Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

Abstract

The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-the-art operational ROVER algorithm for precipitation nowcasting.

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• On the difficulty of training Recurrent Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Fully Convolutional Networks for Semantic Segmentation
• Unsupervised Learning of Video Representations using LSTMs
• Theano: new features and speed improvements
• Video (language) modeling: a baseline for generative models of natural videos

Cited by in corpus (725)

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• Physics-informed learning of governing equations from scarce data
• Human Action Recognition from Various Data Modalities: A Review
• Recent Advances in Recurrent Neural Networks
• FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• Dynamic Filter Networks
• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
• BRITS: Bidirectional Recurrent Imputation for Time Series
• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• A Review on Deep Learning Techniques for Video Prediction
• MetNet: A Neural Weather Model for Precipitation Forecasting
• Multi-output Bus Travel Time Prediction with Convolutional LSTM Neural Network
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Evaluation of deep learning models for multi-step ahead time series prediction
• Unsupervised Learning for Physical Interaction through Video Prediction
• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
• Spatio-temporal video autoencoder with differentiable memory
• Combining Physically-Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn from Mismatch?
• Neural GPUs Learn Algorithms
• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
• Spatial-Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification
• Stochastic Adversarial Video Prediction
• End-to-End CNN+LSTM Deep Learning Approach for Bearing Fault Diagnosis
• PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction
• Adversarial Text-to-Image Synthesis: A Review
• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
• A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
• Deep Learning for Post-Processing Ensemble Weather Forecasts
• Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTM
• Localizing Anomalies from Weakly-Labeled Videos
• A new prediction method of unsteady wake flow by the hybrid deep neural network
• Transformers for Modeling Physical Systems
• Classification of EEG-Based Brain Connectivity Networks in Schizophrenia Using a Multi-Domain Connectome Convolutional Neural Network
• A Novel Framework for Spatio-Temporal Prediction of Environmental Data Using Deep Learning
• Deep learning via LSTM models for COVID-19 infection forecasting in India
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• Video Transformers: A Survey
• Deep Complex Networks
• Stock Price Prediction Using CNN and LSTM-Based Deep Learning Models
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation
• A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification
• Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Learning for Video Compression
• Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
• Physics-informed neural networks for the shallow-water equations on the sphere
• Learning to Detect Objects with a 1 Megapixel Event Camera
• BigDL: A Distributed Deep Learning Framework for Big Data
• Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020-2022
• LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Recurrent Neural Networks: An Embedded Computing Perspective
• Deep Learning in Mobile and Wireless Networking: A Survey
• Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey
• DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data
• Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data
• Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads
• Path-Restore: Learning Network Path Selection for Image Restoration
• Variable Rate Image Compression with Recurrent Neural Networks
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• Learning to Decompose and Disentangle Representations for Video Prediction
• Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
• Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring
• Learning Molecular Dynamics with Simple Language Model built upon Long Short-Term Memory Neural Network
• Statistical and machine learning ensemble modelling to forecast sea surface temperature
• Factorization tricks for LSTM networks
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM
• AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection
• Discovering state-parameter mappings in subsurface models using generative adversarial networks
• Trellis Networks for Sequence Modeling
• Light Field Salient Object Detection: A Review and Benchmark
• Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
• Exchanging Dual Encoder-Decoder: A New Strategy for Change Detection with Semantic Guidance and Spatial Localization
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning
• Solving inverse problems using conditional invertible neural networks
• Kriging Convolutional Networks
• Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
• PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
• One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
• Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction
• Machine Learning: Algorithms, Models, and Applications
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
• CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke
• MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification
• Exploiting temporal and depth information for multi-frame face anti-spoofing
• Boosting multiple sclerosis lesion segmentation through attention mechanism
• Spatial-Angular Attention Network for Light Field Reconstruction
• FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network
• Long-term Forecasting using Higher Order Tensor RNNs
• Stochastic Variational Video Prediction
• CLEVRER: CoLlision Events for Video REpresentation and Reasoning
• Short-term precipitation prediction using deep learning
• CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
• Unsupervised Deep Learning for IoT Time Series
• Generalizing semi-supervised generative adversarial networks to regression using feature contrasting
• SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
• A review of radar-based nowcasting of precipitation and applicable machine learning techniques
• VideoLSTM Convolves, Attends and Flows for Action Recognition
• Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
• Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
• ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
• On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation
• Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Information
• Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
• Small Sample Learning in Big Data Era
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units
• Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERG
• Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning
• Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data
• Deep Learning Fetal Ultrasound Video Model Match Human Observers in Biometric Measurements
• Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling
• Sequence-to-Sequence Models Can Directly Translate Foreign Speech
• Chasing Ghosts: Instruction Following as Bayesian State Tracking
• Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
• Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
• Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
• Sky Imager-Based Forecast of Solar Irradiance Using Machine Learning
• TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
• A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction
• Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
• A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning
• Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks
• Learning Dynamical Systems from Partial Observations
• ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
• A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection
• End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
• Spatio-Temporal Point Process for Multiple Object Tracking
• A Survey on State-of-the-art Deep Learning Applications and Challenges
• Multi-Grained Spatio-temporal Modeling for Lip-reading
• Cross-Modal Self-Attention Network for Referring Image Segmentation
• Learning Video Object Segmentation with Visual Memory
• Dynamic Occupancy Grid Mapping with Recurrent Neural Networks
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Challenging Machine Learning-based Clone Detectors via Semantic-preserving Code Transformations
• Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
• Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin
• Quality-Gated Convolutional LSTM for Enhancing Compressed Video
• Advancing Learned Video Compression with In-loop Frame Prediction
• Recurrent neural network-based volumetric fluorescence microscopy
• A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
• A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific
• Mobile Video Object Detection with Temporally-Aware Feature Maps
• A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals
• Video Object Segmentation and Tracking: A Survey
• Application of Multi-channel 3D-cube Successive Convolution Network for Convective Storm Nowcasting
• CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
• Revisiting Video Saliency: A Large-scale Benchmark and a New Model
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Neural Predictive Belief Representations
• Annotating Object Instances with a Polygon-RNN
• Temporal Consistency Learning of inter-frames for Video Super-Resolution
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• Deep Idempotent Network for Efficient Single Image Blind Deblurring
• RWF-2000: An Open Large Scale Video Database for Violence Detection
• Towards Binary-Valued Gates for Robust LSTM Training
• Plasma Surrogate Modelling using Fourier Neural Operators
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
• End-to-end Learning of Driving Models from Large-scale Video Datasets
• A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery
• Learning future terrorist targets through temporal meta-graphs
• Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks
• Joint Denoising and Demosaicking with Green Channel Prior for Real-world Burst Images
• Deep Watershed Transform for Instance Segmentation
• Detail-revealing Deep Video Super-resolution
• Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
• Recovery of Future Data via Convolution Nuclear Norm Minimization
• Comparing recurrent and convolutional neural networks for predicting wave propagation
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey
• Context-self contrastive pretraining for crop type semantic segmentation
• Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Single-frame Regularization for Temporally Stable CNNs
• CAVE: Cerebral Artery-Vein Segmentation in Digital Subtraction Angiography
• Unsupervised Learning of Long-Term Motion Dynamics for Videos
• To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles
• FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equations
• Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks
• Future Semantic Segmentation with Convolutional LSTM
• Short-term daily precipitation forecasting with seasonally-integrated autoencoder
• VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
• Pancreas Segmentation in CT and MRI Images via Domain Specific Network Designing and Recurrent Neural Contextual Learning
• Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference
• CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
• HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
• One shot PACS: Patient specific Anatomic Context and Shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTs
• Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning
• Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
• PreCNet: Next-Frame Video Prediction Based on Predictive Coding
• Earth System Data Cubes: Avenues for advancing Earth system research
• A neural network-based scale-adaptive cloud-fraction scheme for GCMs
• DeepSignals: Predicting Intent of Drivers Through Visual Signals
• Deep learning with 4D spatio-temporal data representations for OCT-based force estimation
• Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network
• QMDP-Net: Deep Learning for Planning under Partial Observability
• RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
• Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects
• D-GAN: Deep Generative Adversarial Nets for Spatio-Temporal Prediction
• Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts
• TDIOT: Target-driven Inference for Deep Video Object Tracking
• Simple vs complex temporal recurrences for video saliency prediction
• Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation
• Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective
• Physics-informed generative neural network: an application to troposphere temperature prediction
• Deep Learning Based Forecasting of Indian Summer Monsoon Rainfall
• ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
• MGANet: A Robust Model for Quality Enhancement of Compressed Video
• Learning Implicitly Recurrent CNNs Through Parameter Sharing
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition
• Spatially Adaptive Computation Time for Residual Networks
• Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array
• Gaussian Kernel Mixture Network for Single Image Defocus Deblurring
• Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
• Learning to Deblur and Generate High Frame Rate Video with an Event Camera
• Budget-aware Semi-Supervised Semantic and Instance Segmentation
• RNDiff: Rainfall nowcasting with Condition Diffusion Model
• DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
• Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses
• Towards Stable Co-saliency Detection and Object Co-segmentation
• CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds
• VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
• Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
• Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
• Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
• ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration
• Temporal-Spatial Feature Pyramid for Video Saliency Detection
• Rotor Localization and Phase Mapping of Cardiac Excitation Waves using Deep Neural Networks
• Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
• Cloud Cover Nowcasting with Deep Learning
• Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment
• Prediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks
• Scale-recurrent Network for Deep Image Deblurring
• Distributed Deep Learning for Precipitation Nowcasting
• TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression
• Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting
• Precipitation Nowcasting with Star-Bridge Networks
• Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data
• A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
• Cross-City Transfer Learning for Deep Spatio-Temporal Prediction
• Metric-Based Few-Shot Learning for Video Action Recognition
• Convolution, attention and structure embedding
• Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
• Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation
• Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network
• Face Mask Extraction in Video Sequence
• Dynamic Face Video Segmentation via Reinforcement Learning
• Artificial neural networks ensemble methodology to predict significant wave height
• On The Stability of Video Detection and Tracking
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• Attention-aware non-rigid image registration for accelerated MR imaging
• Robotic Table Tennis: A Case Study into a High Speed Learning System
• DONet: Dual Objective Networks for Skin Lesion Segmentation
• Augmenting correlation structures in spatial data using deep generative models
• HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
• Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results
• Enhancing Road Safety through Accurate Detection of Hazardous Driving Behaviors with Graph Convolutional Recurrent Networks
• Adversarial multi-task underwater acoustic target recognition: towards robustness against various influential factors
• Localized convolutional neural networks for geospatial wind forecasting
• Neural Network-Based Processing and Reconstruction of Compromised Biophotonic Image Data
• PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction
• A Bayesian Deep Learning Approach to Near-Term Climate Prediction
• Towards Learning to Detect and Predict Contact Events on Vision-based Tactile Sensors
• PredNet and Predictive Coding: A Critical Review
• Solving Raven's Progressive Matrices with Neural Networks
• (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment
• MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weather
• Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
• MixNet: Structured Deep Neural Motion Prediction for Autonomous Racing
• Progressive Image Deraining Networks: A Better and Simpler Baseline
• RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous Driving
• ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles
• Can Active Memory Replace Attention?
• Inception-inspired LSTM for Next-frame Video Prediction
• Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
• Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
• Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
• Instance Embedding Transfer to Unsupervised Video Object Segmentation
• SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
• Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics
• Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications
• SLANTS: Sequential Adaptive Nonlinear Modeling of Vector Time Series
• DeepFEA: Deep Learning for Prediction of Transient Finite Element Analysis Solutions
• Scaling Autoregressive Video Models
• Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
• Where and What: Driver Attention-based Object Detection
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks
• Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing
• Hard Encoding of Physics for Learning Spatiotemporal Dynamics
• Spatial-Temporal Dynamic Graph Attention Networks for Ride-hailing Demand Prediction
• Exploiting temporal consistency for real-time video depth estimation
• Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
• To Create What You Tell: Generating Videos from Captions
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking
• Physics-informed Tensor-train ConvLSTM for Volumetric Velocity Forecasting of Loop Current
• Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Video Anomaly Detection via Prediction Network with Enhanced Spatio-Temporal Memory Exchange
• Deep learning of many-body observables and quantum information scrambling
• Hierarchical Opacity Propagation for Image Matting
• Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification
• Deep recurrent networks predicting the gap evolution in adiabatic quantum computing
• Road Segmentation Using CNN with GRU
• Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association
• Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction
• PDE-Driven Spatiotemporal Disentanglement
• Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
• Spatial-Temporal Self-Attention Network for Flow Prediction
• A Dual Sensor Computational Camera for High Quality Dark Videography
• mEBAL2 Database and Benchmark: Image-based Multispectral Eyeblink Detection
• Mutual Suppression Network for Video Prediction using Disentangled Features
• Periodic Residual Learning for Crowd Flow Forecasting
• Precise Forecasting of Sky Images Using Spatial Warping
• Improving Subseasonal Forecasting in the Western U.S. with Machine Learning
• Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction
• The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
• Urban Anomaly Analytics: Description, Detection, and Prediction
• Predictive and Causal Implications of using Shapley Value for Model Interpretation
• Needle Tip Force Estimation using an OCT Fiber and a Fused convGRU-CNN Architecture
• Recurrent Back-Projection Network for Video Super-Resolution
• Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction
• Learning Synergistic Attention for Light Field Salient Object Detection
• Gaussian Process Nowcasting: Application to COVID-19 Mortality Reporting
• VizADS-B: Analyzing Sequences of ADS-B Images Using Explainable Convolutional LSTM Encoder-Decoder to Detect Cyber Attacks
• What Face and Body Shapes Can Tell About Height
• Unlocking the Potential of Deep Learning in Peak-Hour Series Forecasting
• Interpretable Spatio-temporal Attention for Video Action Recognition
• Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
• Unsupervised Motion Representation Learning with Capsule Autoencoders
• Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
• LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
• Time Series Analysis and Forecasting of COVID-19 Cases Using LSTM and ARIMA Models
• Linguistic Structure Guided Context Modeling for Referring Image Segmentation
• Neural Video Compression using Spatio-Temporal Priors
• Recurrent Filter Learning for Visual Tracking
• Deep Learning for Optimal Deployment of UAVs with Visible Light Communications
• Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
• SFTformer: A Spatial-Frequency-Temporal Correlation-Decoupling Transformer for Radar Echo Extrapolation
• Learning Long-Term Style-Preserving Blind Video Temporal Consistency
• Vehicular Intrusion Detection System for Controller Area Network: A Comprehensive Survey and Evaluation
• Learning to Compress Videos without Computing Motion
• Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
• A Dilated Inception Network for Visual Saliency Prediction
• Flow-Grounded Spatial-Temporal Video Prediction from Still Images
• A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction
• DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
• The Neural Painter: Multi-Turn Image Generation
• Effective Abstract Reasoning with Dual-Contrast Network
• End-to-end Person Search Sequentially Trained on Aggregated Dataset
• MT-IceNet -- A Spatial and Multi-Temporal Deep Learning Model for Arctic Sea Ice Forecasting
• SGRU: A High-Performance Structured Gated Recurrent Unit for Traffic Flow Prediction
• Multitask Learning in Minimally Invasive Surgical Vision: A Review
• A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
• Open-World Stereo Video Matching with Deep RNN
• Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
• MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
• Object and Relation Centric Representations for Push Effect Prediction
• Myocardial Segmentation of Cardiac MRI Sequences with Temporal Consistency for Coronary Artery Disease Diagnosis
• Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series
• Learning Deep Matrix Representations
• Hierarchical Human Parsing with Typed Part-Relation Reasoning
• Efficient Semantic Video Segmentation with Per-frame Inference
• ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
• BUSU-Net: An Ensemble U-Net Framework for Medical Image Segmentation
• Computing a human-like reaction time metric from stable recurrent vision models
• Performing Video Frame Prediction of Microbial Growth with a Recurrent Neural Network
• Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction
• FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems
• Spatio-Temporal Convolutional LSTMs for Tumor Growth Prediction by Learning 4D Longitudinal Patient Data
• Pose Guided Fashion Image Synthesis Using Deep Generative Model
• Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation
• Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
• Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter
• Disentangled Image Matting
• Exploiting Interpretable Patterns for Flow Prediction in Dockless Bike Sharing Systems
• Feature Boosting Network For 3D Pose Estimation
• Relational Long Short-Term Memory for Video Action Recognition
• ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery
• Interpretable Deep Feature Propagation for Early Action Recognition
• Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
• Image Generation from Layout
• Spatiotemporal forecasting of vertical track alignment with exogenous factors
• MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images
• LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
• Forward Prediction for Physical Reasoning
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
• Skeleton Focused Human Activity Recognition in RGB Video
• Deep Neural Networks to Correct Sub-Precision Errors in CFD
• CrevNet: Conditionally Reversible Video Prediction
• RGait-NET: An Effective Network for Recovering Missing Information from Occluded Gait Cycles
• Planning Robot Motion using Deep Visual Prediction
• Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey
• KISS: Keeping It Simple for Scene Text Recognition
• Textual Echo Cancellation
• Non-Local ConvLSTM for Video Compression Artifact Reduction
• Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection
• Order Matters: Shuffling Sequence Generation for Video Prediction
• Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network
• Model predictive control design for dynamical systems learned by Long Short-Term Memory Networks
• Single Image Reflection Removal through Cascaded Refinement
• Temporal Distinct Representation Learning for Action Recognition
• Learning Over Long Time Lags
• Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
• Distributed Heteromodal Split Learning for Vision Aided mmWave Received Power Prediction
• Long Short-Term Attention
• VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
• Simultaneous Energy Harvesting and Gait Recognition using Piezoelectric Energy Harvester
• Streaming Object Detection for 3-D Point Clouds
• Pi-PE: A Pipeline for Pulmonary Embolism Detection using Sparsely Annotated 3D CT Images
• Travel Speed Prediction with a Hierarchical Convolutional Neural Network and Long Short-Term Memory Model Framework
• Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab
• RA V-Net: Deep learning network for automated liver segmentation
• Predicting Weather Uncertainty with Deep Convnets
• Dual Recurrent Attention Units for Visual Question Answering
• Spatiotemporal Entropy Model is All You Need for Learned Video Compression
• FADEC: FPGA-based Acceleration of Video Depth Estimation by HW/SW Co-design
• Deep Vision in Analysis and Recognition of Radar Data: Achievements, Advancements and Challenges
• SceneGen: Learning to Generate Realistic Traffic Scenes
• A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Inconsistent illusory motion in predictive coding deep neural networks
• Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests
• Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder
• Feature Engineering with Regularity Structures
• Epileptic Seizure Classification with Symmetric and Hybrid Bilinear Models
• Do Neural Networks for Segmentation Understand Insideness?
• Simple Video Generation using Neural ODEs
• Trajectory Prediction using Equivariant Continuous Convolution
• Topological Map Extraction from Overhead Images
• Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
• Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
• Deep RNN Framework for Visual Sequential Applications
• Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction
• Deep MRI Reconstruction with Radial Subsampling
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Machine learning spatio-temporal epidemiological model to evaluate Germany-county-level COVID-19 risk
• Composite Neural Network: Theory and Application to PM2.5 Prediction
• PISEP^2: Pseudo Image Sequence Evolution based 3D Pose Prediction
• Deep-MAPS: Machine Learning based Mobile Air Pollution Sensing
• Exploiting deep learning in forecasting the occurrence of severe haze in Southeast Asia
• Compute, Time and Energy Characterization of Encoder-Decoder Networks with Automatic Mixed Precision Training
• SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
• Few-shot Scene-adaptive Anomaly Detection
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
• Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation
• Cascading Convolutional Temporal Colour Constancy
• FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting
• RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions
• Different eigenvalue distributions encode the same temporal tasks in recurrent neural networks
• Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale
• Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness
• Recurrent U-net for automatic pelvic floor muscle segmentation on 3D ultrasound
• Frame-To-Frame Consistent Semantic Segmentation
• Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network
• Estimating People Flows to Better Count Them in Crowded Scenes
• Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
• RMSim: Controlled Respiratory Motion Simulation on Static Patient Scans
• Stacked Neural Networks for end-to-end ciliary motion analysis
• A Structured Model For Action Detection
• CNN aided Weighted Interpolation for Channel Estimation in Vehicular Communications
• Two-stream Convolutional Networks for Multi-frame Face Anti-spoofing
• Assessing the Performance of Deep Learning Algorithms for Newsvendor Problem
• SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation
• Climate Modeling with Neural Diffusion Equations
• Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks
• SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments
• Making a Case for 3D Convolutions for Object Segmentation in Videos
• Deep Motion Blur Removal Using Noisy/Blurry Image Pairs
• A Benchmark for Temporal Color Constancy
• Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
• Uncertainty Quantification of Graph Convolution Neural Network Models of Evolving Processes
• Learning State Representations in Complex Systems with Multimodal Data
• Learned Video Compression via Joint Spatial-Temporal Correlation Exploration
• One-Shot Imitation Filming of Human Motion Videos
• Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
• Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
• 3D Randomized Connection Network with Graph-based Label Inference
• A Temporally-Aware Interpolation Network for Video Frame Inpainting
• Rapid quantification of COVID-19 pneumonia burden from computed tomography with convolutional LSTM networks
• Referring Image Segmentation via Cross-Modal Progressive Comprehension
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods
• KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
• Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
• IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
• TENT: Tensorized Encoder Transformer for Temperature Forecasting
• Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
• DiffusionNet: Accelerating the solution of Time-Dependent partial differential equations using deep learning
• Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks
• An End-to-end Video Text Detector with Online Tracking
• Long Short-Term Memory Spatial Transformer Network
• CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
• RecSal : Deep Recursive Supervision for Visual Saliency Prediction
• ContextVP: Fully Context-Aware Video Prediction
• MoNet: Motion-based Point Cloud Prediction Network
• Learning compact generalizable neural representations supporting perceptual grouping
• Use of 1D-CNN for input data size reduction of LSTM in Hourly Rainfall-Runoff modeling
• Deep Learning Methods for Daily Wildfire Danger Forecasting
• Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
• Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video
• Multi-Service Mobile Traffic Forecasting via Convolutional Long Short-Term Memories
• Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling
• Universal-to-Specific Framework for Complex Action Recognition
• Crowd Density Forecasting by Modeling Patch-based Dynamics
• TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video
• Spatiotemporal deep learning model for citywide air pollution interpolation and prediction
• Self-supervised Depth Denoising Using Lower- and Higher-quality RGB-D sensors
• On the difficulty of learning and predicting the long-term dynamics of bouncing objects
• Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
• An unsupervised long short-term memory neural network for event detection in cell videos
• Spatio-temporal Video Re-localization by Warp LSTM
• A CNN-RNN Architecture for Multi-Label Weather Recognition
• Representing ill-known parts of a numerical model using a machine learning approach
• Deep Learning Based Motion Planning For Autonomous Vehicle Using Spatiotemporal LSTM Network
• Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB
• Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
• A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction
• Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
• Hybrid Scheme of Kinematic Analysis and Lagrangian Koopman Operator Analysis for Short-term Precipitation Forecasting
• An Effective Dynamic Spatio-temporal Framework with Multi-Source Information for Traffic Prediction
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
• STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation
• Learning Event-Based Motion Deblurring
• Future Frame Prediction for Robot-assisted Surgery
• Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
• Temporal Autoencoder with U-Net Style Skip-Connections for Frame Prediction
• Multi-layer Feature Aggregation for Deep Scene Parsing Models
• Wide and Narrow: Video Prediction from Context and Motion
• Two-stage Visual Cues Enhancement Network for Referring Image Segmentation
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• CNN-based Realized Covariance Matrix Forecasting
• STEP: Spatial-Temporal Network Security Event Prediction
• DFPN: Deformable Frame Prediction Network
• Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach
• Unsupervised Hebbian Learning on Point Sets in StarCraft II
• Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time
• Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks
• Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos
• A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes
• Counting People by Estimating People Flows
• Modular Action Concept Grounding in Semantic Video Prediction
• From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
• Latent Neural Differential Equations for Video Generation
• RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
• A Multi-task Two-stream Spatiotemporal Convolutional Neural Network for Convective Storm Nowcasting
• Video captioning with stacked attention and semantic hard pull
• Benchmarking Tropical Cyclone Rapid Intensification with Satellite Images and Attention-based Deep Models
• Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
• AMSI-Based Detection of Malicious PowerShell Code Using Contextual Embeddings
• Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
• Seeing in the dark with recurrent convolutional neural networks
• Neural Allocentric Intuitive Physics Prediction from Real Videos
• Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin
• Temporally Identity-Aware SSD with Attentional LSTM
• Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• Deep Anticipation: Light Weight Intelligent Mobile Sensing in IoT by Recurrent Architecture
• Efficient and Phase-aware Video Super-resolution for Cardiac MRI
• Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism
• Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting
• Learning Various Length Dependence by Dual Recurrent Neural Networks
• DJEnsemble: On the Selection of a Disjoint Ensemble of Deep Learning Black-Box Spatio-Temporal Models
• Coupled Recurrent Network (CRN)
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• Learning Blind Video Temporal Consistency
• ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
• Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework
• Temporal Saliency Adaptation in Egocentric Videos
• T${}^2$-Net: A Semi-supervised Deep Model for Turbulence Forecasting
• Deep Visual Odometry with Adaptive Memory
• Detecting Attended Visual Targets in Video
• Integrating Human Gaze into Attention for Egocentric Activity Recognition
• Feedback Attention for Cell Image Segmentation
• Curriculum Learning for Recurrent Video Object Segmentation
• TENet: Triple Excitation Network for Video Salient Object Detection
• Post-processing Multi-Model Medium-Term Precipitation Forecasts Using Convolutional Neural Networks
• Cross-Modal Progressive Comprehension for Referring Segmentation
• Deformable Kernel Convolutional Network for Video Extreme Super-Resolution
• LIP: Learning Instance Propagation for Video Object Segmentation
• Theoretical Investigation of Composite Neural Network
• Early Estimation of User's Intention of Tele-Operation Using Object Affordance and Hand Motion in a Dual First-Person Vision
• A Non-linear Function-on-Function Model for Regression with Time Series Data
• Recurrent Multimodal Interaction for Referring Image Segmentation
• Learning Scene Dynamics from Point Cloud Sequences
• Segmenting Medical MRI via Recurrent Decoding Cell
• Recurrent Flow-Guided Semantic Forecasting
• Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
• Predicting the Future with Transformational States
• Unsupervised View-Invariant Human Posture Representation
• Multimodal Laryngoscopic Video Analysis for Assisted Diagnosis of Vocal Fold Paralysis
• Joint Spatial and Layer Attention for Convolutional Networks
• Complex Valued Gated Auto-encoder for Video Frame Prediction
• Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments
• Instance-Aware Predictive Navigation in Multi-Agent Environments
• Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation
• Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
• Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems
• Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning
• Mapping high-performance RNNs to in-memory neuromorphic chips
• A Distributed SGD Algorithm with Global Sketching for Deep Learning Training Acceleration
• PGT: A Progressive Method for Training Models on Long Videos
• Efficient Spatialtemporal Context Modeling for Action Recognition
• Multimodal Data Fusion based on the Global Workspace Theory
• Brain Segmentation from k-space with End-to-end Recurrent Attention Network
• Predicting future astronomical events using deep learning
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Unsupervised predictive coding models may explain visual brain representation
• Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series
• Lighting Enhancement Aids Reconstruction of Colonoscopic Surfaces
• Learning Semantic-Aware Dynamics for Video Prediction
• Liquified protein vibrations, classification and cross-paradigm de novo image generation using deep neural networks
• Complete CVDL Methodology for Investigating Hydrodynamic Instabilities
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Spatio-Temporal Tensor Sketching via Adaptive Sampling
• Robustifying Sequential Neural Processes
• Understanding Road Layout from Videos as a Whole
• Pixel-wise object tracking
• Comparison of Different Methods for Time Sequence Prediction in Autonomous Vehicles
• SiamParseNet: Joint Body Parsing and Label Propagation in Infant Movement Videos
• Approximated Bilinear Modules for Temporal Modeling
• Graph Wasserstein Correlation Analysis for Movie Retrieval
• Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone
• Modification method for single-stage object detectors that allows to exploit the temporal behaviour of a scene to improve detection accuracy
• Urban Traffic Flow Forecast Based on FastGCRNN
• VARENN: Graphical representation of spatiotemporal data and application to climate studies
• Unaligned Image-to-Sequence Transformation with Loop Consistency
• Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
• Temporally Folded Convolutional Neural Networks for Sequence Forecasting
• Temporally Consistent Depth Prediction with Flow-Guided Memory Units
• A Hybrid 3DCNN and 3DC-LSTM based model for 4D Spatio-temporal fMRI data: An ABIDE Autism Classification study
• An investigation of model-free planning
• Nearest-Neighbor Neural Networks for Geostatistics
• Cubic LSTMs for Video Prediction
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
• FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting
• Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
• Visual-Relation Conscious Image Generation from Structured-Text
• Comparing linear structure-based and data-driven latent spatial representations for sequence prediction
• In Defense of LSTMs for Addressing Multiple Instance Learning Problems
• IoT Network Behavioral Fingerprint Inference with Limited Network Trace for Cyber Investigation: A Meta Learning Approach
• Spatio-Temporal Deep Learning Models for Tip Force Estimation During Needle Insertion
• Guided Feature Selection for Deep Visual Odometry
• Recurrent Existence Determination Through Policy Optimization
• Semi-supervised estimation of event temporal length for cell event detection
• Generative Memorize-Then-Recall framework for low bit-rate Surveillance Video Compression
• ARMA Nets: Expanding Receptive Field for Dense Prediction
• Deep Variational Luenberger-type Observer for Stochastic Video Prediction
• Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks
• CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
• Model Linkage Selection for Cooperative Learning
• Learning to infer in recurrent biological networks
• Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks
• LORCK: Learnable Object-Resembling Convolution Kernels
• FADACS: A Few-shot Adversarial Domain Adaptation Architecture for Context-Aware Parking Availability Sensing
• A Study on Trees's Knots Prediction from their Bark Outer-Shape
• Recurrent convolutional neural network for the surrogate modeling of subsurface flow simulation
• Deep Photovoltaic Nowcasting
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
• CASU2Net: Cascaded Unification Network by a Two-step Early Fusion for Fault Detection in Offshore Wind Turbines
• Predictive Process Model Monitoring using Recurrent Neural Networks
• A Novel Deep ML Architecture by Integrating Visual Simultaneous Localization and Mapping (vSLAM) into Mask R-CNN for Real-time Surgical Video Analysis
• Deep Convolution for Irregularly Sampled Temporal Point Clouds
• Space Time Recurrent Memory Network
• Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
• IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination
• Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks
• Stochastic Dynamics for Video Infilling
• Novel EEG based Schizophrenia Detection with IoMT Framework for Smart Healthcare
• Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction
• SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• Combining Individual and Joint Networking Behavior for Intelligent IoT Analytics
• Rethinking the Form of Latent States in Image Captioning
• Taylor saves for later: disentanglement for video prediction using Taylor representation
• Semi-tied Units for Efficient Gating in LSTM and Highway Networks
• Anomaly Detection in Video Sequences: A Benchmark and Computational Model
• From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting
• Improving the Authentication with Built-in Camera Protocol Using Built-in Motion Sensors: A Deep Learning Solution
• Predicting Future Opioid Incidences Today
• Unsupervised Abstract Reasoning for Raven's Problem Matrices
• Improving the Thermal Infrared Monitoring of Volcanoes: A Deep Learning Approach for Intermittent Image Series
• Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
• ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting
• Machine Learning Forecasting of Active Nematics
• Adaptive Future Frame Prediction with Ensemble Network
• Deep Sequence Learning for Accurate Gestational Age Estimation from a $\$$25 Doppler Device
• Unsupervised learning of the brain connectivity dynamic using residual D-net
• Joint Extraction of Entity and Relation with Information Redundancy Elimination
• HECT: High-Dimensional Ensemble Consistency Testing for Climate Models