Two-Stream Convolutional Networks for Action Recognition in Videos
arXiv:1406.2199
Abstract
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.
References in corpus (3)
Cited by in corpus (979)
- Res2Net: A New Multi-scale Backbone Architecture
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
- Deep Facial Expression Recognition: A Survey
- Unsupervised Learning of Video Representations using LSTMs
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
- Anabranch Network for Camouflaged Object Segmentation
- Video Salient Object Detection via Fully Convolutional Networks
- The THUMOS Challenge on Action Recognition for Videos "in the Wild"
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
- Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- Human Action Recognition from Various Data Modalities: A Review
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Contrastive Multiview Coding
- A scoping review of transfer learning research on medical image analysis using ImageNet
- Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
- An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
- Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
- Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
- Towards Good Practices for Very Deep Two-Stream ConvNets
- Deep multi-scale video prediction beyond mean square error
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Action Recognition using Visual Attention
- Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
- Recent Advances in Convolutional Neural Networks
- Rank Pooling for Action Recognition
- A Review on Deep Learning Techniques for Video Prediction
- Video (language) modeling: a baseline for generative models of natural videos
- Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification
- Self-supervised Co-training for Video Representation Learning
- Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics
- Visual Question Answering: Datasets, Algorithms, and Future Challenges
- A Deep Learning Framework for Assessing Physical Rehabilitation Exercises
- SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos
- Learnable pooling with Context Gating for video classification
- A Survey on Content-Aware Video Analysis for Sports
- Learning Video Representations using Contrastive Bidirectional Transformer
- Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects
- Motion-Attentive Transition for Zero-Shot Video Object Segmentation
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Learning Longer Memory in Recurrent Neural Networks
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
- Sequence to Sequence -- Video to Text
- Describing Videos by Exploiting Temporal Structure
- Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
- Learning a Text-Video Embedding from Incomplete and Heterogeneous Data
- TSM: Temporal Shift Module for Efficient Video Understanding
- Discrimination-aware Channel Pruning for Deep Neural Networks
- Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Audiovisual SlowFast Networks for Video Recognition
- Discrimination-aware Network Pruning for Deep Model Compression
- FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos
- Non-local Neural Networks
- Delving Deeper into Convolutional Networks for Learning Video Representations
- SlowFast Networks for Video Recognition
- MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language
- Deformable Kernel Networks for Joint Image Filtering
- Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
- Temporal Action Detection with Structured Segment Networks
- Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
- Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
- Long-term Temporal Convolutions for Action Recognition
- Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
- Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
- Semantic-Aware Scene Recognition
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
- Drivers Drowsiness Detection using Condition-Adaptive Representation Learning Framework
- Recurrent Mixture Density Network for Spatiotemporal Visual Attention
- Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
- MoVi: A Large Multipurpose Motion and Video Dataset
- Motion-Aware Feature for Improved Video Anomaly Detection
- A Comprehensive Study of Deep Video Action Recognition
- Recent Advances in Deep Learning: An Overview
- Evaluating Two-Stream CNN for Video Classification
- Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
- You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
- Semantics for Robotic Mapping, Perception and Interaction: A Survey
- Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
- What Do We Understand About Convolutional Networks?
- ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild
- ROAD: The ROad event Awareness Dataset for Autonomous Driving
- Hidden Two-Stream Convolutional Networks for Action Recognition
- A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation
- Motion-driven Visual Tempo Learning for Video-based Action Recognition
- Rethinking ImageNet Pre-training
- Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM
- An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
- PP-LCNet: A Lightweight CPU Convolutional Neural Network
- SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
- Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks
- Unsupervised Learning of View-invariant Action Representations
- Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
- A Survey on 3D Skeleton-Based Action Recognition Using Learning Method
- Object Level Visual Reasoning in Videos
- Learning with privileged information via adversarial discriminative modality distillation
- Dynamic Sampling Networks for Efficient Action Recognition in Videos
- Exploiting deep residual networks for human action recognition from skeletal data
- Flowing ConvNets for Human Pose Estimation in Videos
- Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
- Video Classification with Channel-Separated Convolutional Networks
- Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
- RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data
- End-to-End Multi-Channel Speech Separation
- Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans
- Synthetic Humans for Action Recognition from Unseen Viewpoints
- Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
- Deep Learning for Video Classification and Captioning
- Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
- Analyzing Human-Human Interactions: A Survey
- Early Melanoma Diagnosis with Sequential Dermoscopic Images
- Dynamic Gesture Recognition by Using CNNs and Star RGB: a Temporal Information Condensation
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation
- Learning to track for spatio-temporal action localization
- Convolutional Invasion and Expansion Networks for Tumor Growth Prediction
- Contextual Action Recognition with R*CNN
- Future Frame Prediction for Anomaly Detection -- A New Baseline
- Machine Learning for recognition of minerals from multispectral data
- Generalized Domain Conditioned Adaptation Network
- PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
- Human Action Localization with Sparse Spatial Supervision
- Relation Networks for Object Detection
- Bilinear CNNs for Fine-grained Visual Recognition
- Infrared and 3D skeleton feature fusion for RGB-D action recognition
- Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
- Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
- BodyNet: Volumetric Inference of 3D Human Body Shapes
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
- Spatial Transformer Networks
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
- STM: SpatioTemporal and Motion Encoding for Action Recognition
- Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey
- Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensions
- Multi-modal Deep Analysis for Multimedia
- Action Recognition with Image Based CNN Features
- Cascaded Boundary Regression for Temporal Action Detection
- Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos
- HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild
- StructureFlow: Image Inpainting via Structure-aware Appearance Flow
- An Image is Worth 16x16 Words, What is a Video Worth?
- Multiscale Vision Transformers
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
- Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
- Real-time Action Recognition with Enhanced Motion Vector CNNs
- Temporal Segment Networks for Action Recognition in Videos
- Learnable Gated Temporal Shift Module for Deep Video Inpainting
- autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients
- Multi-modal Fusion for Single-Stage Continuous Gesture Recognition
- Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors
- STFCN: Spatio-Temporal FCN for Semantic Video Segmentation
- Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
- Video Representation Learning by Dense Predictive Coding
- Cognitively-Inspired Model for Incremental Learning Using a Few Examples
- Skeleton-based Relational Reasoning for Group Activity Analysis
- VideoMix: Rethinking Data Augmentation for Video Classification
- V4D:4D Convolutional Neural Networks for Video-level Representation Learning
- Graph Convolutional Networks for Temporal Action Localization
- On the effectiveness of task granularity for transfer learning
- Efficient Processing of Deep Neural Networks: A Tutorial and Survey
- Time-series modeling with undecimated fully convolutional neural networks
- Deep Cascaded Bi-Network for Face Hallucination
- VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
- Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videos
- Learning Video Object Segmentation with Visual Memory
- Multi-Grained Spatio-temporal Modeling for Lip-reading
- Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading
- ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
- Appearance-and-Relation Networks for Video Classification
- Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
- Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation
- DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks
- Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
- CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
- Activity Graph Transformer for Temporal Action Localization
- S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
- Action2Vec: A Crossmodal Embedding Approach to Action Learning
- Uncovering Temporal Context for Video Question and Answering
- Video Big Data Analytics in the Cloud: A Reference Architecture, Survey, Opportunities, and Open Research Issues
- Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
- RWF-2000: An Open Large Scale Video Database for Violence Detection
- Skeleton-based Action Recognition of People Handling Objects
- Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
- TEA: Temporal Excitation and Aggregation for Action Recognition
- Predictive-Corrective Networks for Action Detection
- Finding Action Tubes
- VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
- When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
- Semantic Image Networks for Human Action Recognition
- Expanded Parts Model for Semantic Description of Humans in Still Images
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
- Few-shot Action Recognition with Prototype-centered Attentive Learning
- UG Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition
- Temporally smooth online action detection using cycle-consistent future anticipation
- HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
- Objects2action: Classifying and localizing actions without any video example
- Early Action Prediction with Generative Adversarial Networks
- Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model
- Temporal Generative Adversarial Nets with Singular Value Clipping
- BosphorusSign22k Sign Language Recognition Dataset
- TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
- MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
- PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation
- Long-Term Feature Banks for Detailed Video Understanding
- The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
- Deep Learning for Saliency Prediction in Natural Video
- Guided Optical Flow Learning
- Temporal Relational Reasoning in Videos
- RGB-D-based Human Motion Recognition with Deep Learning: A Survey
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization
- End-to-End Incremental Learning
- Learning Spatiotemporal Features via Video and Text Pair Discrimination
- PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
- Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
- Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
- FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
- Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification
- Collaborative Spatio-temporal Feature Learning for Video Action Recognition
- UntrimmedNets for Weakly Supervised Action Recognition and Detection
- Unsupervised Learning of Long-Term Motion Dynamics for Videos
- Spatiotemporal Transformer for Video-based Person Re-identification
- Video Action Understanding
- Image Captioning with Deep Bidirectional LSTMs
- Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
- Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices
- Correlation Net: Spatiotemporal multimodal deep learning for action recognition
- SRG: Snippet Relatedness-based Temporal Action Proposal Generator
- Relation Distillation Networks for Video Object Detection
- Learn to cycle: Time-consistent feature discovery for action recognition
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks
- Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
- Deep learning with 4D spatio-temporal data representations for OCT-based force estimation
- DeepSignals: Predicting Intent of Drivers Through Visual Signals
- STAIR Actions: A Video Dataset of Everyday Home Actions
- Multi-scale 3D Convolution Network for Video Based Person Re-Identification
- TEINet: Towards an Efficient Architecture for Video Recognition
- G-TAD: Sub-Graph Localization for Temporal Action Detection
- Fusing Multi-Stream Deep Networks for Video Classification
- Going Deeper into First-Person Activity Recognition
- What Makes Training Multi-Modal Classification Networks Hard?
- TRAT: Tracking by Attention Using Spatio-Temporal Features
- Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles
- Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
- Learning to Extract Motion from Videos in Convolutional Neural Networks
- Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition
- Distinguishing mirror from glass: A 'big data' approach to material perception
- DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
- Deep Image Spatial Transformation for Person Image Generation
- Simple vs complex temporal recurrences for video saliency prediction
- AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
- Compressing 3DCNNs Based on Tensor Train Decomposition
- CT-Net: Channel Tensorization Network for Video Classification
- Towards more realistic human motion prediction with attention to motion coordination
- 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
- Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition
- TDN: Temporal Difference Networks for Efficient Action Recognition
- Video-based Human Action Recognition using Deep Learning: A Review
- A Survey of Video-based Action Quality Assessment
- Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders
- An Efficient 3D CNN for Action/Object Segmentation in Video
- Cross Modal Distillation for Supervision Transfer
- Temporal Pyramid Network for Action Recognition
- LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN
- Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
- Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
- 3D Gated Recurrent Fusion for Semantic Scene Completion
- Video action detection by learning graph-based spatio-temporal interactions
- Learning with hidden variables
- Revisiting Skeleton-based Action Recognition
- TAM: Temporal Adaptive Module for Video Recognition
- DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
- Action Capsules: Human Skeleton Action Recognition
- Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
- Coarse to Fine Multi-Resolution Temporal Convolutional Network
- Grouped Spatial-Temporal Aggregation for Efficient Action Recognition
- AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition
- BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
- Actionness Estimation Using Hybrid Fully Convolutional Networks
- Global-Local Face Upsampling Network
- Pointly-Supervised Action Localization
- Band Attention Convolutional Networks For Hyperspectral Image Classification
- Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
- Weakly-Supervised Action Localization by Generative Attention Modeling
- AViD Dataset: Anonymized Videos from Diverse Countries
- Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
- Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
- All About Knowledge Graphs for Actions
- Metric-Based Few-Shot Learning for Video Action Recognition
- Unsupervised learning from videos using temporal coherency deep networks
- Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
- Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
- ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
- Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
- Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
- Feedback Graph Convolutional Network for Skeleton-based Action Recognition
- Central Similarity Quantization for Efficient Image and Video Retrieval
- Multi-granularity Generator for Temporal Action Proposal
- From Trailers to Storylines: An Efficient Way to Learn from Movies
- Recognizing American Sign Language Manual Signs from RGB-D Videos
- The Open World of Micro-Videos
- Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
- Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
- Temporal Unet: Sample Level Human Action Recognition using WiFi
- Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
- Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
- Video Representation Learning Using Discriminative Pooling
- Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks
- Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network
- Occlusion Aware Unsupervised Learning of Optical Flow
- Generalized Rank Pooling for Activity Recognition
- Omni-sourced Webly-supervised Learning for Video Recognition
- Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
- Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
- Dense Optical Flow Prediction from a Static Image
- Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
- DDFlow: Learning Optical Flow with Unlabeled Data Distillation
- Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection
- MoViNets: Mobile Video Networks for Efficient Video Recognition
- CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
- Human-Object Interaction Prediction in Videos through Gaze Following
- Hierarchical LSTMs with Adaptive Attention for Visual Captioning
- Temporal Recurrent Networks for Online Action Detection
- PredNet and Predictive Coding: A Critical Review
- Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
- Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
- AdaFrame: Adaptive Frame Selection for Fast Video Recognition
- ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
- Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos
- Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain
- CTAP: Complementary Temporal Action Proposal Generation
- VideoCapsuleNet: A Simplified Network for Action Detection
- Deep Audio-Visual Learning: A Survey
- Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks
- GTA: Global Temporal Attention for Video Action Understanding
- Temporal Action Proposal Generation with Transformers
- MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
- Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
- Sparse Adversarial Perturbations for Videos
- Towards Universal Representation for Unseen Action Recognition
- Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild
- ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
- Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
- REPAIR: Removing Representation Bias by Dataset Resampling
- Deep Adaptive Temporal Pooling for Activity Recognition
- Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning
- An Evaluation of Action Recognition Models on EPIC-Kitchens
- Deep Keyframe Detection in Human Action Videos
- Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos
- Fast Learning of Temporal Action Proposal via Dense Boundary Generator
- Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs
- SelFlow: Self-Supervised Learning of Optical Flow
- Rethinking Full Connectivity in Recurrent Neural Networks
- Mobile Video Action Recognition
- Understanding More about Human and Machine Attention in Deep Neural Networks
- Memory Warps for Learning Long-Term Online Video Representations
- Joint Surgical Gesture and Task Classification with Multi-Task and Multimodal Learning
- WebVision Challenge: Visual Learning and Understanding With Web Data
- Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
- Multimodal Urban Sound Tagging with Spatiotemporal Context
- Actor-Centric Relation Network
- Moviescope: Large-scale Analysis of Movies using Multiple Modalities
- Video-based Person Re-identification with Accumulative Motion Context
- Semantic Video Segmentation by Gated Recurrent Flow Propagation
- OmniNet: A unified architecture for multi-modal multi-task learning
- Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
- A Study on Action Detection in the Wild
- Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
- Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs
- Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
- End-to-end Video-level Representation Learning for Action Recognition
- Multitask Learning of Temporal Connectionism in Convolutional Networks using a Joint Distribution Loss Function to Simultaneously Identify Tools and Phase in Surgical Videos
- IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition
- Learning to Anonymize Faces for Privacy Preserving Action Detection
- Temporal Context Aggregation Network for Temporal Action Proposal Refinement
- A Fast Face Detection Method via Convolutional Neural Network
- Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition
- BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications
- Using Spatial Pooler of Hierarchical Temporal Memory to classify noisy videos with predefined complexity
- Surgical Gesture Recognition with Optical Flow only
- Hierarchical Contrastive Motion Learning for Video Action Recognition
- Action Recognition with Dynamic Image Networks
- Learning Representative Temporal Features for Action Recognition
- Dense Intrinsic Appearance Flow for Human Pose Transfer
- Attend and Interact: Higher-Order Object Interactions for Video Understanding
- TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
- CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
- AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
- Making the Invisible Visible: Action Recognition Through Walls and Occlusions
- When Work Matters: Transforming Classical Network Structures to Graph CNN
- Spatio-Temporal Fusion Networks for Action Recognition
- Automatic learning of gait signatures for people identification
- SF-Net: Single-Frame Supervision for Temporal Action Localization
- Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks
- Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation
- Action Prediction in Humans and Robots
- Identifying and Resisting Adversarial Videos Using Temporal Consistency
- Mutual Suppression Network for Video Prediction using Disentangled Features
- Improving Sign Language Translation with Monolingual Data by Sign Back-Translation
- Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks
- Visual Data Synthesis via GAN for Zero-Shot Video Classification
- ACTION-Net: Multipath Excitation for Action Recognition
- Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
- PaStaNet: Toward Human Activity Knowledge Engine
- Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
- Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
- Deep Tracking: Visual Tracking Using Deep Convolutional Networks
- Two Stream Networks for Self-Supervised Ego-Motion Estimation
- EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
- PruneNet: Channel Pruning via Global Importance
- Nrityantar: Pose oblivious Indian classical dance sequence classification system
- Learning Video Representations from Correspondence Proposals
- DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
- DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
- AR-Net: Adaptive Frame Resolution for Efficient Action Recognition
- Two-stream Fusion Model for Dynamic Hand Gesture Recognition using 3D-CNN and 2D-CNN Optical Flow guided Motion Template
- Unsupervised Motion Representation Learning with Capsule Autoencoders
- Spatio-Temporal Perturbations for Video Attribution
- Video 3D Sampling for Self-supervised Representation Learning
- NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions
- MR-STGN: Multi-Residual Spatio Temporal Graph Network Using Attention Fusion for Patient Action Assessment
- Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
- Unsupervised Learning and Segmentation of Complex Activities from Video
- Listen to Look: Action Recognition by Previewing Audio
- Learning Where to Focus for Efficient Video Object Detection
- ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
- Identifying Visible Actions in Lifestyle Vlogs
- Interpretable Spatio-temporal Attention for Video Action Recognition
- Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
- Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction
- Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
- Im2Flow: Motion Hallucination from Static Images for Action Recognition
- Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition
- Differential Angular Imaging for Material Recognition
- Deep End2End Voxel2Voxel Prediction
- Performing Highly Accurate Predictions Through Convolutional Networks for Actual Telecommunication Challenges
- MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
- Non-local NetVLAD Encoding for Video Classification
- Asynchronous Temporal Fields for Action Recognition
- Object Activity Scene Description, Construction and Recognition
- Zero-Shot Visual Recognition via Bidirectional Latent Embedding
- Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
- Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
- Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
- Temporal Gaussian Mixture Layer for Videos
- ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications
- Real-Time End-to-End Action Detection with Two-Stream Networks
- FASTER Recurrent Networks for Efficient Video Classification
- AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
- PERF-Net: Pose Empowered RGB-Flow Net
- Learning from Temporal Gradient for Semi-supervised Action Recognition
- Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
- ActionFlowNet: Learning Motion Representation for Action Recognition
- Handcrafted Local Features are Convolutional Neural Networks
- Learning Visual Abstract Reasoning through Dual-Stream Networks
- Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
- In the Eye of the Beholder: Gaze and Actions in First Person Video
- Deep Concept-wise Temporal Convolutional Networks for Action Localization
- Conditional Extreme Value Theory for Open Set Video Domain Adaptation
- LapTool-Net: A Contextual Detector of Surgical Tools in Laparoscopic Videos Based on Recurrent Convolutional Neural Networks
- Frankenstein: Learning Deep Face Representations using Small Data
- Embryo staging with weakly-supervised region selection and dynamically-decoded predictions
- Feature Boosting Network For 3D Pose Estimation
- Self-Attention Network for Skeleton-based Human Action Recognition
- Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
- Towards Real-Time Action Recognition on Mobile Devices Using Deep Models
- AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
- Compressed Video Action Recognition with Refined Motion Vector
- Boundary Content Graph Neural Network for Temporal Action Proposal Generation
- Adding Attentiveness to the Neurons in Recurrent Neural Networks
- OccInpFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning
- Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
- Learning to Discriminate Information for Online Action Detection: Analysis and Application
- Intra- and Inter-Action Understanding via Temporal Action Parsing
- Two-Stream AMTnet for Action Detection
- Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
- Face Completion with Semantic Knowledge and Collaborative Adversarial Learning
- Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
- ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
- Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
- Group-Skeleton-Based Human Action Recognition in Complex Events
- Action Completion: A Temporal Model for Moment Detection
- PV-NAS: Practical Neural Architecture Search for Video Recognition
- Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
- AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
- Action Recognition for Depth Video using Multi-view Dynamic Images
- Trear: Transformer-based RGB-D Egocentric Action Recognition
- Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
- Shifted Chunk Transformer for Spatio-Temporal Representational Learning
- Self-supervised Motion Learning from Static Images
- Video Contents Understanding using Deep Neural Networks
- The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
- Real-Time Activity Recognition and Intention Recognition Using a Vision-based Embedded System
- Streamlined Dense Video Captioning
- Deep Tensor Convolution on Multicores
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
- MarioQA: Answering Questions by Watching Gameplay Videos
- High-Resolution Optical Flow from 1D Attention and Correlation
- Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding
- IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
- MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
- Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
- Video-Text Pre-training with Learned Regions
- Order Matters: Shuffling Sequence Generation for Video Prediction
- Video Is Graph: Structured Graph Module for Video Action Recognition
- Learning Fine-grained Features via a CNN Tree for Large-scale Classification
- UC Merced Submission to the ActivityNet Challenge 2016
- Residual Squeeze VGG16
- LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
- Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
- Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
- Real-time End-to-End Federated Learning: An Automotive Case Study
- Relational Long Short-Term Memory for Video Action Recognition
- RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
- Learning to score the figure skating sports videos
- Virtual Piano using Computer Vision
- Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving
- ReHAR: Robust and Efficient Human Activity Recognition
- Transformers for One-Shot Visual Imitation
- VideoSSL: Semi-Supervised Learning for Video Classification
- Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
- Learning the semantic structure of objects from Web supervision
- Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
- Multi-Level Recurrent Residual Networks for Action Recognition
- Optimization Planning for 3D ConvNets
- DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding
- Object Discovery in Videos as Foreground Motion Clustering
- 3DRM:Pair-wise relation module for 3D object detection
- MVFNet: Multi-View Fusion Network for Efficient Video Recognition
- Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data
- Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
- Generalizing Monocular 3D Human Pose Estimation in the Wild
- Joint Discovery of Object States and Manipulation Actions
- Attention Distillation for Learning Video Representations
- PIC: Permutation Invariant Convolution for Recognizing Long-range Activities
- Asynchronous Interaction Aggregation for Action Detection
- Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
- Deep Multimodal Feature Encoding for Video Ordering
- Challenges in Time-Stamp Aware Anomaly Detection in Traffic Videos
- DAP3D-Net: Where, What and How Actions Occur in Videos?
- Volterra Neural Networks (VNNs)
- Temporal Human Action Segmentation via Dynamic Clustering
- Long-short Term Motion Feature for Action Classification and Retrieval
- Spatio-Temporal Action Detection with Multi-Object Interaction
- Busy-Quiet Video Disentangling for Video Classification
- VA-RED: Video Adaptive Redundancy Reduction
- 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
- A Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point
- Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning
- On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
- Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition
- Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
- Low-light Environment Neural Surveillance
- Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism
- Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models
- PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
- PISEP^2: Pseudo Image Sequence Evolution based 3D Pose Prediction
- Multi-shot Temporal Event Localization: a Benchmark
- Delving into 3D Action Anticipation from Streaming Videos
- Self-supervised Video Representation Learning by Context and Motion Decoupling
- What can human minimal videos tell us about dynamic recognition models?
- NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification
- Deep RNN Framework for Visual Sequential Applications
- Diagnosing Error in Temporal Action Detectors
- Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition
- Characterizing Deep Learning Training Workloads on Alibaba-PAI
- Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images
- A Unified Method for First and Third Person Action Recognition
- Identifying First-person Camera Wearers in Third-person Videos
- Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines
- Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
- Weakly supervised learning of actions from transcripts
- Convolutional Relational Machine for Group Activity Recognition
- Learning Discriminative Features via Label Consistent Neural Network
- Hierarchical Feature Aggregation Networks for Video Action Recognition
- Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action Recognition
- BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
- Tensor Analysis with n-Mode Generalized Difference Subspace
- Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks
- Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
- Multiple Human Tracking using Multi-Cues including Primitive Action Features
- 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
- Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
- STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition
- P-CNN: Pose-based CNN Features for Action Recognition
- Fingerspelling recognition in the wild with iterative visual attention
- Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web
- Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
- Cooperative Cross-Stream Network for Discriminative Action Representation
- Order-aware Convolutional Pooling for Video Based Action Recognition
- Pushing the Limits of Deep CNNs for Pedestrian Detection
- Universal Prototype Transport for Zero-Shot Action Recognition and Localization
- STEP: Spatio-Temporal Progressive Learning for Video Action Detection
- Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
- Learning from Videos with Deep Convolutional LSTM Networks
- Spatiotemporal Pyramid Network for Video Action Recognition
- Temporal Tessellation: A Unified Approach for Video Analysis
- Learning Motion Patterns in Videos
- Deep Discriminative Representation Learning with Attention Map for Scene Classification
- Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
- Accelerating temporal action proposal generation via high performance computing
- Exploring Dynamic Context for Multi-path Trajectory Prediction
- Manipulation-skill Assessment from Videos with Spatial Attention Network
- Motion-Focused Contrastive Learning of Video Representations
- Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
- 3DPalsyNet: A Facial Palsy Grading and Motion Recognition Framework using Fully 3D Convolutional Neural Networks
- Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos
- ActionVLAD: Learning spatio-temporal aggregation for action classification
- Making a Case for 3D Convolutions for Object Segmentation in Videos
- Video Imprint
- Learning Efficient Video Representation with Video Shuffle Networks
- UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
- Budget-Aware Activity Detection with A Recurrent Policy Network
- Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
- Automatic Generation of Dense Non-rigid Optical Flow
- Discriminability Distillation in Group Representation Learning
- A Structured Model For Action Detection
- Elaborative Rehearsal for Zero-shot Action Recognition
- ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction
- CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps
- Modeling Spatio-Temporal Human Track Structure for Action Localization
- Learning Optical Flow via Dilated Networks and Occlusion Reasoning
- Graph Distillation for Action Detection with Privileged Modalities
- On the Importance of Video Action Recognition for Visual Lipreading
- StreamTinyNet: video streaming analysis with spatial-temporal TinyML
- Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
- Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
- Picket: Guarding Against Corrupted Data in Tabular Data during Learning and Inference
- Learning Class Regularized Features for Action Recognition
- Extreme Low Resolution Activity Recognition with Confident Spatial-Temporal Attention Transfer
- Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation
- MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
- Learning Cross-modal Contrastive Features for Video Domain Adaptation
- AFO-TAD: Anchor-free One-Stage Detector for Temporal Action Detection
- Being the center of attention: A Person-Context CNN framework for Personality Recognition
- Saliency-guided video classification via adaptively weighted learning
- Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos
- Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
- Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
- Cross-modal knowledge distillation for action recognition
- Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
- Alleviating Over-segmentation Errors by Detecting Action Boundaries
- Universal-to-Specific Framework for Complex Action Recognition
- Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
- TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
- Temporal Extension Module for Skeleton-Based Action Recognition
- Representing Videos as Discriminative Sub-graphs for Action Recognition
- Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
- ASL Recognition with Metric-Learning based Lightweight Network
- P-ODN: Prototype based Open Deep Network for Open Set Recognition
- Beyond the Camera: Neural Networks in World Coordinates
- A deep neural network to enhance prediction of 1-year mortality using echocardiographic videos of the heart
- Action Tubelet Detector for Spatio-Temporal Action Localization
- Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
- Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
- Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition
- HDRVideo-GAN: Deep Generative HDR Video Reconstruction
- Dynamic Network Quantization for Efficient Video Inference
- Deep Learning for Robust Motion Segmentation with Non-Static Cameras
- Higher Order Recurrent Space-Time Transformer for Video Action Prediction
- Learning to Discriminate Information for Online Action Detection
- Learning Spatiotemporal Features of Ride-sourcing Services with Fusion Convolutional Network
- Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
- Future Frame Prediction of a Video Sequence
- Learning Action Maps of Large Environments via First-Person Vision
- Cross-Modal Message Passing for Two-stream Fusion
- Predicting the Future: A Jointly Learnt Model for Action Anticipation
- Human Action Sequence Classification
- AVD: Adversarial Video Distillation
- Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
- Deformable Tube Network for Action Detection in Videos
- Object-aware Feature Aggregation for Video Object Detection
- Reasoning About Human-Object Interactions Through Dual Attention Networks
- Dance with Flow: Two-in-One Stream Action Detection
- Towards Visually Explaining Video Understanding Networks with Perturbation
- Hallucinating Optical Flow Features for Video Classification
- TSI: Temporal Saliency Integration for Video Action Recognition
- Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
- Spatial-Temporal Alignment Network for Action Recognition and Detection
- FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
- Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos
- Falls Prediction Based on Body Keypoints and Seq2Seq Architecture
- Explainable Video Action Reasoning via Prior Knowledge and State Transitions
- Temporal Reasoning Graph for Activity Recognition
- Universal Embeddings for Spatio-Temporal Tagging of Self-Driving Logs
- Two-Stream Video Classification with Cross-Modality Attention
- Spatiotemporal Information Processing with a Reservoir Decision-making Network
- Video Modeling with Correlation Networks
- Learning spatio-temporal representations with temporal squeeze pooling
- Reinforcement Learning with Latent Flow
- NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition
- Few Shot Activity Recognition Using Variational Inference
- Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition
- Temporal Bilinear Networks for Video Action Recognition
- Temporal Alignment Prediction for Few-Shot Video Classification
- Visual-Texual Emotion Analysis with Deep Coupled Video and Danmu Neural Networks
- CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition
- Random Temporal Skipping for Multirate Video Analysis
- Fine-grained Video Categorization with Redundancy Reduction Attention
- Inter-BMV: Interpolation with Block Motion Vectors for Fast Semantic Segmentation on Video
- Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
- RGB Video Based Tennis Action Recognition Using a Deep Historical Long Short-Term Memory
- A Symbolic Temporal Pooling method for Video-based Person Re-Identification
- Local Clustering with Mean Teacher for Semi-supervised Learning
- Attentive One-Dimensional Heatmap Regression for Facial Landmark Detection and Tracking
- Deep Unsupervised Multi-View Detection of Video Game Stream Highlights
- Video Time: Properties, Encoders and Evaluation
- Visually Guided Sound Source Separation using Cascaded Opponent Filter Network
- Extracting Contact and Motion from Manipulation Videos
- AutoLoc: Weakly-supervised Temporal Action Localization
- Spatio-Temporal Channel Correlation Networks for Action Classification
- Key Frame Proposal Network for Efficient Pose Estimation in Videos
- A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
- I Have Seen Enough: A Teacher Student Network for Video Classification Using Fewer Frames
- Coupling Intent and Action for Pedestrian Crossing Behavior Prediction
- Multi-Level Temporal Pyramid Network for Action Detection
- 2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework
- Effective Action Recognition with Embedded Key Point Shifts
- Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
- iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
- MOD: A Deep Mixture Model with Online Knowledge Distillation for Large Scale Video Temporal Concept Localization
- Region-based Non-local Operation for Video Classification
- IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
- Air-Writing Translater: A Novel Unsupervised Domain Adaptation Method for Inertia-Trajectory Translation of In-air Handwriting
- CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
- Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
- Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos
- Temporal Action Localization by Structured Maximal Sums
- Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations
- Randomness in Deconvolutional Networks for Visual Representation
- Two-Stream Multi-Task Network for Fashion Recognition
- Cricket stroke extraction: Towards creation of a large-scale cricket actions dataset
- Ordered Pooling of Optical Flow Sequences for Action Recognition
- RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
- Efficient Action Detection in Untrimmed Videos via Multi-Task Learning
- Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
- Towards ontology driven learning of visual concept detectors
- Improved Dense Trajectory with Cross Streams
- Long-Short Temporal Contrastive Learning of Video Transformers
- Improving Human Action Recognition by Non-action Classification
- GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
- From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
- Spatio-temporal Video Re-localization by Warp LSTM
- What can we learn about CNNs from a large scale controlled object dataset?
- Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
- Detecting Kissing Scenes in a Database of Hollywood Films
- Efficient Action Recognition Using Confidence Distillation
- UniDual: A Unified Model for Image and Video Understanding
- Learning Spatio-Temporal Representation with Local and Global Diffusion
- Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations
- Triple-view Convolutional Neural Networks for COVID-19 Diagnosis with Chest X-ray
- VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
- Forecasting Future Action Sequences with Neural Memory Networks
- OadTR: Online Action Detection with Transformers
- Multiple Visual-Semantic Embedding for Video Retrieval from Query Sentence
- Training for temporal sparsity in deep neural networks, application in video processing
- Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending
- Coupled Recurrent Network (CRN)
- Recognition from Hand Cameras
- Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanism
- Group-aware Contrastive Regression for Action Quality Assessment
- Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
- Temporal Action Localization with Variance-Aware Networks
- Efficient Spatialtemporal Context Modeling for Action Recognition
- A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
- Differential Viewpoints for Ground Terrain Material Recognition
- Encode the Unseen: Predictive Video Hashing for Scalable Mid-Stream Retrieval
- Learning Energy-based Spatial-Temporal Generative ConvNets for Dynamic Patterns
- M-PACT: An Open Source Platform for Repeatable Activity Classification Research
- SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
- Temporal Action Segmentation from Timestamp Supervision
- Streaming Networks: Enable A Robust Classification of Noise-Corrupted Images
- S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
- Hopper: Multi-hop Transformer for Spatiotemporal Reasoning
- Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model
- Online Detection of Action Start in Untrimmed, Streaming Videos
- Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation
- Deep-Temporal LSTM for Daily Living Action Recognition
- PGT: A Progressive Method for Training Models on Long Videos
- Temporal Action Localization using Long Short-Term Dependency
- Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN Framework
- Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
- Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition
- When Video Classification Meets Incremental Classes
- Do Deep Neural Networks Model Nonlinear Compositionality in the Neural Representation of Human-Object Interactions?
- A Universal Model for Cross Modality Mapping by Relational Reasoning
- Out the Window: A Crowd-Sourced Dataset for Activity Classification in Security Video
- Recognizing Manipulation Actions from State-Transformations
- Privacy-Preserving Video Classification with Convolutional Neural Networks
- GCF-Net: Gated Clip Fusion Network for Video Action Recognition
- Weakly-Supervised Multi-Person Action Recognition in 360 Videos
- Forecasting Hands and Objects in Future Frames
- Action Understanding with Multiple Classes of Actors
- Three-stream network for enriched Action Recognition
- Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
- Neural networks behave as hash encoders: An empirical study
- Action Representation Using Classifier Decision Boundaries
- Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
- ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
- Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization
- Global Context Networks
- Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates
- Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
- ODN: Opening the Deep Network for Open-set Action Recognition
- Generating the Cloud Motion Winds Field from Satellite Cloud Imagery Using Deep Learning Approach
- Identification of Attack-Specific Signatures in Adversarial Examples
- An Action Recognition network for specific target based on rMC and RPN
- Online Action Detection in Streaming Videos with Time Buffers
- A Fully Trainable Network with RNN-based Pooling
- Unsupervised Human Action Detection by Action Matching
- Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
- ParaNet: Deep Regular Representation for 3D Point Clouds
- The Effect of Data Ordering in Image Classification
- Scaling Matters in Deep Structured-Prediction Models
- BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues
- AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos
- Consistency-Aware Graph Network for Human Interaction Understanding
- Video Anomaly Detection by Estimating Likelihood of Representations
- Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
- LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
- Human Activity Recognition for Edge Devices
- Ontology Based Global and Collective Motion Patterns for Event Classification in Basketball Videos
- Cross-Enhancement Transform Two-Stream 3D ConvNets for Action Recognition
- RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
- Spatio-Temporal Video Representation Learning for AI Based Video Playback Style Prediction
- Recent Progress in Appearance-based Action Recognition
- Deep set conditioned latent representations for action recognition
- Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
- Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks
- Token Shift Transformer for Video Classification
- Applications of the Streaming Networks
- Multi-Frame Content Integration with a Spatio-Temporal Attention Mechanism for Person Video Motion Transfer
- Tubelets: Unsupervised action proposals from spatiotemporal super-voxels
- Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset
- Temporal-Spatial Mapping for Action Recognition
- Low Pass Filter for Anti-aliasing in Temporal Action Localization
- Action Anticipation By Predicting Future Dynamic Images
- Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition
- Multi-Task Learning of Generalizable Representations for Video Action Recognition
- Multi-modal Residual Perceptron Network for Audio-Video Emotion Recognition
- Deep Spatio-temporal Manifold Network for Action Recognition
- Contrastive Video Representation Learning via Adversarial Perturbations
- Overview of Tencent Multi-modal Ads Video Understanding Challenge
- W-TALC: Weakly-supervised Temporal Activity Localization and Classification
- Unified Embedding and Metric Learning for Zero-Exemplar Event Detection
- Boosting Video Representation Learning with Multi-Faceted Integration
- Higher-order Network for Action Recognition
- Understanding Road Layout from Videos as a Whole
- Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video
- OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow
- Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition
- Bridging the gap between Human Action Recognition and Online Action Detection
- Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
- 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
- Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation
- Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation
- Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks
- ADNet: Temporal Anomaly Detection in Surveillance Videos
- SummaryNet: A Multi-Stage Deep Learning Model for Automatic Video Summarisation
- Three-Stream Fusion Network for First-Person Interaction Recognition
- Fine-grained Action Segmentation using the Semi-Supervised Action GAN
- Temporal Action Detection by Joint Identification-Verification
- Adaptive Interaction Modeling via Graph Operations Search
- Fine-Grained Instance-Level Sketch-Based Video Retrieval
- OOWL500: Overcoming Dataset Collection Bias in the Wild
- HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
- Spatio-Temporal Deep Learning Models for Tip Force Estimation During Needle Insertion
- Hierarchical Attention Network for Action Segmentation
- DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition
- Turning old models fashion again: Recycling classical CNN networks using the Lattice Transformation
- Multi-Modal Three-Stream Network for Action Recognition
- Exploring Temporal Information for Improved Video Understanding
- BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization
- Two-stream Spatiotemporal Feature for Video QA Task
- Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
- Domain Adaptor Networks for Hyperspectral Image Recognition
- Modelling Temporal Information Using Discrete Fourier Transform for Video Classification
- Large-Scale Mapping of Human Activity using Geo-Tagged Videos
- Real-time tracker with fast recovery from target loss
- Using phase instead of optical flow for action recognition
- Exploring Frame Segmentation Networks for Temporal Action Localization
- ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling
- Skeleon-Based Typing Style Learning For Person Identification
- SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos
- Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
- Approximated Bilinear Modules for Temporal Modeling
- Hierarchical Action Classification with Network Pruning
- Writing Style Invariant Deep Learning Model for Historical Manuscripts Alignment
- Multimodal and self-supervised representation learning for automatic gesture recognition in surgical robotics
- Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
- Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification
- Temporal Accumulative Features for Sign Language Recognition
- Video-based Person Re-identification with Two-stream Convolutional Network and Co-attentive Snippet Embedding
- Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection
- Long Short-Term Relation Networks for Video Action Detection
- Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
- Sparsifying and Down-scaling Networks to Increase Robustness to Distortions
- Exploring Feature Representation and Training strategies in Temporal Action Localization
- Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
- Deep Dual Relation Modeling for Egocentric Interaction Recognition
- SUSiNet: See, Understand and Summarize it
- Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification
- Motion Representation with Acceleration Images
- A Real-time Action Representation with Temporal Encoding and Deep Compression
- CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
- Decision Support for Video-based Detection of Flu Symptoms
- Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos
- Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures
- V-SlowFast Network for Efficient Visual Sound Separation
- Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
- Online Spatiotemporal Action Detection and Prediction via Causal Representations
- Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
- Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
- A Genetic Feature Selection Based Two-stream Neural Network for Anger Veracity Recognition
- Triple Attention Network architecture for MovieQA
- Global Temporal Representation based CNNs for Infrared Action Recognition
- Knowledge Fusion Transformers for Video Action Recognition
- Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
- Layout-induced Video Representation for Recognizing Agent-in-Place Actions
- VideoMCC: a New Benchmark for Video Comprehension
- SmallBigNet: Integrating Core and Contextual Views for Video Classification
- cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey
- Multi-Stream Single Shot Spatial-Temporal Action Detection
- Learning Goals from Failure
- Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
- Learning Object Permanence from Video
- T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition
- An Attractor-Guided Neural Networks for Skeleton-Based Human Motion Prediction
- Spatial-temporal Fusion Convolutional Neural Network for Simulated Driving Behavior Recognition
- Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
- Adaptive and Iteratively Improving Recurrent Lateral Connections
- Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
- Neural Image Decompression: Learning to Render Better Image Previews
- Long-Short Temporal Modeling for Efficient Action Recognition
- Predictive Coding Networks Meet Action Recognition
- Multi-modal Transformer for Video Retrieval
- Making a Case for Learning Motion Representations with Phase
- Curvature: A signature for Action Recognition in Video Sequences
- Temporally Consistent Depth Prediction with Flow-Guided Memory Units
- Hide and Seek tracker: Real-time recovery from target loss
- Global2Local: Efficient Structure Search for Video Action Segmentation
- Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
- ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
- White Paper Assistance: A Step Forward Beyond the Shortcut Learning
- E-Sports Talent Scouting Based on Multimodal Twitch Stream Data
- Primary Tumor Origin Classification of Lung Nodules in Spectral CT using Transfer Learning
- Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
- Graph Convolutional Module for Temporal Action Localization in Videos
- DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
- Discriminative Video Representation Learning Using Support Vector Classifiers
- An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments
- cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
- Deep CTR Prediction in Display Advertising
- CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
- Detecting and Tracking Small Moving Objects in Wide Area Motion Imagery (WAMI) Using Convolutional Neural Networks (CNNs)
- Action Recognition Using Volumetric Motion Representations
- TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction
- Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation
- Deep Discriminative Model for Video Classification
- Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos
- Summarizing First-Person Videos from Third Persons' Points of Views
- Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
- Transform-Invariant Convolutional Neural Networks for Image Classification and Search
- Image to Video Domain Adaptation Using Web Supervision
- Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
- Unsupervised Motion Representation Enhanced Network for Action Recognition
- We don't Need Thousand Proposals Single Shot Actor-Action Detection in Videos
- Efficient Modelling Across Time of Human Actions and Interactions
- Action parsing using context features
- Visual Relation Grounding in Videos
- Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
- On Flow Profile Image for Video Representation
- Phase Space Reconstruction Network for Lane Intrusion Action Recognition
- Feature-Supervised Action Modality Transfer
- A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation
- Modality Compensation Network: Cross-Modal Adaptation for Action Recognition