNet: Weakly Supervised Hybrid Learning for Depth and Pose Estimation
• Deep Weakly Supervised Positioning
• Q-matrix Unaware Double JPEG Detection using DCT-Domain Deep BiLSTM Network
• Harmonic Recomposition using Conditional Autoregressive Modeling
• GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification
• Conversational Semantic Role Labeling
• A Graph Convolutional Neural Network based Framework for Estimating Future Citations Count of Research Articles
• An Order Preserving Bilinear Model for Person Detection in Multi-Modal Data
• Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
• Seq2Seq Mimic Games: A Signaling Perspective
• Personalized Bundle Recommendation in Online Games
• Performance Estimation of Synthesis Flows cross Technologies using LSTMs and Transfer Learning
• Interpreting Models by Allowing to Ask
• Text Assisted Insight Ranking Using Context-Aware Memory Network
• Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearity
• Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
• PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations
• An acceleration strategy for randomize-then-optimize sampling via deep neural networks
• Learning to recover orientations from projections in single-particle cryo-EM
• Incorporating Relevant Knowledge in Context Modeling and Response Generation
• Splenomegaly Segmentation on Multi-modal MRI using Deep Convolutional Networks
• Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network
• The RLLChatbot: a solution to the ConvAI challenge
• ADNet: Temporal Anomaly Detection in Surveillance Videos
• A New Method to Classify Type IIP/IIL Supernovae Based on their Spectra
• Learning Metrics from Mean Teacher: A Supervised Learning Method for Improving the Generalization of Speaker Verification System
• Multitasking Inhibits Semantic Drift
• Neural Sequence Segmentation as Determining the Leftmost Segments
• An Uncertainty-aware Hierarchical Probabilistic Network for Early Prediction, Quantification and Segmentation of Pulmonary Tumour Growth
• Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network
• Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs
• Modeling Graph Node Correlations with Neighbor Mixture Models
• Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
• Development of digitally obtainable 10-year risk scores for depression and anxiety in the general population
• Using CNNs for AD classification based on spatial correlation of BOLD signals during the observation
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
• A Framework for Recognizing and Estimating Human Concentration Levels
• A Low-Complexity MIMO Channel Estimator with Implicit Structure of a Convolutional Neural Network
• Self-Refining Deep Symmetry Enhanced Network for Rain Removal
• Dynamic VAEs with Generative Replay for Continual Zero-shot Learning
• Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval
• Predicting Unplanned Readmissions with Highly Unstructured Data
• Incremental Scene Synthesis
• Lily-like twist distribution in toroidal nematics
• Learning to fool the speaker recognition
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
• Improving Expressivity of Graph Neural Networks
• Low Bitrate Image Compression with Discretized Gaussian Mixture Likelihoods
• Training few-shot classification via the perspective of minibatch and pretraining
• Learning to Separate Multiple Illuminants in a Single Image
• A Lightweight Solution of Industrial Computed Tomography with Convolutional Neural Network
• Hybrid Attention Networks for Flow and Pressure Forecasting in Water Distribution Systems
• Contextual Pyramid Attention Network for Building Segmentation in Aerial Imagery
• Generative Adversarial Networks for Video-to-Video Domain Adaptation
• CPARR: Category-based Proposal Analysis for Referring Relationships
• Toward Verifiable Real-Time Obstacle Motion Prediction for Dynamic Collision Avoidance
• Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series
• Skeptical Deep Learning with Distribution Correction
• CommUnet: U-net decoder for convolutional codes in communication
• Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack
• Structure Learning of Deep Neural Networks with Q-Learning
• Strategies for Language Identification in Code-Mixed Low Resource Languages
• A Deeper Look at the Unsupervised Learning of Disentangled Representations in $\beta$-VAE from the Perspective of Core Object Recognition
• Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning
• Identity Enhanced Residual Image Denoising
• SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
• Learning to Learn Morphological Inflection for Resource-Poor Languages
• Training of a Skull-Stripping Neural Network with efficient data augmentation
• APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals
• Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network
• Learning sparse transformations through backpropagation
• KaLM at SemEval-2020 Task 4: Knowledge-aware Language Models for Comprehension And Generation
• Deep neural network based i-vector mapping for speaker verification using short utterances
• Online Visual Robot Tracking and Identification using Deep LSTM Networks
• Sound event detection using weakly-labeled semi-supervised data with GCRNNS, VAT and Self-Adaptive Label Refinement
• Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
• Relay Selection for 5G New Radio Via Artificial Neural Networks
• A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
• A Blended Deep Learning Approach for Predicting User Intended Actions
• PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
• Improving Adversarial Text Generation by Modeling the Distant Future
• Low Power In-Memory Implementation of Ternary Neural Networks with Resistive RAM-Based Synapse
• On Deep Learning for Radio Resource Management in A Non-stationary Radio Environment
• TAG : Type Auxiliary Guiding for Code Comment Generation
• Hierarchical Attention Network for Action Segmentation
• Deep Learning based Person Re-identification
• Can a powerful neural network be a teacher for a weaker neural network?
• Planning from Images with Deep Latent Gaussian Process Dynamics
• Molecular Sparse Representation by 3D Ellipsoid Radial Basis Function Neural Networks via $L_1$ Regularization
• An Integrated Enhancement Solution for 24-hour Colorful Imaging
• Counterfactual Propagation for Semi-Supervised Individual Treatment Effect Estimation
• Iterative Domain Optimization
• Deep Learning for Wireless Communications
• W-Cell-Net: Multi-frame Interpolation of Cellular Microscopy Videos
• IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection
• Learning Probabilistic Sentence Representations from Paraphrases
• MicroNet for Efficient Language Modeling
• Predicting Video features from EEG and Vice versa
• Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
• Aggregation of binary feature descriptors for compact scene model representation in large scale structure-from-motion applications
• Distilling neural networks into skipgram-level decision lists
• Exponentially improved detection and correction of errors in experimental systems using neural networks
• Benchmarking End-to-end Learning of MIMO Physical-Layer Communication
• Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech
• Unsupervised Trajectory Segmentation and Promoting of Multi-Modal Surgical Demonstrations
• Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
• Consensus Driven Learning
• Mapping Natural Language Commands to Web Elements
• Benchmarks of ResNet Architecture for Atrial Fibrillation Classification
• CHEER: Rich Model Helps Poor Model via Knowledge Infusion
• KL-Divergence-Based Region Proposal Network for Object Detection
• dynamicMF: A Matrix Factorization Approach to Monitor Resource Usage in High Performance Computing Systems
• A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images
• Full waveform inversion with random shot selection using adaptive gradient descent
• MobileFace: 3D Face Reconstruction with Efficient CNN Regression
• EpiRL: A Reinforcement Learning Agent to Facilitate Epistasis Detection
• Cylindrical Transform: 3D Semantic Segmentation of Kidneys With Limited Annotated Images
• A Case Study of Spherical Parallel Manipulators Fabricated via Laminate Processes
• Towards Language Agnostic Universal Representations
• A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
• Knowledge Graph Simple Question Answering for Unseen Domains
• GoChat: Goal-oriented Chatbots with Hierarchical Reinforcement Learning
• Semi-Automating Knowledge Base Construction for Cancer Genetics
• Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging
• How to do Physics-based Learning
• A study on the use of Boundary Equilibrium GAN for Approximate Frontalization of Unconstrained Faces to aid in Surveillance
• Learning to Fingerprint the Latent Structure in Question Articulation
• Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems
• Sequential Coordination of Deep Models for Learning Visual Arithmetic
• LyRN (Lyapunov Reaching Network): A Real-Time Closed Loop approach from Monocular Vision
• Enhanced Network Embeddings via Exploiting Edge Labels
• Deep Co-investment Network Learning for Financial Assets
• EEG-based video identification using graph signal modeling and graph convolutional neural network
• Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation
• Predicting Different Acoustic Features from EEG and towards direct synthesis of Audio Waveform from EEG
• OPAL-Net: A Generative Model for Part-based Object Layout Generation
• Convolutional Neural Networks for the segmentation of microcalcification in Mammography Imaging
• SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques
• 3D Face Reconstruction by Learning from Synthetic Data
• An Improved Relevance Feedback in CBIR
• Geoseg: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction
• Representation Learning Models for Entity Search
• Compositional Stochastic Average Gradient for Machine Learning and Related Applications
• Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
• Nested Scale Editing for Conditional Image Synthesis
• Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence
• Optical Flow Super-Resolution Based on Image Guidence Using Convolutional Neural Network
• Future-Prediction-Based Model for Neural Machine Translation
• A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images
• Spoken dialect identification in Twitter using a multi-filter architecture
• C-SL: Contrastive Sound Localization with Inertial-Acoustic Sensors
• End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera
• The Lower The Simpler: Simplifying Hierarchical Recurrent Models
• Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning
• Neural Network Activation Quantization with Bitwise Information Bottlenecks
• Physically constrained short-term vehicle trajectory forecasting with naive semantic maps
• Explicit Gradient Learning
• Tangent Space Sensitivity and Distribution of Linear Regions in ReLU Networks
• RTEX: A novel methodology for Ranking, Tagging, and Explanatory diagnostic captioning of radiography exams
• Preconditioner on Matrix Lie Group for SGD
• Privacy-Aware Activity Classification from First Person Office Videos
• ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
• An Empirical Comparison of Syllabuses for Curriculum Learning
• Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation
• A Generative Model for Joint Natural Language Understanding and Generation
• NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
• Numerical Simulation of Exchange Option with Finite Liquidity: Controlled Variate Model
• Synthesis of recurrent neural networks for dynamical system simulation
• Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
• Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
• Deep Multimodal Transfer-Learned Regression in Data-Poor Domains
• Multi-scenario deep learning for multi-speaker source separation
• An online evolving framework for advancing reinforcement-learning based automated vehicle control
• GO Hessian for Expectation-Based Objectives
• Interval-valued Data Prediction via Regularized Artificial Neural Network
• A maximum-entropy approach to off-policy evaluation in average-reward MDPs
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
• Time-Variant Variational Transfer for Value Functions
• Image Sentiment Transfer
• Siamese Survival Analysis with Competing Risks
• Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
• MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
• Live Video Comment Generation Based on Surrounding Frames and Live Comments
• Dropout during inference as a model for neurological degeneration in an image captioning network
• Global Image Sentiment Transfer
• Using holistic event information in the trigger
• Real-time Flexibility Feedback for Closed-loop Aggregator and System Operator Coordination
• Deep Factorised Inverse-Sketching
• Robust Implicit Backpropagation
• A Hierarchical Approach to Neural Context-Aware Modeling
• Robust Face Verification via Disentangled Representations
• Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions
• Image-to-image Mapping with Many Domains by Sparse Attribute Transfer
• Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator
• Uncertainty in Neural Relational Inference Trajectory Reconstruction
• Deep Learning-based Stress Determinator for Mouse Psychiatric Analysis using Hippocampus Activity
• Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions
• Empirically Verifying Hypotheses Using Reinforcement Learning
• Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition
• A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans
• Exploring Recombination for Efficient Decoding of Neural Machine Translation
• Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features
• Binarized Convolutional Neural Networks for Efficient Inference on GPUs
• Conformal Prediction Intervals for Neural Networks Using Cross Validation
• A Simple Domain Shifting Networkfor Generating Low Quality Images
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
• Pan-Sharpening with Color-Aware Perceptual Loss and Guided Re-Colorization
• Leveraging Medical Sentiment to Understand Patients Health on Social Media
• RS-Net: Regression-Segmentation 3D CNN for Synthesis of Full Resolution Missing Brain MRI in the Presence of Tumours
• CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
• A differential neural network learns stochastic differential equations and the Black-Scholes equation for pricing multi-asset options
• Deep Fence Estimation using Stereo Guidance and Adversarial Learning
• Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification
• MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks
• Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
• Multi-Objective DNN-based Precoder for MIMO Communications
• MCMI: Multi-Cycle Image Translation with Mutual Information Constraints
• Distinctive-attribute Extraction for Image Captioning
• A Few-Shot Sequential Approach for Object Counting
• On the Flip Side: Identifying Counterexamples in Visual Question Answering
• Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms
• Deep Fiducial Inference
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
• Bounding Box Embedding for Single Shot Person Instance Segmentation
• Question-Aware Sentence Gating Networks for Question and Answering
• Expressive power of outer product manifolds on feed-forward neural networks
• Accuracy to Throughput Trade-offs for Reduced Precision Neural Networks on Reconfigurable Logic
• End-to-End Multi-Object Tracking with Global Response Map
• Modeling Coherency in Generated Emails by Leveraging Deep Neural Learners
• Multi-Perspective Neural Architecture for Recommendation System
• Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
• Comprehensive Facial Expression Synthesis using Human-Interpretable Language
• Discovering Interesting Plots in Production Yield Data Analytics
• Topic-Guided Attention for Image Captioning
• Enriching Knowledge Bases with Counting Quantifiers
• Scalable Recommender Systems through Recursive Evidence Chains
• The SPectral Image Typer (SPIT)
• A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation
• Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
• Across-domains transferability of Deep-RED in de-noising and compressive sensing recovery of seismic data
• Deconfounding age effects with fair representation learning when assessing dementia
• Visual Relation Grounding in Videos
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
• Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks
• Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
• Saliency Prediction with External Knowledge
• Binary Search and First Order Gradient Based Method for Stochastic Optimization
• Latent Transformations for Object View Points Synthesis
• Automatic Detection and Classification of Waste Consumer Medications for Proper Management and Disposal
• Deep Reinforcement Learning for Dynamic Spectrum Sensing and Aggregation in Multi-Channel Wireless Networks
• On Deep Unsupervised Active Learning
• Unnormalized Variational Bayes
• Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation
• Deep Direct Likelihood Knockoffs
• Shape-CD: Change-Point Detection in Time-Series Data with Shapes and Neurons
• Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network
• Prior Attention for Style-aware Sequence-to-Sequence Models
• Neural text-to-speech with a modeling-by-generation excitation vocoder
• Applying Incremental Deep Neural Networks-based Posture Recognition Model for Injury Risk Assessment in Construction
• Dynamic Spectrum Matching with One-shot Learning
• Wall Stress Estimation of Cerebral Aneurysm based on Zernike Convolutional Neural Networks
• Point or Generate Dialogue State Tracker
• Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone
• Deep Learning based Estimation of Weaving Target Maneuvers
• Mastering Rate based Curriculum Learning
• Multi-task learning of daily work and study round-trips from survey data
• Mastering Large Scale Multi-label Image Recognition with high efficiency overCamera trap images
• Adversarial confidence and smoothness regularizations for scalable unsupervised discriminative learning
• Multiple View Generation and Classification of Mid-wave Infrared Images using Deep Learning
• Uncertainty-aware Self-supervised 3D Data Association
• A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer
• LIRA: Lifelong Image Restoration from Unknown Blended Distortions
• Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents
• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization
• Improving the Performance of Neural Networks in Regression Tasks Using Drawering
• Emergent symbolic language based deep medical image classification
• Learn to Talk via Proactive Knowledge Transfer
• Residual Network Based Direct Synthesis of EM Structures: A Study on One-to-One Transformers
• Towards Comprehensive Recommender Systems: Time-Aware UnifiedcRecommendations Based on Listwise Ranking of Implicit Cross-Network Data
• Exploiting Temporal Attention Features for Effective Denoising in Videos
• Teaching a Machine to Diagnose a Heart Disease; Beginning from digitizing scanned ECGs to detecting the Brugada Syndrome (BrS)
• Variational learning across domains with triplet information
• Sample Efficiency in Sparse Reinforcement Learning: Or Your Money Back
• Cost-Quality Adaptive Active Learning for Chinese Clinical Named Entity Recognition
• Memory Augmented Self-Play
• Being curious about the answers to questions: novelty search with learned attention
• DNN Based Speech Enhancement for Unseen Noises Using Monte Carlo Dropout
• An Adversarial Attack Defending System for Securing In-Vehicle Networks
• Modulating Scalable Gaussian Processes for Expressive Statistical Learning
• Unsupervised and Supervised Structure Learning for Protein Contact Prediction
• Short-term Load Forecasting with Deep Residual Networks
• Analysis of memory in LSTM-RNNs for source separation
• Learning to Transcribe by Ear
• Forward Amortized Inference for Likelihood-Free Variational Marginalization
• Open-set Adversarial Defense
• PSO-PS: Parameter Synchronization with Particle Swarm Optimization for Distributed Training of Deep Neural Networks
• Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products
• Robust Spoken Language Understanding with RL-based Value Error Recovery
• Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression
• Diversified Mutual Learning for Deep Metric Learning
• RoIFusion: 3D Object Detection from LiDAR and Vision
• A new dataset and model for learning to understand navigational instructions
• STEP-GAN: A Step-by-Step Training for Multi Generator GANs with application to Cyber Security in Power Systems
• Syntax Role for Neural Semantic Role Labeling
• A Genetic Feature Selection Based Two-stream Neural Network for Anger Veracity Recognition
• SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
• Multifunction Cognitive Radar Task Scheduling Using Monte Carlo Tree Search and Policy Networks
• A Multisensory Learning Architecture for Rotation-invariant Object Recognition
• 3D Object Detection and Tracking Based on Streaming Data
• PointIso: Point Cloud Based Deep Learning Model for Detecting Arbitrary-Precision Peptide Features in LC-MS Map through Attention Based Segmentation
• Malicious Network Traffic Detection via Deep Learning: An Information Theoretic View
• Replicating Active Appearance Model by Generator Network
• Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
• Type-driven Neural Programming by Example
• Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
• Gaussian Mixture Latent Vector Grammars
• Automatic deep learning for trend prediction in time series data
• On Multi-Session Website Fingerprinting over TLS Handshake
• Topology Optimization through Differentiable Finite Element Solver
• Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
• Leveraging Local and Global Descriptors in Parallel to Search Correspondences for Visual Localization
• Focus-Constrained Attention Mechanism for CVAE-based Response Generation
• fMRI Multiple Missing Values Imputation Regularized by a Recurrent Denoiser
• Artificial Intelligence in Surgery: Neural Networks and Deep Learning
• BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
• Cross Learning in Deep Q-Networks
• Automatic Segmentation, Localization, and Identification of Vertebrae in 3D CT Images Using Cascaded Convolutional Neural Networks
• A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition
• Facilitate the Parametric Dimension Reduction by Gradient Clipping
• Machine Learning and Computer Vision Techniques to Predict Thermal Properties of Particulate Composites
• Learned Dual-View Reflection Removal
• Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition
• Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
• An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
• Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
• Arbitrary Style Transfer using Graph Instance Normalization
• PDE-Inspired Algorithms for Semi-Supervised Learning on Point Clouds
• Single Camera Training for Person Re-identification
• Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
• Translation, Sentiment and Voices: A Computational Model to Translate and Analyse Voices from Real-Time Video Calling
• Reliable counting of weakly labeled concepts by a single spiking neuron model
• RLCache: Automated Cache Management Using Reinforcement Learning
• IIITM Face: A Database for Facial Attribute Detection in Constrained and Simulated Unconstrained Environments
• Boosting Image Recognition with Non-differentiable Constraints
• A machine learning method correlating pulse pressure wave data with pregnancy
• High Mutual Information in Representation Learning with Symmetric Variational Inference
• On stochastic optimization methods for Monte Carlo least-squares problems
• Unaligned Image-to-Sequence Transformation with Loop Consistency
• Did you miss it? Automatic lung nodule detection combined with gaze information improves radiologists' screening performance
• Investigation on the generalization of the Sampled Policy Gradient algorithm
• Improving Tweet Representations using Temporal and User Context
• On the Effects of Pseudo and Quantum Random Number Generators in Soft Computing
• Orthogonality Constrained Multi-Head Attention For Keyword Spotting
• Unconstrained Road Marking Recognition with Generative Adversarial Networks
• Attention-based Fault-tolerant Approach for Multi-agent Reinforcement Learning Systems
• Shape Constrained Network for Eye Segmentation in the Wild
• Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
• Isolation and Localization of Unknown Faults Using Neural Network-Based Residuals
• The Role of Embedding Complexity in Domain-invariant Representations
• Robust Dual View Deep Agent
• Wasserstein Distance Guided Cross-Domain Learning
• Residual Switching Network for Portfolio Optimization
• Why can't memory networks read effectively?
• FlowNorm: A Learning-based Method for Increasing Convergence Range of Direct Alignment
• Memory-Augmented Recurrent Networks for Dialogue Coherence
• Towards Annotating and Creating Sub-Sentence Summary Highlights
• CLN2INV: Learning Loop Invariants with Continuous Logic Networks
• Towards Learning Cross-Modal Perception-Trace Models
• BOBBY2: Buffer Based Robust High-Speed Object Tracking
• You Can Run, But You Cannot Hide: Using Elevation Profiles to Breach Location Privacy through Trajectory Prediction
• Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
• Batch Face Alignment using a Low-rank GAN
• Knowledge infused cascade convolutional neural network for segmenting retinal vessels in volumetric optical coherence tomography
• Parallel Stochastic Optimization Framework for Large-Scale Non-Convex Stochastic Problems
• ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
• TCT: A Cross-supervised Learning Method for Multimodal Sequence Representation
• Superposition as Data Augmentation using LSTM and HMM in Small Training Sets
• Unsupervised learning of the brain connectivity dynamic using residual D-net
• AI in Pursuit of Happiness, Finding Only Sadness: Multi-Modal Facial Emotion Recognition Challenge
• Neighborhood Watch: Representation Learning with Local-Margin Triplet Loss and Sampling Strategy for K-Nearest-Neighbor Image Classification
• Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech Synthesis
• Iterative Residual Image Deconvolution
• Mixing of Stochastic Accelerated Gradient Descent
• Efficient Target Activity Detection based on Recurrent Neural Networks
• Dynamic Regularizer with an Informative Prior
• Learning-based Real-time Detection of Intrinsic Reflectional Symmetry
• Neural Networks Classifier for Data Selection in Statistical Machine Translation
• ARSM Gradient Estimator for Supervised Learning to Rank
• Machine Translation in Pronunciation Space
• The LIG system for the English-Czech Text Translation Task of IWSLT 2019
• Community-preserving Graph Convolutions for Structural and Functional Joint Embedding of Brain Networks
• A Deep Error Correction Network for Compressed Sensing MRI
• Bootstrapping Disjoint Datasets for Multilingual Multimodal Representation Learning
• Preservation of Anomalous Subgroups On Machine Learning Transformed Data
• Demystifying Deep Learning: A Geometric Approach to Iterative Projections
• Robust Depth Estimation from Auto Bracketed Images
• Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation
• Transfer Learning of fMRI Dynamics
• Extra Proximal-Gradient Inspired Non-local Network
• Protein Mutation Stability Ternary Classification using Neural Networks and Rigidity Analysis
• An Unsupervised Model with Attention Autoencoders for Question Retrieval
• Efficient decorrelation of features using Gramian in Reinforcement Learning
• Cascaded Detail-Preserving Networks for Super-Resolution of Document Images
• LucidDream: Controlled Temporally-Consistent DeepDream on Videos
• Region segmentation via deep learning and convex optimization
• De-identification In practice
• Adaptive Bayesian Reticulum
• Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images
• AMR-to-Text Generation with Cache Transition Systems
• DeepFPC: Deep Unfolding of a Fixed-Point Continuation Algorithm for Sparse Signal Recovery from Quantized Measurements
• Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?
• DAVID: Dual-Attentional Video Deblurring
• Deep motion estimation for parallel inter-frame prediction in video compression
• Generalization Challenges for Neural Architectures in Audio Source Separation
• Hue-Net: Intensity-based Image-to-Image Translation with Differentiable Histogram Loss Functions
• Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image Sequences
• Shape analysis in Higgs boson pair production
• Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation
• Quantifying the effect of representations on task complexity
• Optimal Real-Space Renormalization-Group Transformations with Artificial Neural Networks
• Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification
• Black Box Algorithm Selection by Convolutional Neural Network
• Batch Normalization and the impact of batch structure on the behavior of deep convolution networks
• Learning Multiple Categories on Deep Convolution Networks
• Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization
• Dialog Context Language Modeling with Recurrent Neural Networks
• MoEVC: A Mixture-of-experts Voice Conversion System with Sparse Gating Mechanism for Accelerating Online Computation
• Consistency-Aware Recommendation for User-Generated ItemList Continuation
• Substation Signal Matching with a Bagged Token Classifier
• HMM-guided frame querying for bandwidth-constrained video search
• Machine Learning the Effective Hamiltonian in High Entropy Alloys
• Estimating 3D Camera Pose from 2D Pedestrian Trajectories
• Orthogonally Regularized Deep Networks For Image Super-resolution
• Selective Sampling and Mixture Models in Generative Adversarial Networks
• Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation
• An Analysis of Object Representations in Deep Visual Trackers
• Identifying Table Structure in Documents using Conditional Generative Adversarial Networks
• Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model
• DNNs as Layers of Cooperating Classifiers
• Human-Aware Motion Deblurring
• Interpretable Filter Learning Using Soft Self-attention For Raw Waveform Speech Recognition
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Keyword-based Topic Modeling and Keyword Selection
• Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation
• Comparison of Syntactic and Semantic Representations of Programs in Neural Embeddings
• Source coding of audio signals with a generative model
• Pretrained Transformers for Simple Question Answering over Knowledge Graphs
• Transport-Based Pattern Theory: A Signal Transformation Approach
• Motor Imagery Classification of Single-Arm Tasks Using Convolutional Neural Network based on Feature Refining
• CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions
• From Route Instructions to Landmark Graphs
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
• Estimation of Critical Temperature of High-Temperature Superconductors from AC susceptibility measurements using a pair of Neural Networks
• Unsupervised Adaptive Neural Network Regularization for Accelerated Radial Cine MRI
• Semi-Implicit Back Propagation
• Regularizing Semi-supervised Graph Convolutional Networks with a Manifold Smoothness Loss
• Think Global, Act Local: Relating DNN generalisation and node-level SNR
• A study of local optima for learning feature interactions using neural networks
• Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization
• Stochastic Approximate Gradient Descent via the Langevin Algorithm
• Neural arbitrary style transfer for portrait images using the attention mechanism
• Meta Segmentation Network for Ultra-Resolution Medical Images
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
• GRET: Global Representation Enhanced Transformer
• Technical report: Kidney tumor segmentation using a 2D U-Net followed by a statistical post-processing filter
• Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders
• Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue
• Blurry Video Frame Interpolation
• How Much Can A Retailer Sell? Sales Forecasting on Tmall
• Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing
• Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier
• KF-LAX: Kronecker-factored curvature estimation for control variate optimization in reinforcement learning
• Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks
• A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction
• Learning Incremental Triplet Margin for Person Re-identification
• Supervised Sentiment Classification with CNNs for Diverse SE Datasets
• An Inattention Model for Traveler Behavior with e-Coupons
• MEETING BOT: Reinforcement Learning for Dialogue Based Meeting Scheduling
• Unsupervised Learning of Morphological Forests
• A Constructive Approach for One-Shot Training of Neural Networks Using Hypercube-Based Topological Coverings
• Use of First and Third Person Views for Deep Intersection Classification
• Reducing state updates via Gaussian-gated LSTMs
• Composition and decomposition of GANs
• Learning Markov Chain in Unordered Dataset
• Securing Tag-based recommender systems against profile injection attacks: A comparative study. (Extended Report)
• Semi-Supervised Semantic Matching
• Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data
• Diversity Regularized Adversarial Learning
• Evaluating Bregman Divergences for Probability Learning from Crowd
• Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints
• Towards Controlled Transformation of Sentiment in Sentences
• Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noise
• Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane Representation
• Differential Description Length for Hyperparameter Selection in Machine Learning
• Where Do Human Heuristics Come From?
• Neural-Network Guided Expression Transformation
• Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval
• Improving Catheter Segmentation & Localization in 3D Cardiac Ultrasound Using Direction-Fused FCN
• Realizing Continual Learning through Modeling a Learning System as a Fiber Bundle
• Neuromodulated Goal-Driven Perception in Uncertain Domains
• Low-Latency Deep Clustering For Speech Separation
• Label-Removed Generative Adversarial Networks Incorporating with K-Means
• Predicting city safety perception based on visual image content
• Rapidly Adapting Moment Estimation
• Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize
• SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction
• End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
• Approximating Optimisation Solutions for Travelling Officer Problem with Customised Deep Learning Network
• Distributed deep learning for robust multi-site segmentation of CT imaging after traumatic brain injury
• A Sequential Set Generation Method for Predicting Set-Valued Outputs
• Are My Invariants Valid? A Learning Approach
• IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
• BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning
• Trainable Time Warping: Aligning Time-Series in the Continuous-Time Domain
• Improving Search through A3C Reinforcement Learning based Conversational Agent
• Threshold-Based Portfolio: The Role of the Threshold and Its Applications
• Nearest-Neighbor Neural Networks for Geostatistics
• Imbalanced Sentiment Classification Enhanced with Discourse Marker
• On the Vulnerability of CNN Classifiers in EEG-Based BCIs
• An End-to-End Approach to Automatic Speech Assessment for Cantonese-speaking People with Aphasia
• GAN You Do the GAN GAN?
• Data-Driven Microstructure Property Relations
• Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning
• Defeats GAN: A Simpler Model Outperforms in Knowledge Representation Learning
• Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
• Topic Spotting using Hierarchical Networks with Self Attention
• Long-Term Vehicle Localization by Recursive Knowledge Distillation
• An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
• Evaluating the Representational Hub of Language and Vision Models
• Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
• Analyzing the benefits of communication channels between deep learning models
• Late or Earlier Information Fusion from Depth and Spectral Data? Large-Scale Digital Surface Model Refinement by Hybrid-cGAN
• Using Context Information to Enhance Simple Question Answering
• Informative sample generation using class aware generative adversarial networks for classification of chest Xrays
• Learn to synthesize and synthesize to learn
• On Expected Accuracy
• Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding
• Generative Model with Dynamic Linear Flow
• Unsupervised Learning through Temporal Smoothing and Entropy Maximization
• Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction
• Monocular Depth Estimation with Directional Consistency by Deep Networks
• Accelerated Target Updates for Q-learning
• Improving Natural Language Interaction with Robots Using Advice
• S-OHEM: Stratified Online Hard Example Mining for Object Detection
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
• Efficient Deep Gaussian Process Models for Variable-Sized Input
• Cluster, Classify, Regress: A General Method For Learning Discountinous Functions
• Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
• Deep Learning: a new definition of artificial neuron with double weight
• Thwarting finite difference adversarial attacks with output randomization
• Effects of the optimisation of the margin distribution on generalisation in deep architectures
• GWU NLP Lab at SemEval-2019 Task 3: EmoContext: Effective Contextual Information in Models for Emotion Detection in Sentence-level in a Multigenre Corpus
• Generative Imaging and Image Processing via Generative Encoder
• A general method for regularizing tensor decomposition methods via pseudo-data
• Fast computation of loudness using a deep neural network
• OrderNet: Ordering by Example
• Unsupervised Holistic Image Generation from Key Local Patches
• Generative Parameter Sampler For Scalable Uncertainty Quantification
• Use Generalized Representations, But Do Not Forget Surface Features
• Learning to Rank for Plausible Plausibility
• A Closed-Form Learned Pooling for Deep Classification Networks
• Learning Approximately Objective Priors
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets
• A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
• Unifying the Stochastic Spectral Descent for Restricted Boltzmann Machines with Bernoulli or Gaussian Inputs
• MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks
• Surf at MEDIQA 2019: Improving Performance of Natural Language Inference in the Clinical Domain by Adopting Pre-trained Language Model
• Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection
• Recurrent Adversarial Service Times
• Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
• Automated Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction
• Bundle Optimization for Multi-aspect Embedding
• The University of Sydney's Machine Translation System for WMT19
• Recurrent Models for Situation Recognition
• Autonomous Skill-centric Testing using Deep Learning
• Coarse Grained Exponential Variational Autoencoders
• BASN -- Learning Steganography with Binary Attention Mechanism
• Two-stream Spatiotemporal Feature for Video QA Task
• An Evolutionary Algorithm of Linear complexity: Application to Training of Deep Neural Networks
• Convolutional Recurrent Neural Networks for Bird Audio Detection
• A Divide-and-Conquer Approach towards Understanding Deep Networks
• Automatic Estimation of Fetal Abdominal Circumference from Ultrasound Images
• Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning
• Progress Estimation and Phase Detection for Sequential Processes
• Training Deep Neural Networks via Optimization Over Graphs
• Predicting Human Activities from User-Generated Content
• DaiMoN: A Decentralized Artificial Intelligence Model Network
• Fiber Orientation Estimation Guided by a Deep Network
• On Residual CNN in text-dependent speaker verification task
• Sequential Dynamic Decision Making with Deep Neural Nets on a Test-Time Budget
• Binary Latent Representations for Efficient Ranking: Empirical Assessment
• CRNN: A Joint Neural Network for Redundancy Detection
• Learning-based Ensemble Average Propagator Estimation
• A Useful Motif for Flexible Task Learning in an Embodied Two-Dimensional Visual Environment
• Deep Semantics-Aware Photo Adjustment
• Set2Model Networks: Learning Discriminatively To Learn Generative Models
• SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
• An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation
• Language modeling with Neural trans-dimensional random fields
• Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks
• Here's My Point: Joint Pointer Architecture for Argument Mining
• An Embedded Deep Learning based Word Prediction
• Single-Queue Decoding for Neural Machine Translation
• Linear Discriminant Generative Adversarial Networks
• Dragon: A Computation Graph Virtual Machine Based Deep Learning Framework
• Context-Independent Polyphonic Piano Onset Transcription with an Infinite Training Dataset
• Learning Where to Attend Like a Human Driver
• e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
• Recurrent and Contextual Models for Visual Question Answering
• Decoupled Learning of Environment Characteristics for Safe Exploration
• Generative Archimedean Copulas
• Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
• End-to-end Learning for Short Text Expansion
• SCA-Net: A Self-Correcting Two-Layer Autoencoder for Hyper-spectral Unmixing
• U-vectors: Generating clusterable speaker embedding from unlabeled data
• MATCH: Metadata-Aware Text Classification in A Large Hierarchy
• Classification of multivariate weakly-labelled time-series with attention
• Online Graph Dictionary Learning
• Pose Guided Person Image Generation with Hidden p-Norm Regression
• End-to-end neural network approach to 3D reservoir simulation and adaptation
• FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding
• Generative Particle Variational Inference via Estimation of Functional Gradients
• Memory-Associated Differential Learning
• Complex Momentum for Optimization in Games
• Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
• iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
• Under Pressure: Learning to Detect Slip with Barometric Tactile Sensors
• Developing emotion recognition for video conference software to support people with autism
• Dynamically Modelling Heterogeneous Higher-Order Interactions for Malicious Behavior Detection in Event Logs
• Waveform Phasicity Prediction from Arterial Sounds through Spectrogram Analysis using Convolutional Neural Networks for Limb Perfusion Assessment
• Improving Weakly-supervised Object Localization via Causal Intervention
• Multi-Metric Optimization using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement
• Robust Trust Region for Weakly Supervised Segmentation
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles
• Landmark-Aware and Part-based Ensemble Transfer Learning Network for Facial Expression Recognition from Static images
• Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
• Dynamic Matching Markets in Power Grid: Concepts and Solution using Deep Reinforcement Learning
• DeepMI: A Mutual Information Based Framework For Unsupervised Deep Learning of Tasks
• Generating Video Descriptions with Topic Guidance
• Transductive Learning for Abstractive News Summarization
• Convolutions for Spatial Interaction Modeling
• Traveling Wave Solutions of Partial Differential Equations via Neural Networks
• SAS: A Simple, Accurate and Scalable Node Classification Algorithm
• Unified Framework for Feature Extraction based on Contrastive Learning
• UAV-Assisted Communication in Remote Disaster Areas using Imitation Learning
• COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Prediction
• Predicting Distant Metastases in Soft-Tissue Sarcomas from PET-CT scans using Constrained Hierarchical Multi-Modality Feature Learning
• End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning
• A data-driven and model-based accelerated Hamiltonian Monte Carlo method for Bayesian elliptic inverse problems
• Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
• Learning to Select for MIMO Radar based on Hybrid Analog-Digital Beamforming
• Exploring Adversarial Fake Images on Face Manifold
• Tail-Net: Extracting Lowest Singular Triplets for Big Data Applications
• When to Fold'em: How to answer Unanswerable questions
• Plot and Rework: Modeling Storylines for Visual Storytelling
• Internal Calibration Process Using Chirp Pulses with Application of the Adam Learning Algorithm
• EchoCP: An Echocardiography Dataset in Contrast Transthoracic Echocardiography for Patent Foramen Ovale Diagnosis
• Deep Learning for Needle Detection in a Cannulation Simulator
• A cost-benefit analysis of cross-lingual transfer methods
• Potential and limitations of machine-learning approaches to inclusive $|V_{ub}|$ determinations
• Mutual Information Constraints for Monte-Carlo Objectives