Caffe: Convolutional Architecture for Fast Feature Embedding

Abstract

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU ($\approx$ 2.5 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments. Caffe is maintained and developed by the Berkeley Vision and Learning Center (BVLC) with the help of an active community of contributors on GitHub. It powers ongoing research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia.

arXiv commentTech report for the Caffe software at http://github.com/BVLC/Caffe/

References in corpus (2)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• PANDA: Pose Aligned Networks for Deep Attribute Modeling

Cited by in corpus (1412)

• A Survey on Deep Learning in Medical Image Analysis
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• TensorFlow: A system for large-scale machine learning
• Deep learning in agriculture: A survey
• Deep Residual Learning for Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Unsupervised Domain Adaptation by Backpropagation
• Striving for Simplicity: The All Convolutional Net
• AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• YFCC100M: The New Data in Multimedia Research
• Understanding Neural Networks Through Deep Visualization
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• End-to-End Training of Deep Visuomotor Policies
• Recent Trends in Deep Learning Based Natural Language Processing
• Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
• DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
• Going Deeper in Facial Expression Recognition using Deep Neural Networks
• VQA: Visual Question Answering
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• cuDNN: Efficient Primitives for Deep Learning
• fastai: A Layered API for Deep Learning
• Mixed Precision Training
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• Fully Convolutional Networks for Semantic Segmentation
• Richer Convolutional Features for Edge Detection
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Anabranch Network for Camouflaged Object Segmentation
• Ternary Weight Networks
• Trained Ternary Quantization
• Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
• Deeply supervised salient object detection with short connections
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Adversarial Feature Learning
• Embedding Watermarks into Deep Neural Networks
• Deep Recurrent Q-Learning for Partially Observable MDPs
• Video Salient Object Detection via Fully Convolutional Networks
• Learning both Weights and Connections for Efficient Neural Networks
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• FractalNet: Ultra-Deep Neural Networks without Residuals
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• FlowNet: Learning Optical Flow with Convolutional Networks
• Focusing Attention: Towards Accurate Text Recognition in Natural Images
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• NiftyNet: a deep-learning platform for medical imaging
• Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Human pose estimation via Convolutional Part Heatmap Regression
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Training Convolutional Networks with Noisy Labels
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
• Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network
• Beyond One-hot Encoding: lower dimensional target embedding
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks
• Deep Representation Learning with Part Loss for Person Re-Identification
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Learning Structured Sparsity in Deep Neural Networks
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Robust Face Recognition via Multimodal Deep Face Representation
• Adversarial Discriminative Domain Adaptation
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
• Action-Conditional Video Prediction using Deep Networks in Atari Games
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Texture Synthesis Using Convolutional Neural Networks
• Cascade R-CNN: Delving into High Quality Object Detection
• Aggregated Residual Transformations for Deep Neural Networks
• Convolutional neural networks with low-rank regularization
• DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
• Text-Attentional Convolutional Neural Networks for Scene Text Detection
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Path Aggregation Network for Instance Segmentation
• Channel Pruning for Accelerating Very Deep Neural Networks
• Learning Activation Functions to Improve Deep Neural Networks
• A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
• A Survey on Edge Computing Systems and Tools
• Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision
• An application of cascaded 3D fully convolutional networks for medical image segmentation
• Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
• Recent Advances in Convolutional Neural Networks
• Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
• Systematic evaluation of CNN advances on the ImageNet
• Pyramid Scene Parsing Network
• Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
• Convolutional Pose Machines
• Securing the Internet of Things in the Age of Machine Learning and Software-defined Networking
• First Steps Toward Camera Model Identification with Convolutional Neural Networks
• Unsupervised Visual Representation Learning by Context Prediction
• Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
• Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
• Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
• Apple Flower Detection using Deep Convolutional Networks
• Universal Correspondence Network
• Visual Saliency Based on Multiscale Deep Features
• Medical Deep Learning -- A systematic Meta-Review
• Direction-aware Spatial Context Features for Shadow Detection
• Fast Convolutional Nets With fbfft: A GPU Performance Evaluation
• Ray: A Distributed Framework for Emerging AI Applications
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• FPNN: Field Probing Neural Networks for 3D Data
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Recurrent computations for visual pattern completion
• A Convolutional Neural Network Neutrino Event Classifier
• Neuromorphic Deep Learning Machines
• Detecting Sarcasm in Multimodal Social Platforms
• A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
• Large-scale JPEG steganalysis using hybrid deep-learning framework
• Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
• Source localization in an ocean waveguide using supervised machine learning
• Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• Loss Functions for Neural Networks for Image Processing
• Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation
• Flattened Convolutional Neural Networks for Feedforward Acceleration
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
• Software Engineering Challenges of Deep Learning
• CNN-RNN: A Unified Framework for Multi-label Image Classification
• All you need is a good init
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• Unsupervised Learning of Visual Representations using Videos
• MemNet: A Persistent Memory Network for Image Restoration
• Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
• Describing Videos by Exploiting Temporal Structure
• Data-dependent Initializations of Convolutional Neural Networks
• Few-Example Object Detection with Model Communication
• A Bi-layered Parallel Training Architecture for Large-scale Convolutional Neural Networks
• Gland Instance Segmentation Using Deep Multichannel Neural Networks
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• Fathom: Reference Workloads for Modern Deep Learning Methods
• Pose Invariant Embedding for Deep Person Re-identification
• A Richly Annotated Dataset for Pedestrian Attribute Recognition
• BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation
• Text Matching as Image Recognition
• Learning Visual Importance for Graphic Designs and Data Visualizations
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• FusionNet: 3D Object Classification Using Multiple Data Representations
• Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
• Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks
• Training Deeper Convolutional Networks with Deep Supervision
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Deeply-Learned Part-Aligned Representations for Person Re-Identification
• Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Deep Image Homography Estimation
• Simultaneous Traffic Sign Detection and Boundary Estimation using Convolutional Neural Network
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Exploring Nearest Neighbor Approaches for Image Captioning
• Deep Learning in the Automotive Industry: Applications and Tools
• Bags of Local Convolutional Features for Scalable Instance Search
• End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
• Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding
• Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
• Speed/accuracy trade-offs for modern convolutional object detectors
• Multispecies fruit flower detection using a refined semantic segmentation network
• Learning Spatiotemporal Features with 3D Convolutional Networks
• Bridging Category-level and Instance-level Semantic Image Segmentation
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
• Deep Learning on FPGAs: Past, Present, and Future
• Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks
• A Light CNN for Deep Face Representation with Noisy Labels
• Database Meets Deep Learning: Challenges and Opportunities
• A Deeper Look at Facial Expression Dataset Bias
• BigDL: A Distributed Deep Learning Framework for Big Data
• Siamese Instance Search for Tracking
• Dynamic Network Surgery for Efficient DNNs
• A Survey of FPGA-Based Neural Network Accelerator
• Improvements to context based self-supervised learning
• Deep Shading: Convolutional Neural Networks for Screen-Space Shading
• An All-in-One Network for Dehazing and Beyond
• ImageNet pre-trained models with batch normalization
• Finding strong lenses in CFHTLS using convolutional neural networks
• Places205-VGGNet Models for Scene Recognition
• Faster CNNs with Direct Sparse Convolutions and Guided Pruning
• Deep Contrast Learning for Salient Object Detection
• A Pursuit of Temporal Accuracy in General Activity Detection
• Shallow and Deep Convolutional Networks for Saliency Prediction
• DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
• Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image
• Deep Learning in Mobile and Wireless Networking: A Survey
• Good Practice in CNN Feature Transfer
• Memory Bounded Deep Convolutional Networks
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
• Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
• Deep Transfer Network: Unsupervised Domain Adaptation
• Fully Convolutional Attention Networks for Fine-Grained Recognition
• An Energy-Efficient FPGA-based Deconvolutional Neural Networks Accelerator for Single Image Super-Resolution
• Dual Deep Network for Visual Tracking
• Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
• Mixed Precision Training of Convolutional Neural Networks using Integer Operations
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
• Hierarchical 3D fully convolutional networks for multi-organ segmentation
• R${}^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
• DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation
• Unsupervised Deep Embedding for Clustering Analysis
• Analysis of the hands in egocentric vision: A survey
• Scale-aware Fast R-CNN for Pedestrian Detection
• Beyond triplet loss: a deep quadruplet network for person re-identification
• Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
• DeepFool: a simple and accurate method to fool deep neural networks
• User Diverse Preference Modeling by Multimodal Attentive Metric Learning
• Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
• LPRNet: License Plate Recognition via Deep Neural Networks
• Single-Shot Refinement Neural Network for Object Detection
• Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
• Super-Resolution via Deep Learning
• Truncated Cauchy Non-negative Matrix Factorization
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Review: Deep Learning in Electron Microscopy
• Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data
• Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild
• Classification of Alzheimer's Disease using fMRI Data and Deep Learning Convolutional Neural Networks
• DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
• DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
• Proposal-free Network for Instance-level Object Segmentation
• Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
• Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
• FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging
• Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering
• Ultimate tensorization: compressing convolutional and FC layers alike
• Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• Learning a visuomotor controller for real world robotic grasping using simulated depth images
• Wavelet Convolutional Neural Networks for Texture Classification
• Visualizing Convolutional Neural Network Protein-Ligand Scoring
• Energy-Efficient ConvNets Through Approximate Computing
• Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology
• Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
• Generative Image Modeling Using Spatial LSTMs
• BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
• Deep Ordinal Hashing with Spatial Attention
• PipeDream: Fast and Efficient Pipeline Parallel DNN Training
• Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks
• Deep Learning with S-shaped Rectified Linear Activation Units
• Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning
• Learning Representations for Automatic Colorization
• DSOD: Learning Deeply Supervised Object Detectors from Scratch
• A Unified Perspective on Multi-Domain and Multi-Task Learning
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• Accelerator-Aware Pruning for Convolutional Neural Networks
• Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search
• Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
• The Non-IID Data Quagmire of Decentralized Machine Learning
• Universal adversarial perturbations
• From Captions to Visual Concepts and Back
• Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
• Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
• Perceptual Generative Adversarial Networks for Small Object Detection
• Multi-Adversarial Domain Adaptation
• Memory-Efficient Implementation of DenseNets
• WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images
• Predicting Daily Activities From Egocentric Images Using Deep Learning
• Object Detection with Deep Learning: A Review
• Exploiting Local Features from Deep Networks for Image Retrieval
• Neural Models for Information Retrieval
• Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
• Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations
• Deep Probabilistic Programming
• Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets
• Stacked Deconvolutional Network for Semantic Segmentation
• Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
• Model-based Deep Hand Pose Estimation
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• ME R-CNN: Multi-Expert R-CNN for Object Detection
• Clipper: A Low-Latency Online Prediction Serving System
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• Automatic Image Annotation via Label Transfer in the Semantic Space
• A Computer Vision System to Localize and Classify Wastes on the Streets
• Label Distribution Learning Forests
• Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
• Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark
• GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent
• Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network
• Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction
• NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
• Hierarchical Attention Network for Action Recognition in Videos
• FIVR: Fine-grained Incident Video Retrieval
• Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots
• Learning visual groups from co-occurrences in space and time
• Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform
• Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
• Network Decoupling: From Regular to Depthwise Separable Convolutions
• Bayesian Layers: A Module for Neural Network Uncertainty
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Recurrent Neural Networks to Correct Satellite Image Classification Maps
• Learning View-Specific Deep Networks for Person Re-Identification
• Tell Me Where to Look: Guided Attention Inference Network
• Bayesian convolutional neural network based MRI brain extraction on nonhuman primates
• Towards seamless multi-view scene analysis from satellite to street-level
• Deep Convolution Networks for Compression Artifacts Reduction
• Learning to track for spatio-temporal action localization
• Eye Tracking for Everyone
• Facial Attributes: Accuracy and Adversarial Robustness
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Learning Language-Visual Embedding for Movie Understanding with Natural-Language
• VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback
• HashNet: Deep Learning to Hash by Continuation
• Benchmarking State-of-the-Art Deep Learning Software Tools
• Learning Background-Aware Correlation Filters for Visual Tracking
• Illuminating Pedestrians via Simultaneous Detection & Segmentation
• DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
• On-field player workload exposure and knee injury risk monitoring via deep learning
• CREST: Convolutional Residual Learning for Visual Tracking
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• Deep learning Approach for Classifying, Detecting and Predicting Photometric Redshifts of Quasars in the Sloan Digital Sky Survey Stripe 82
• See, Hear, and Read: Deep Aligned Representations
• Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning
• Webly Supervised Learning of Convolutional Networks
• Combining Data-driven and Model-driven Methods for Robust Facial Landmark Detection
• Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
• Deep Learning with Low Precision by Half-wave Gaussian Quantization
• Background rejection in NEXT using deep neural networks
• Detecting Visual Relationships with Deep Relational Networks
• Adversarial Manipulation of Deep Representations
• Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
• Deep Learning Driven Visual Path Prediction from a Single Image
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
• Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
• Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
• Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
• Scanner: Efficient Video Analysis at Scale
• NISP: Pruning Networks using Neuron Importance Score Propagation
• Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
• Characterizing Deep-Learning I/O Workloads in TensorFlow
• Improving Outfit Recommendation with Co-supervision of Fashion Generation
• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• A neural network memory prefetcher using semantic locality
• CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
• Action Recognition with Image Based CNN Features
• Fast and Accurate Single Image Super-Resolution via Information Distillation Network
• DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
• Single Shot Text Detector with Regional Attention
• Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos
• WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification
• Modeling human intuitions about liquid flow with particle-based simulation
• Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques
• Synthesized Classifiers for Zero-Shot Learning
• Implementing the Deep Q-Network
• Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
• Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
• PixelNet: Towards a General Pixel-level Architecture
• Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
• Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
• Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
• PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems
• SuperDTI: Ultrafast diffusion tensor imaging and fiber tractography with deep learning
• ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks
• Restructuring Batch Normalization to Accelerate CNN Training
• Robotic Endoscope Control via Autonomous Instrument Tracking
• Colorization as a Proxy Task for Visual Understanding
• Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets
• Deep learning for plasma tomography using the bolometer system at JET
• Temporal Segment Networks for Action Recognition in Videos
• Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mapping
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking
• Label Refinement Network for Coarse-to-Fine Semantic Segmentation
• Range Loss for Deep Face Recognition with Long-tail
• The Freiburg Groceries Dataset
• A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets
• Fine-grained pose prediction, normalization, and recognition
• Deep Learning for Computational Chemistry
• Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation
• Looking at Outfit to Parse Clothing
• An exploration of parameter redundancy in deep networks with circulant projections
• Love Thy Neighbors: Image Annotation by Exploiting Image Metadata
• A Systematic Approach to Blocking Convolutional Neural Networks
• ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey
• Interleaved Text/Image Deep Mining on a Large-Scale Radiology Database for Automated Image Interpretation
• Enabling Sparse Winograd Convolution by Native Pruning
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video
• An Iterative Machine-Learning Framework for RANS Turbulence Modeling
• Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
• Synergy: A HW/SW Framework for High Throughput CNNs on Embedded Heterogeneous SoC
• Unsupervised Semantic-based Aggregation of Deep Convolutional Features
• Automatic Large-Scale Data Acquisition via Crowdsourcing for Crosswalk Classification: A Deep Learning Approach
• Convolutional Neural Networks: Ensemble Modeling, Fine-Tuning and Unsupervised Semantic Localization for Intraoperative CLE Images
• Skin Lesions Classification Using Convolutional Neural Networks in Clinical Images
• ImageNet Training in Minutes
• DeepVO: A Deep Learning approach for Monocular Visual Odometry
• Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
• Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures
• Deep Temporal Appearance-Geometry Network for Facial Expression Recognition
• Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters
• SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• Low-memory GEMM-based convolution algorithms for deep neural networks
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• Semantic Scene Completion from a Single Depth Image
• Feedforward semantic segmentation with zoom-out features
• Defending Against Universal Attacks Through Selective Feature Regeneration
• A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
• Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
• Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
• DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networks
• Graph Based Convolutional Neural Network
• A deep architecture for unified aesthetic prediction
• Poseidon: A System Architecture for Efficient GPU-based Deep Learning on Multiple Machines
• Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval
• High Performance Zero-Memory Overhead Direct Convolutions
• DeepSpace: An Online Deep Learning Framework for Mobile Big Data to Understand Human Mobility Patterns
• Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
• Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
• Video Big Data Analytics in the Cloud: A Reference Architecture, Survey, Opportunities, and Open Research Issues
• Inductive Bias of Deep Convolutional Networks through Pooling Geometry
• ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements
• Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
• Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
• Photo Aesthetics Ranking Network with Attributes and Content Adaptation
• End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perception
• Deep representation learning for human motion prediction and classification
• Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
• Boosting Image Captioning with Attributes
• Deep FisherNet for Object Classification
• Why are deep nets reversible: A simple theory, with implications for training
• Jointly Localizing and Describing Events for Dense Video Captioning
• Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
• Parallel Tracking and Verifying
• Anchor Cascade for Efficient Face Detection
• Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping
• Pose-driven Deep Convolutional Model for Person Re-identification
• NITI: Training Integer Neural Networks Using Integer-only Arithmetic
• FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition
• Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
• Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
• Learning to Inpaint for Image Compression
• Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
• Multi-scale Deep Learning Architectures for Person Re-identification
• More is Less: A More Complicated Network with Less Inference Complexity
• Classification is a Strong Baseline for Deep Metric Learning
• A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency
• On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
• Inferring Latent Domains for Unsupervised Deep Domain Adaptation
• Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
• A Low-Cost, Flexible and Portable Volumetric Capturing System
• SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing
• PHOTONAI -- A Python API for Rapid Machine Learning Model Development
• Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Humans and deep networks largely agree on which kinds of variation make object recognition harder
• Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
• H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis
• Unconstrained Facial Landmark Localization with Backbone-Branches Fully-Convolutional Networks
• Distributed TensorFlow with MPI
• Understanding and Comparing Deep Neural Networks for Age and Gender Classification
• Deep Joint Face Hallucination and Recognition
• Deep Neural Network with l2-norm Unit for Brain Lesions Detection
• Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects
• Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification
• S${}^3$FD: Single Shot Scale-invariant Face Detector
• Distributed Robust Learning
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
• Speeding up Convolutional Neural Networks By Exploiting the Sparsity of Rectifier Units
• Declarative Recursive Computation on an RDBMS, or, Why You Should Use a Database For Distributed Machine Learning
• GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
• Deep Ordinal Ranking for Multi-Category Diagnosis of Alzheimer's Disease using Hippocampal MRI data
• Deep Learning for Saliency Prediction in Natural Video
• Learning Attributes Equals Multi-Source Domain Generalization
• Learning under Distributed Weak Supervision
• Zero-Shot Hashing via Transferring Supervised Knowledge
• Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition
• Scene Image Representation by Foreground, Background and Hybrid Features
• Edit Probability for Scene Text Recognition
• Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
• Cerebro: Static Subsuming Mutant Selection
• Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
• Quantized Convolutional Neural Networks for Mobile Devices
• Fisher Kernel for Deep Neural Activations
• Convolutional Neural Pyramid for Image Processing
• Hough-CNN: Deep Learning for Segmentation of Deep Brain Regions in MRI and Ultrasound
• UntrimmedNets for Weakly Supervised Action Recognition and Detection
• Classification regions of deep neural networks
• Learning for Disparity Estimation through Feature Constancy
• The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs
• Deep Convolutional Features for Image Based Retrieval and Scene Categorization
• Adapting Deep Network Features to Capture Psychological Representations
• Semantic Object Parsing with Local-Global Long Short-Term Memory
• Weakly Supervised Semantic Segmentation using Web-Crawled Videos
• On Vectorization of Deep Convolutional Neural Networks for Vision Tasks
• Accelerating Very Deep Convolutional Networks for Classification and Detection
• Visual Servoing from Deep Neural Networks
• Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
• Towards Automatic Abdominal Multi-Organ Segmentation in Dual Energy CT using Cascaded 3D Fully Convolutional Network
• End-to-end people detection in crowded scenes
• Reinterpreting CTC training as iterative fitting
• Multiple Instance Detection Network with Online Instance Classifier Refinement
• Content and Context Features for Scene Image Representation
• Human Pose Estimation using Deep Consensus Voting
• A Good Practice Towards Top Performance of Face Recognition: Transferred Deep Feature Fusion
• Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
• Look at Boundary: A Boundary-Aware Face Alignment Algorithm
• Self-Transfer Learning for Fully Weakly Supervised Object Localization
• Approximate Fisher Kernels of non-iid Image Models for Image Categorization
• Neural Compatibility Modeling with Attentive Knowledge Distillation
• Fusing Multi-Stream Deep Networks for Video Classification
• Convolutional Neural Networks at Constrained Time Cost
• Automatic Discovery and Optimization of Parts for Image Classification
• Freehand Sketch Recognition Using Deep Features
• Exploring the Neural Algorithm of Artistic Style
• Unsupervised Representation Learning by Sorting Sequences
• Visual Representations: Defining Properties and Deep Approximations
• A Tour of TensorFlow
• Geometry in Active Learning for Binary and Multi-class Image Segmentation
• RankIQA: Learning from Rankings for No-reference Image Quality Assessment
• Learning to Prune Filters in Convolutional Neural Networks
• Lightweight Unsupervised Deep Loop Closure
• Face Detection using Deep Learning: An Improved Faster RCNN Approach
• Joint Object and Part Segmentation using Deep Learned Potentials
• Viewpoints and Keypoints
• Video Propagation Networks
• Going Deeper into First-Person Activity Recognition
• Learning Image Representations by Completing Damaged Jigsaw Puzzles
• Learning Affinity via Spatial Propagation Networks
• View Synthesis by Appearance Flow
• A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
• HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks
• OpenSalicon: An Open Source Implementation of the Salicon Saliency Model
• AI Benchmark: Running Deep Neural Networks on Android Smartphones
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation By Use Of Convolutional Neural Networks
• Pose-Invariant Face Alignment with a Single CNN
• AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
• Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
• Natural Language Object Retrieval
• Learning to Detect Human-Object Interactions
• Attributes for Improved Attributes: A Multi-Task Network for Attribute Classification
• Zoom Out-and-In Network with Recursive Training for Object Proposal
• A New Method to Visualize Deep Neural Networks
• Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation
• Single- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016
• Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval
• Block-Matching Convolutional Neural Network for Image Denoising
• When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
• PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
• Feature Agglomeration Networks for Single Stage Face Detection
• Yedrouj-Net: An efficient CNN for spatial steganalysis
• Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
• Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
• Efficient Gender Classification Using a Deep LDA-Pruned Net
• Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016
• Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
• CASENet: Deep Category-Aware Semantic Edge Detection
• Rethinking Feature Distribution for Loss Functions in Image Classification
• Learning to count with deep object features
• Multi-Instance Visual-Semantic Embedding
• Learning Compatibility Across Categories for Heterogeneous Item Recommendation
• Matching-CNN Meets KNN: Quasi-Parametric Human Parsing
• FPGAs-as-a-Service Toolkit (FaaST)
• Factors of Transferability for a Generic ConvNet Representation
• Deep Covariance Descriptors for Facial Expression Recognition
• Constructing Fast Network through Deconstruction of Convolution
• Caffe con Troll: Shallow Ideas to Speed Up Deep Learning
• Attention-Based Multimodal Fusion for Video Description
• Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
• Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
• Detecting Vanishing Points using Global Image Context in a Non-Manhattan World
• FairTest: Discovering Unwarranted Associations in Data-Driven Applications
• Model compression as constrained optimization, with application to neural nets. Part II: quantization
• Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning
• Beyond Classification: Latent User Interests Profiling from Visual Contents Analysis
• Auxiliary Image Regularization for Deep CNNs with Noisy Labels
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks
• SFA: Small Faces Attention Face Detector
• Deep Learning for Single-View Instance Recognition
• Network of Experts for Large-Scale Image Categorization
• Active and Incremental Learning with Weak Supervision
• Walk and Learn: Facial Attribute Representation Learning from Egocentric Video and Contextual Data
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
• Flower Categorization using Deep Convolutional Neural Networks
• Attentional Network for Visual Object Detection
• Localizing and Orienting Street Views Using Overhead Imagery
• Deep Multi-Center Learning for Face Alignment
• Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation
• Semantically Consistent Regularization for Zero-Shot Recognition
• Actionness Estimation Using Hybrid Fully Convolutional Networks
• Global-Local Face Upsampling Network
• Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions
• Semantic Scene Completion Combining Colour and Depth: preliminary experiments
• Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs
• Online Open World Recognition
• Not All Ops Are Created Equal!
• S3: A Spectral-Spatial Structure Loss for Pan-Sharpening Networks
• Structural Compression of Convolutional Neural Networks
• Material Recognition in the Wild with the Materials in Context Database
• JPEG Steganalysis Based on DenseNet
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Learning Deep Networks from Noisy Labels with Dropout Regularization
• A Century of Portraits: A Visual Historical Record of American High School Yearbooks
• ACDC: A Structured Efficient Linear Layer
• DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
• Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field
• Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
• Evaluating Content-centric vs User-centric Ad Affect Recognition
• Deep Image Harmonization
• Unsupervised learning from videos using temporal coherency deep networks
• Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
• Neural Person Search Machines
• Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)
• Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities
• Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras
• An Introduction to Deep Learning for the Physical Layer
• Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
• The challenge of simultaneous object detection and pose estimation: a comparative study
• Are Safer Looking Neighborhoods More Lively? A Multimodal Investigation into Urban Life
• Deep Cuboid Detection: Beyond 2D Bounding Boxes
• Improving utility of brain tumor confocal laser endomicroscopy: objective value assessment and diagnostic frame detection with convolutional neural networks
• From handcrafted to deep local features
• DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications
• Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images
• Can we unify monocular detectors for autonomous driving by using the pixel-wise semantic segmentation of CNNs?
• Image Credibility Analysis with Effective Domain Transferred Deep Networks
• Self-supervised learning of visual features through embedding images into text topic spaces
• Deep Structured Models For Group Activity Recognition
• Fast ConvNets Using Group-wise Brain Damage
• MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
• Object cosegmentation using deep Siamese network
• Efficient Misalignment-Robust Multi-Focus Microscopical Images Fusion
• Half-CNN: A General Framework for Whole-Image Regression
• Visualizing and Understanding Deep Texture Representations
• BIRNet: Brain Image Registration Using Dual-Supervised Fully Convolutional Networks
• Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-trap Images using Very Deep Convolutional Neural Networks
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection
• Correlation Hashing Network for Efficient Cross-Modal Retrieval
• Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
• Dense Optical Flow Prediction from a Static Image
• HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
• Deep Fried Convnets
• BreakingNews: Article Annotation by Image and Text Processing
• Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
• Evaluating ResNeXt Model Architecture for Image Classification
• Learning Hypergraph-regularized Attribute Predictors
• Tensorial Mixture Models
• Learning Multi-Scale Deep Features for High-Resolution Satellite Image Classification
• Treelogy: A Novel Tree Classifier Utilizing Deep and Hand-crafted Representations
• Target Driven Instance Detection
• Deep Predictive Policy Training using Reinforcement Learning
• Adaptive Object Detection Using Adjacency and Zoom Prediction
• FashionNet: Personalized Outfit Recommendation with Deep Neural Network
• DualNet: Domain-Invariant Network for Visual Question Answering
• Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability
• On the Compression of Neural Networks Using ${\ell }_0$-Norm Regularization and Weight Pruning
• Self-taught Object Localization with Deep Networks
• Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks
• An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
• Privacy-Preserving Deep Inference for Rich User Data on The Cloud
• Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
• First Person Action-Object Detection with EgoNet
• A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction
• Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
• Automatic Concept Discovery from Parallel Text and Visual Corpora
• Optical Flow with Semantic Segmentation and Localized Layers
• Learning to Group and Label Fine-Grained Shape Components
• Deep Keyframe Detection in Human Action Videos
• CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
• Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network
• Modeling Visual Compatibility through Hierarchical Mid-level Elements
• Single View Stereo Matching
• Quantification in-the-wild: data-sets and baselines
• Anchor Box Optimization for Object Detection
• Relaxed Multiple-Instance SVM with Application to Object Discovery
• Why my photos look sideways or upside down? Detecting Canonical Orientation of Images using Convolutional Neural Networks
• Crime Mapping from Satellite Imagery via Deep Learning
• Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
• Cell nuclei classification in histopathological images using hybrid OLConvNet
• Deep Embedding Convolutional Neural Network for Synthesizing CT Image from T1-Weighted MR Image
• Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
• Ligand Pose Optimization with Atomic Grid-Based Convolutional Neural Networks
• A visual approach for age and gender identification on Twitter
• Scene Parsing with Global Context Embedding
• Pixel-wise Segmentation of Street with Neural Networks
• Contrastive-center loss for deep neural networks
• Exploring Food Detection using CNNs
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• Understanding More about Human and Machine Attention in Deep Neural Networks
• Hoard: A Distributed Data Caching System to Accelerate Deep Learning Training on the Cloud
• Let's Dance: Learning From Online Dance Videos
• SBNet: Sparse Blocks Network for Fast Inference
• Transfer Learning for Material Classification using Convolutional Networks
• Detection and Tracking of Liquids with Fully Convolutional Networks
• Inverse Compositional Spatial Transformer Networks
• Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
• Convolutional Random Walk Networks for Semantic Image Segmentation
• Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition
• Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
• Learning a Discriminative Model for the Perception of Realism in Composite Images
• Action Recognition by Hierarchical Mid-level Action Elements
• Visual Learning of Arithmetic Operations
• Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detection
• Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation
• Cardea: Context-Aware Visual Privacy Protection from Pervasive Cameras
• Probing Convolutional Neural Networks for Event Reconstruction in γ-Ray Astronomy with Cherenkov Telescopes
• Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs
• Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
• Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs
• DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
• On Periodic Functions as Regularizers for Quantization of Neural Networks
• Fingertip in the Eye: A cascaded CNN pipeline for the real-time fingertip detection in egocentric videos
• A Semi-supervised Framework for Image Captioning
• Deep Adaptive Proposal Network for Object Detection in Optical Remote Sensing Images
• Context-Aware Mixed Reality: A Framework for Ubiquitous Interaction
• Feature Incay for Representation Regularization
• Action Recognition with Joint Attention on Multi-Level Deep Features
• End-to-end Video-level Representation Learning for Action Recognition
• Parallel Multi Channel Convolution using General Matrix Multiplication
• Teacher-Student Compression with Generative Adversarial Networks
• Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment
• Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks
• Deep-Energy: Unsupervised Training of Deep Neural Networks
• Active Convolution: Learning the Shape of Convolution for Image Classification
• Visual Discovery at Pinterest
• On the Dimensionality of Embeddings for Sparse Features and Data
• Variational Inference to Measure Model Uncertainty in Deep Neural Networks
• Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks
• Situational Object Boundary Detection
• An Error Detection and Correction Framework for Connectomics
• Object Level Deep Feature Pooling for Compact Image Representation
• Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
• Action Recognition with Dynamic Image Networks
• Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
• Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
• Deep Temporal Linear Encoding Networks
• Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
• BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition
• A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
• Deep Learning for identifying radiogenomic associations in breast cancer
• Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
• Manifold Regularized Deep Neural Networks using Adversarial Examples
• From Plants to Landmarks: Time-invariant Plant Localization that uses Deep Pose Regression in Agricultural Fields
• Scalable Greedy Algorithms for Transfer Learning
• Big Learning with Bayesian Methods
• Deep Heterogeneous Feature Fusion for Template-Based Face Recognition
• CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Servers
• Multi-scale Location-aware Kernel Representation for Object Detection
• Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition
• Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
• Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
• Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection
• InverseFaceNet: Deep Monocular Inverse Face Rendering
• Reversible Recursive Instance-level Object Segmentation
• Learning a Dilated Residual Network for SAR Image Despeckling
• Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features
• Image-embodied Knowledge Representation Learning
• Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems
• Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
• Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?
• Evaluating the Impact of Semantic Segmentation and Pose Estimation on Dense Semantic SLAM
• Coordinating Filters for Faster Deep Neural Networks
• Domain Specific Approximation for Object Detection
• Scale-Invariant Structure Saliency Selection for Fast Image Fusion
• FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation
• Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models
• Estimated Depth Map Helps Image Classification
• Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
• A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild
• Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding
• Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
• Learning Structured Inference Neural Networks with Label Relations
• Actions and Attributes from Wholes and Parts
• Efficient ConvNets for Analog Arrays
• PetroSurf3D - A Dataset for high-resolution 3D Surface Segmentation
• Deep Joint Rain Detection and Removal from a Single Image
• Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
• Discriminative Label Consistent Domain Adaptation
• Taxonomy of Saliency Metrics for Channel Pruning
• Dual Path Networks for Multi-Person Human Pose Estimation
• A Compromise Principle in Deep Monocular Depth Estimation
• Cultural Event Recognition with Visual ConvNets and Temporal Models
• Multi-Image Matching via Fast Alternating Minimization
• MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
• FoveaNet: Perspective-aware Urban Scene Parsing
• Collaborative Summarization of Topic-Related Videos
• BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet
• Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets
• Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
• Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
• The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks
• Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural Networks
• Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
• Content-Based Video Retrieval in Historical Collections of the German Broadcasting Archive
• On transfer learning of neural networks using bi-fidelity data for uncertainty propagation
• Learning a Repression Network for Precise Vehicle Search
• Learning with Hierarchical Gaussian Kernels
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation
• FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
• Im2Flow: Motion Hallucination from Static Images for Action Recognition
• Matching Linear Algebra and Tensor Code to Specialized Hardware Accelerators
• Salient Object Detection by Lossless Feature Reflection
• Correlation Tracking via Joint Discrimination and Reliability Learning
• What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
• Learning Robust Deep Face Representation
• Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
• Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors
• A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
• Rethinking Machine Learning Development and Deployment for Edge Devices
• SA-CNN: Dynamic Scene Classification using Convolutional Neural Networks
• Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features
• Adaptive Spatial Steganography Based on Probability-Controlled Adversarial Examples
• Node-Based Job Scheduling for Large Scale Simulations of Short Running Jobs
• LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDAR
• Reducing Object Detection Uncertainty from RGB and Thermal Data for UAV Outdoor Surveillance
• Deep video gesture recognition using illumination invariants
• 3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
• Fast and Energy-Efficient CNN Inference on IoT Devices
• Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
• Block Switching: A Stochastic Approach for Deep Learning Security
• Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation
• Distributed Training Large-Scale Deep Architectures
• A 4D Light-Field Dataset and CNN Architectures for Material Recognition
• Nonlinear Statistical Learning with Truncated Gaussian Graphical Models
• Comprehensive Evaluation of OpenCL-based Convolutional Neural Network Accelerators in Xilinx and Altera FPGAs
• Towards Better Analysis of Deep Convolutional Neural Networks
• Layered Interpretation of Street View Images
• A practical convolutional neural network as loop filter for intra frame
• Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
• Accelerating Deep Neural Networks for Real-time Data Selection for High-resolution Imaging Particle Detectors
• Two-stream Flow-guided Convolutional Attention Networks for Action Recognition
• Dense Captioning with Joint Inference and Visual Context
• GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB
• Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
• Fast Semantic Image Segmentation with High Order Context and Guided Filtering
• Accelerating CNN Training by Pruning Activation Gradients
• Wildest Faces: Face Detection and Recognition in Violent Settings
• Performance Evaluation of Deep Learning Tools in Docker Containers
• GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design
• Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
• Optimized Broadcast for Deep Learning Workloads on Dense-GPU InfiniBand Clusters: MPI or NCCL?
• All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
• Structured Pruning for Efficient ConvNets via Incremental Regularization
• nuts-flow/ml: data pre-processing for deep learning
• Multi-label Object Attribute Classification using a Convolutional Neural Network
• Leaf Identification Using a Deep Convolutional Neural Network
• Simultaneous Hand Pose and Skeleton Bone-Lengths Estimation from a Single Depth Image
• Im2win: Memory Efficient Convolution On SIMD Architectures
• Multi-Modal Music Information Retrieval: Augmenting Audio-Analysis with Visual Computing for Improved Music Video Analysis
• Social Behavior Prediction from First Person Videos
• Optimizing Region Selection for Weakly Supervised Object Detection
• Weaving Multi-scale Context for Single Shot Detector
• Partitioning Compute Units in CNN Acceleration for Statistical Memory Traffic Shaping
• Texture segmentation with Fully Convolutional Networks
• Deep Learning for Surface Material Classification Using Haptic And Visual Information
• Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
• FOTS: Fast Oriented Text Spotting with a Unified Network
• Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach
• ScratchDet: Training Single-Shot Object Detectors from Scratch
• Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form
• Basic Level Categorization Facilitates Visual Object Recognition
• Pose-Aware Person Recognition
• Learning Versatile Convolution Filters for Efficient Visual Recognition
• Learning A Task-Specific Deep Architecture For Clustering
• Deep 3D Face Identification
• Learning Fine-grained Features via a CNN Tree for Large-scale Classification
• Recovering hard-to-find object instances by sampling context-based object proposals
• Textually Enriched Neural Module Networks for Visual Question Answering
• SMILER: Saliency Model Implementation Library for Experimental Research
• Object-Scene Convolutional Neural Networks for Event Recognition in Images
• Frustrated with Replicating Claims of a Shared Model? A Solution
• BrainSlug: Transparent Acceleration of Deep Learning Through Depth-First Parallelism
• Outlier Robust Online Learning
• Training Deep Networks without Learning Rates Through Coin Betting
• Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks
• The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
• Event Selection and Background Rejection in Time Projection Chambers Using Convolutional Neural Networks and a Specific Application to the AdEPT Gamma-ray Polarimeter Mission
• Multi-bin Trainable Linear Unit for Fast Image Restoration Networks
• Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
• Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
• Surveillance Video Parsing with Single Frame Supervision
• Real-time Human Pose Estimation from Video with Convolutional Neural Networks
• Face Flashing: a Secure Liveness Detection Protocol based on Light Reflections
• Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz
• Photo Filter Recommendation by Category-Aware Aesthetic Learning
• DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images
• A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation
• Rethinking Numerical Representations for Deep Neural Networks
• Deep Scene Text Detection with Connected Component Proposals
• Residual Squeeze VGG16
• Convolutional Regression for Visual Tracking
• Becoming the Expert - Interactive Multi-Class Machine Teaching
• Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Categorization and Scene Recognition
• Fast and Accurate Person Re-Identification with RMNet
• Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
• Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
• Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle
• Designing a Micro-Benchmark Suite to Evaluate gRPC for TensorFlow: Early Experiences
• Computation Error Analysis of Block Floating Point Arithmetic Oriented Convolution Neural Network Accelerator Design
• Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks
• DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
• Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
• Context-Aware Semantic Inpainting
• Egocentric Basketball Motion Planning from a Single First-Person Image
• Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks
• FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs
• Multi-stage Object Detection with Group Recursive Learning
• Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
• HMD Vision-based Teleoperating UGV and UAV for Hostile Environment using Deep Learning
• Learning Spatial-Aware Regressions for Visual Tracking
• Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
• Learning Detection with Diverse Proposals
• Tracking Persons-of-Interest via Unsupervised Representation Adaptation
• GPGPU Performance Estimation with Core and Memory Frequency Scaling
• Learning the semantic structure of objects from Web supervision
• Spatial Pyramid Convolutional Neural Network for Social Event Detection in Static Image
• Beyond Caption To Narrative: Video Captioning With Multiple Sentences
• DeepFace: Face Generation using Deep Learning
• Embedding based on function approximation for large scale image search
• Visual Summary of Egocentric Photostreams by Representative Keyframes
• 2L-3W: 2-Level 3-Way Hardware-Software Co-Verification for the Mapping of Deep Learning Architecture (DLA) onto FPGA Boards
• DAP3D-Net: Where, What and How Actions Occur in Videos?
• A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal MRI
• Sparsifying Neural Network Connections for Face Recognition
• When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks
• How hard can it be? Estimating the difficulty of visual search in an image
• Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing
• Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification
• Learning Concept Embeddings with Combined Human-Machine Expertise
• LEWIS: Latent Embeddings for Word Images and their Semantics
• Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
• Unconstrained Face Verification using Deep CNN Features
• Real-time 2D/3D Registration via CNN Regression
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• On the Depth of Deep Neural Networks: A Theoretical View
• Fast Deep Matting for Portrait Animation on Mobile Phone
• Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence
• DeepSkeleton: Skeleton Map for 3D Human Pose Regression
• SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks
• Contour Detection Using Cost-Sensitive Convolutional Neural Networks
• Efficient Communications in Training Large Scale Neural Networks
• Predicting Human Interaction via Relative Attention Model
• Stretching Domain Adaptation: How far is too far?
• An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms
• Learning Discriminative Features via Label Consistent Neural Network
• MLtuner: System Support for Automatic Machine Learning Tuning
• Ensemble Soft-Margin Softmax Loss for Image Classification
• Permutohedral Lattice CNNs
• pPython for Parallel Python Programming
• On monitoring development indicators using high resolution satellite images
• Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions
• Commonly Uncommon: Semantic Sparsity in Situation Recognition
• Neural Dataset Generality
• Boundary-sensitive Network for Portrait Segmentation
• Identifying First-person Camera Wearers in Third-person Videos
• VIPLFaceNet: An Open Source Deep Face Recognition SDK
• Action Classification and Highlighting in Videos
• Deep Convolutional Neural Network for 6-DOF Image Localization
• Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes
• Flexible Deep Neural Network Processing
• Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection
• Pseudo Mask Augmented Object Detection
• Ranked List Loss for Deep Metric Learning
• Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition
• EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos
• Cascaded Subpatch Networks for Effective CNNs
• CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
• A Method for Computing Class-wise Universal Adversarial Perturbations
• Part-Stacked CNN for Fine-Grained Visual Categorization
• Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
• CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images
• Co-Regularized Deep Representations for Video Summarization
• Group-wise Deep Co-saliency Detection
• Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking
• Fire SSD: Wide Fire Modules based Single Shot Detector on Edge Device
• Learning to see people like people
• Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
• Learning Transferable UAV for Forest Visual Perception
• Model compression as constrained optimization, with application to neural nets. Part V: combining compressions
• M${}^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection
• Robust RGB-D Face Recognition Using Attribute-Aware Loss
• Large Scale Artificial Neural Network Training Using Multi-GPUs
• Modelling Local Deep Convolutional Neural Network Features to Improve Fine-Grained Image Classification
• Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation
• Visual Stability Prediction and Its Application to Manipulation
• Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks
• Primitive Fitting Using Deep Boundary Aware Geometric Segmentation
• Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks
• Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks
• TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces
• Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier
• Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
• Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge
• Training Deep Neural Network in Limited Precision
• Complex Event Recognition from Images with Few Training Examples
• Brain Abnormality Detection by Deep Convolutional Neural Network
• Recognizing Activities of Daily Living from Egocentric Images
• Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
• Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
• Deep Hybrid Similarity Learning for Person Re-identification
• Multi-velocity neural networks for gesture recognition in videos
• A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms
• Learning from Web Data: the Benefit of Unsupervised Object Localization
• Learning to Disambiguate by Asking Discriminative Questions
• FFT-Based Deep Learning Deployment in Embedded Systems
• Mixed context networks for semantic segmentation
• Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
• Purine: A bi-graph based deep learning framework
• Open Problems in Engineering and Quality Assurance of Safety Critical Machine Learning Systems
• Image Classification and Retrieval from User-Supplied Tags
• A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
• Training for 'Unstable' CNN Accelerator:A Case Study on FPGA
• Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
• Kernelized Deep Convolutional Neural Network for Describing Complex Images
• Deep Multi-task Learning for Railway Track Inspection
• Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition
• Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks
• Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning
• PAD-Net: A Perception-Aided Single Image Dehazing Network
• Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?
• Deep Priority Hashing
• Query-adaptive Image Retrieval by Deep Weighted Hashing
• Deep Regression Forests for Age Estimation
• MG-WFBP: Efficient Data Communication for Distributed Synchronous SGD Algorithms
• Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning
• Designing Adaptive Neural Networks for Energy-Constrained Image Classification
• An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles
• Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
• Deep Kinematic Pose Regression
• Viewpoint Invariant Action Recognition using RGB-D Videos
• Superpixel Convolutional Networks using Bilateral Inceptions
• End-to-End Detection and Re-identification Integrated Net for Person Search
• Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
• PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI
• SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
• Deep joint rain and haze removal from single images
• On Deep Representation Learning from Noisy Web Images
• Analysing domain shift factors between videos and images for object detection
• PageNet: Page Boundary Extraction in Historical Handwritten Documents
• Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting
• Active learning with version spaces for object detection
• Parsing Occluded People by Flexible Compositions
• Hierarchical Bayesian Noise Inference for Robust Real-time Probabilistic Object Classification
• MGSim + MGMark: A Framework for Multi-GPU System Research
• Generalized Deep Image to Image Regression
• Disentanglement for Discriminative Visual Recognition
• Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web
• Application-Driven Near-Data Processing for Similarity Search
• Matrix Neural Networks
• Order-aware Convolutional Pooling for Video Based Action Recognition
• Learning image representations tied to ego-motion
• Efficient Image Evidence Analysis of CNN Classification Results
• A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
• Learning to Count Objects with Few Exemplar Annotations
• Multi-Branch Fully Convolutional Network for Face Detection
• Real Time Fine-Grained Categorization with Accuracy and Interpretability
• Optimal deep neural networks for sparse recovery via Laplace techniques
• Efficient Neural Network Compression
• Stock-out Prediction in Multi-echelon Networks
• An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
• Leveraging Class Similarity to Improve Deep Neural Network Robustness
• Searching for Apparel Products from Images in the Wild
• A Convolution Tree with Deconvolution Branches: Exploiting Geometric Relationships for Single Shot Keypoint Detection
• A Unified Iteration Space Transformation Framework for Sparse and Dense Tensor Algebra
• Scale Optimization for Full-Image-CNN Vehicle Detection
• 3D Face Reconstruction from Light Field Images: A Model-free Approach
• Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning
• Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation
• Latent fingerprint minutia extraction using fully convolutional network
• Multilevel Context Representation for Improving Object Recognition
• Write a Classifier: Predicting Visual Classifiers from Unstructured Text
• Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions
• Pedestrian Detection with Autoregressive Network Phases
• Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ
• Enhanced Touchable Projector-depth System with Deep Hand Pose Estimation
• AON: Towards Arbitrarily-Oriented Text Recognition
• Scheduled Differentiable Architecture Search for Visual Recognition
• Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
• Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search
• Cascaded Segmentation-Detection Networks for Word-Level Text Spotting
• Learning Neural Network Classifiers with Low Model Complexity
• Learning Temporal Embeddings for Complex Video Analysis
• Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones
• Information-Theoretic Representation Learning for Positive-Unlabeled Classification
• Pooled Motion Features for First-Person Videos
• Neural Style Representations and the Large-Scale Classification of Artistic Style
• ViP-CNN: Visual Phrase Guided Convolutional Neural Network
• Less-forgetful Learning for Domain Expansion in Deep Neural Networks
• A Metaprogramming and Autotuning Framework for Deploying Deep Learning Applications
• A Methodological Review of Visual Road Recognition Procedures for Autonomous Driving Applications
• Deep Differentiable Random Forests for Age Estimation
• Contrast-Oriented Deep Neural Networks for Salient Object Detection
• MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection
• Effective Image Retrieval via Multilinear Multi-index Fusion
• DeepFlux for Skeletons in the Wild
• Deep Neural Network Capacity
• A Visual Embedding for the Unsupervised Extraction of Abstract Semantics
• Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
• Multi-scale prediction for robust hand detection and classification
• Fine-grained Image Classification by Exploring Bipartite-Graph Labels
• A Fast and Accurate System for Face Detection, Identification, and Verification
• Feature Analysis and Selection for Training an End-to-End Autonomous Vehicle Controller Using the Deep Learning Approach
• One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis
• Temporal Action Localization by Structured Maximal Sums
• Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
• Instance-Level Salient Object Segmentation
• Automatically Batching Control-Intensive Programs for Modern Accelerators
• Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes
• Sampling the "Inverse Set" of a Neuron: An Approach to Understanding Neural Nets
• A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment
• Randomness in Deconvolutional Networks for Visual Representation
• Attention-Set based Metric Learning for Video Face Recognition
• Efficient Inferencing of Compressed Deep Neural Networks
• Tutorial on Answering Questions about Images with Deep Learning
• Personalized Saliency and its Prediction
• Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
• Pornographic Image Recognition via Weighted Multiple Instance Learning
• Cost Function Unrolling in Unsupervised Optical Flow
• gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs
• DNN Feature Map Compression using Learned Representation over GF(2)
• Spatially-Adaptive Filter Units for Deep Neural Networks
• DeepNav: Learning to Navigate Large Cities
• Ordered Pooling of Optical Flow Sequences for Action Recognition
• Multimodal Explanations by Predicting Counterfactuality in Videos
• DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
• Unsupervised Learning of Important Objects from First-Person Videos
• Recycle deep features for better object detection
• Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
• Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis
• Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
• A Parallel Approach for Real-Time Face Recognition from a Large Database
• Object Detection with Mask-based Feature Encoding
• ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs
• Learning Abstract Classes using Deep Learning
• When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition
• Transferring and Regularizing Prediction for Semantic Segmentation
• Approximate Policy Iteration for Budgeted Semantic Video Segmentation
• Dense CNN Learning with Equivalent Mappings
• Personality, Culture, and System Factors - Impact on Affective Response to Multimedia
• The Pitfall of Evaluating Performance on Emerging AI Accelerators
• Fully Convolutional Network for Melanoma Diagnostics
• Bringing Impressionism to Life with Neural Style Transfer in Come Swim
• Person Re-Identification via Recurrent Feature Aggregation
• RoboSherlock: Cognition-enabled Robot Perception for Everyday Manipulation Tasks
• CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression
• Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly
• GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
• Fine-Grained Energy and Performance Profiling framework for Deep Convolutional Neural Networks
• LOH and behold: Web-scale visual search, recommendation and clustering using Locally Optimized Hashing
• Random Temporal Skipping for Multirate Video Analysis
• Automatic Handgun Detection Alarm in Videos Using Deep Learning
• Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
• Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions
• Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition
• What can we learn about CNNs from a large scale controlled object dataset?
• Semantic-level Decentralized Multi-Robot Decision-Making using Probabilistic Macro-Observations
• Hierarchical approach to classify food scenes in egocentric photo-streams
• Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification
• Weakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma Images
• Revisiting IM2GPS in the Deep Learning Era
• Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling
• Cloudroid: A Cloud Framework for Transparent and QoS-aware Robotic Computation Outsourcing
• Fast Parallel SAME Gibbs Sampling on General Discrete Bayesian Networks
• Design of Kernels in Convolutional Neural Networks for Image Classification
• End-to-End Saliency Mapping via Probability Distribution Prediction
• Vis-DSS: An Open-Source toolkit for Visual Data Selection and Summarization
• Similarity-based Text Recognition by Deeply Supervised Siamese Network
• Ensemble of Part Detectors for Simultaneous Classification and Localization
• Discriminatively Learned Hierarchical Rank Pooling Networks
• Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild
• Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks
• MLitB: Machine Learning in the Browser
• Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images
• Recommending Outfits from Personal Closet
• Image-based Recommendations on Styles and Substitutes
• GM-Net: Learning Features with More Efficiency
• Persistent Evidence of Local Image Properties in Generic ConvNets
• Occluded Joints Recovery in 3D Human Pose Estimation based on Distance Matrix
• Neural Signatures for Licence Plate Re-identification
• Distance to Center of Mass Encoding for Instance Segmentation
• BENCHIP: Benchmarking Intelligence Processors
• Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning
• Mining Mid-level Visual Patterns with Deep CNN Activations
• Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
• A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
• Visualizing Image Content to Explain Novel Image Discovery
• Automatic Real-time Background Cut for Portrait Videos
• StuffNet: Using 'Stuff' to Improve Object Detection
• Accelerating BLAS and LAPACK via Efficient Floating Point Architecture Design
• RDMAbox : Optimizing RDMA for Memory Intensive Workloads
• Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network
• AFFACT - Alignment-Free Facial Attribute Classification Technique
• Stochastic Gradient MCMC with Stale Gradients
• Multi-scale recognition with DAG-CNNs
• On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
• Cappuccino: Efficient Inference Software Synthesis for Mobile System-on-Chips
• Recognizing and Curating Photo Albums via Event-Specific Image Importance
• Accurate and Efficient Similarity Search for Large Scale Face Recognition
• Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
• Generic 3D Convolutional Fusion for image restoration
• Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
• Integrated Deep and Shallow Networks for Salient Object Detection
• Efficient architecture for deep neural networks with heterogeneous sensitivity
• Progressive Representation Adaptation for Weakly Supervised Object Localization
• Multi-Mode Inference Engine for Convolutional Neural Networks
• Stacked Approximated Regression Machine: A Simple Deep Learning Approach
• Fast Learning and Prediction for Object Detection using Whitened CNN Features
• Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
• GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification
• Better Exploiting OS-CNNs for Better Event Recognition in Images
• Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
• Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
• Data-parallel distributed training of very large models beyond GPU capacity
• High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
• Integrating Multiple Receptive Fields through Grouped Active Convolution
• A Transfer Learning based Feature-Weak-Relevant Method for Image Clustering
• ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
• Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
• Confidence Inference for Focused Learning in Stereo Matching
• M-PACT: An Open Source Platform for Repeatable Activity Classification Research
• Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
• A generic and fast C++ optimization framework
• Learning Image Matching by Simply Watching Video
• Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation
• IBM Deep Learning Service
• Deep Learning At Scale and At Ease
• Hierarchy-Dependent Cross-Platform Multi-View Feature Learning for Venue Category Prediction
• Convolutional Channel Features
• Speeding-up Age Estimation in Intelligent Demographics System via Network Optimization
• Pose estimator and tracker using temporal flow maps for limbs
• Input Aggregated Network for Face Video Representation
• Deep Saliency with Encoded Low level Distance Map and High Level Features
• Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation
• Scalable Discrete Supervised Hash Learning with Asymmetric Matrix Factorization
• Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing
• Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild
• Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries
• Progressively Diffused Networks for Semantic Image Segmentation
• Wearing Many (Social) Hats: How Different are Your Different Social Network Personae?
• What does fault tolerant Deep Learning need from MPI?
• Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks
• weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming
• Hierarchical Spatial Sum-Product Networks for Action Recognition in Still Images
• 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
• Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement
• Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
• Recurrent Flow-Guided Semantic Forecasting
• Full-Stack Filters to Build Minimum Viable CNNs
• Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained "Hard Faces"
• Probe-based Rapid Hybrid Hyperspectral and Tissue Surface Imaging Aided by Fully Convolutional Networks
• Integrating Deep Features for Material Recognition
• Deeply Exploit Depth Information for Object Detection
• One-Shot Fine-Grained Instance Retrieval
• The Compressed Model of Residual CNDS
• Image Matching via Loopy RNN
• Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks
• Reflectance Adaptive Filtering Improves Intrinsic Image Estimation
• Learning Rich Representations For Structured Visual Prediction Tasks
• Set2Model Networks: Learning Discriminatively To Learn Generative Models
• Learning to Segment Object Candidates via Recursive Neural Networks
• Selfie Detection by Synergy-Constraint Based Convolutional Neural Network
• Gaussian Temporal Awareness Networks for Action Localization
• Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition
• When Saliency Meets Sentiment: Understanding How Image Content Invokes Emotion and Sentiment
• Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
• Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison
• Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
• Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
• Video Semantic Object Segmentation by Self-Adaptation of DCNN
• Subset Feature Learning for Fine-Grained Category Classification
• Visual Recognition of Paper Analytical Device Images for Detection of Falsified Pharmaceuticals
• On Large-Scale Retrieval: Binary or n-ary Coding?
• RAM: A Region-Aware Deep Model for Vehicle Re-Identification
• Automatic Estimation of Fetal Abdominal Circumference from Ultrasound Images
• DeepMI: A Mutual Information Based Framework For Unsupervised Deep Learning of Tasks
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
• It All Matters: Reporting Accuracy, Inference Time and Power Consumption for Face Emotion Recognition on Embedded Systems
• Can Image Retrieval help Visual Saliency Detection?
• Learning and Fusing Multimodal Features from and for Multi-task Facial Computing
• Effective Combination of Language and Vision Through Model Composition and the R-CCA Method
• RGB-D Salient Object Detection Based on Discriminative Cross-modal Transfer Learning
• In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization
• Slim-DP: A Light Communication Data Parallelism for DNN
• Learn-Memorize-Recall-Reduce A Robotic Cloud Computing Paradigm
• Utility in Fashion with implicit feedback
• Object Specific Deep Learning Feature and Its Application to Face Detection
• LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
• SHOE: Supervised Hashing with Output Embeddings
• Detecting Engagement in Egocentric Video
• Variational reaction-diffusion systems for semantic segmentation
• P-CapsNets: a General Form of Convolutional Neural Networks
• Structure Learning of Deep Neural Networks with Q-Learning
• DCI: Discriminative and Contrast Invertible Descriptor
• Prune the Convolutional Neural Networks with Sparse Shrink
• Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance
• Temporal Action Detection by Joint Identification-Verification
• Transform-Invariant Convolutional Neural Networks for Image Classification and Search
• Fusing Hierarchical Convolutional Features for Human Body Segmentation and Clothing Fashion Classification
• Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks
• Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
• Residual-CNDS for Grand Challenge Scene Dataset
• Network Lens: Node Classification in Topologically Heterogeneous Networks
• Multi-Level Network for High-Speed Multi-Person Pose Estimation
• Dense Fusion Classmate Network for Land Cover Classification
• Neuromodulated Goal-Driven Perception in Uncertain Domains
• Towards an "In-the-Wild" Emotion Dataset Using a Game-based Framework
• Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
• Joint Learning of Distributed Representations for Images and Texts
• Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos
• Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing
• A Face Recognition Signature Combining Patch-based Features with Soft Facial Attributes
• Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian
• Learning to Remove Multipath Distortions in Time-of-Flight Range Images for a Robotic Arm Setup
• Exploring the Vision Processing Unit as Co-processor for Inference
• Character Proposal Network for Robust Text Extraction
• Non-iterative Label Propagation in Optimal Leading Forest
• Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment
• Learning Discriminative Features with Class Encoder
• On the Modeling of Error Functions as High Dimensional Landscapes for Weight Initialization in Learning Networks
• Bosch Deep Learning Hardware Benchmark
• Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
• Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?
• End-to-End Data Visualization by Metric Learning and Coordinate Transformation
• Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art
• Two-stream convolutional neural network for accurate RGB-D fingertip detection using depth and edge information
• Comparison of the Deep-Learning-Based Automated Segmentation Methods for the Head Sectioned Images of the Virtual Korean Human Project
• Deep Convolutional Poses for Human Interaction Recognition in Monocular Videos
• PrototypeML: A Neural Network Integrated Design and Development Environment
• Flexible numerical optimization with ensmallen
• DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks
• DCNNs: A Transfer Learning comparison of Full Weapon Family threat detection for Dual-Energy X-Ray Baggage Imagery
• Seeing into Darkness: Scotopic Visual Recognition
• VideoMCC: a New Benchmark for Video Comprehension
• Exploring Temporal Information for Improved Video Understanding
• Triplet-based Deep Similarity Learning for Person Re-Identification
• Minimally Supervised Feature Selection for Classification (Master's Thesis, University Politehnica of Bucharest)
• Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks
• MyCaffe: A Complete C# Re-Write of Caffe with Reinforcement Learning
• Fast Face Image Synthesis with Minimal Training
• Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks
• Implicit Sparse Code Hashing
• Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition
• Multimodal Skip-gram Using Convolutional Pseudowords
• MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning
• Constraint-free Natural Image Reconstruction from fMRI Signals Based on Convolutional Neural Network
• Deep Learning Approximation: Zero-Shot Neural Network Speedup
• Should I use TensorFlow
• MoE-SPNet: A Mixture-of-Experts Scene Parsing Network
• Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
• Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions
• Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks
• Learning To Score Olympic Events
• Handwritten digit string recognition by combination of residual network and RNN-CTC
• Automatic Synchronization of Multi-User Photo Galleries
• Homomorphic Parameter Compression for Distributed Deep Learning Training
• Evaluating (and improving) the correspondence between deep neural networks and human representations
• Fixed-point Factorized Networks
• SDN Flow Entry Management Using Reinforcement Learning
• Pseudo-positive regularization for deep person re-identification
• MATIC: Learning Around Errors for Efficient Low-Voltage Neural Network Accelerators
• Efficient Semantic Segmentation for Visual Bird's-eye View Interpretation
• Superpixel-based Semantic Segmentation Trained by Statistical Process Control
• Self-Paced Deep Regression Forests for Facial Age Estimation
• A Hybrid Supervised-unsupervised Method on Image Topic Visualization with Convolutional Neural Network and LDA
• Deep Semantic Hashing with Generative Adversarial Networks
• Large-Scale Mapping of Human Activity using Geo-Tagged Videos
• Am I a Baller? Basketball Performance Assessment from First-Person Videos
• GaDei: On Scale-up Training As A Service For Deep Learning
• clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
• Active Learning for Structured Prediction from Partially Labeled Data
• Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
• A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
• LOTS about Attacking Deep Features
• A CNN Cascade for Landmark Guided Semantic Part Segmentation
• Domain Adaptation with L2 constraints for classifying images from different endoscope systems
• Inferring Restaurant Styles by Mining Crowd Sourced Photos from User-Review Websites
• Approximate Random Dropout
• Action Quality Assessment Across Multiple Actions