UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Abstract

We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.

Cited by in corpus (879)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Learning Transferable Visual Models From Natural Language Supervision
• Transformers in Vision: A Survey
• Learning to Prompt for Vision-Language Models
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Unsupervised Learning of Video Representations using LSTMs
• Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
• Domain Generalization: A Survey
• DINOv2: Learning Robust Visual Features without Supervision
• YouTube-8M: A Large-Scale Video Classification Benchmark
• The THUMOS Challenge on Action Recognition for Videos "in the Wild"
• Human Action Recognition from Various Data Modalities: A Review
• Contrastive Multiview Coding
• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
• Towards Good Practices for Very Deep Two-Stream ConvNets
• Deep multi-scale video prediction beyond mean square error
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• WebVision Database: Visual Learning and Understanding from Web Data
• A Review on Deep Learning Techniques for Video Prediction
• A Short Note about Kinetics-600
• Video (language) modeling: a baseline for generative models of natural videos
• Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
• Self-supervised Co-training for Video Representation Learning
• Beyond Short Snippets: Deep Networks for Video Classification
• Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
• Self-Supervised Learning by Cross-Modal Audio-Video Clustering
• SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos
• 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
• Attentional Pooling for Action Recognition
• BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
• Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
• Self-Supervised MultiModal Versatile Networks
• ActionCLIP: A New Paradigm for Video Action Recognition
• Describing Videos by Exploiting Temporal Structure
• Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• TSM: Temporal Shift Module for Efficient Video Understanding
• Self-supervised Domain Adaptation for Computer Vision Tasks
• TCLR: Temporal Contrastive Learning for Video Representation
• Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
• Learning Spatiotemporal Features with 3D Convolutional Networks
• Audiovisual SlowFast Networks for Video Recognition
• PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding
• Delving Deeper into Convolutional Networks for Learning Video Representations
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Learning for Video Compression
• Adversarial Video Generation on Complex Datasets
• MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language
• Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
• Temporal Action Detection with Structured Segment Networks
• Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
• Long-term Temporal Convolutions for Action Recognition
• A Pursuit of Temporal Accuracy in General Activity Detection
• Compact Generalized Non-local Network
• Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice
• Recurrent Mixture Density Network for Spatiotemporal Visual Attention
• Knowledge Distillation in Deep Learning and its Applications
• A Comprehensive Study of Deep Video Action Recognition
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• Evaluating Two-Stream CNN for Video Classification
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
• Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
• Rethinking CNN Models for Audio Classification
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
• You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
• Semantics for Robotic Mapping, Perception and Interaction: A Survey
• ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild
• A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation
• Hidden Two-Stream Convolutional Networks for Action Recognition
• ROAD: The ROad event Awareness Dataset for Autonomous Driving
• Motion-driven Visual Tempo Learning for Video-based Action Recognition
• Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM
• BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
• Self-Supervised Generalisation with Meta Auxiliary Learning
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks
• Fuzzy human motion analysis: A review
• Dynamic Sampling Networks for Efficient Action Recognition in Videos
• TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
• Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
• Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
• Spatiotemporal Contrastive Video Representation Learning
• Labelling unlabelled videos from scratch with multi-modal self-supervision
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
• Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
• CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
• Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
• Hierarchical Attention Network for Action Recognition in Videos
• Analyzing Human-Human Interactions: A Survey
• MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• Learning to track for spatio-temporal action localization
• Human Action Localization with Sparse Spatial Supervision
• Context Understanding in Computer Vision: A Survey
• A Good Image Generator Is What You Need for High-Resolution Video Synthesis
• Infrared and 3D skeleton feature fusion for RGB-D action recognition
• Improving performance of recurrent neural network with relu nonlinearity
• VideoLSTM Convolves, Attends and Flows for Action Recognition
• Video Representation Learning with Visual Tempo Consistency
• ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
• STM: SpatioTemporal and Motion Encoding for Action Recognition
• Multi-level Second-order Few-shot Learning
• An Image is Worth 16x16 Words, What is a Video Worth?
• Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• On Learning Sets of Symmetric Elements
• MERLOT: Multimodal Neural Script Knowledge Models
• Weakly Supervised Action Localization by Sparse Temporal Pooling Network
• Zero-Shot Action Recognition in Videos: A Survey
• Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
• Real-time Action Recognition with Enhanced Motion Vector CNNs
• A Multi-viewpoint Outdoor Dataset for Human Action Recognition
• Temporal Segment Networks for Action Recognition in Videos
• A Constructive Prediction of the Generalization Error Across Scales
• Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding
• ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
• On the effectiveness of task granularity for transfer learning
• VideoMix: Rethinking Data Augmentation for Video Classification
• Video Representation Learning by Dense Predictive Coding
• VideoGraph: Recognizing Minutes-Long Human Activities in Videos
• Active Contrastive Learning of Audio-Visual Video Representations
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video
• VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
• FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
• Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues
• Appearance-and-Relation Networks for Video Classification
• Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
• Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
• Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation
• CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
• Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications
• Action2Vec: A Crossmodal Embedding Approach to Action Learning
• Video Big Data Analytics in the Cloud: A Reference Architecture, Survey, Opportunities, and Open Research Issues
• Generative Models for Low-Rank Video Representation and Reconstruction
• Recent Advances in Zero-shot Recognition
• RWF-2000: An Open Large Scale Video Database for Violence Detection
• TEA: Temporal Excitation and Aggregation for Action Recognition
• VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
• Emergence of Exploratory Look-Around Behaviors through Active Observation Completion
• Finding Action Tubes
• ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
• Few-shot Action Recognition with Prototype-centered Attentive Learning
• Budget-Aware Adapters for Multi-Domain Learning
• Support-set bottlenecks for video-text representation learning
• Objects2action: Classifying and localizing actions without any video example
• Lower Dimensional Kernels for Video Discriminators
• Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition
• Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model
• Temporal Generative Adversarial Nets with Singular Value Clipping
• Early Action Prediction with Generative Adversarial Networks
• TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
• Learning Spatiotemporal Features via Video and Text Pair Discrimination
• Temporal Relational Reasoning in Videos
• Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
• Learning Attributes Equals Multi-Source Domain Generalization
• Multi-Task Zipping via Layer-wise Neuron Sharing
• Cycle-Contrast for Self-Supervised Video Representation Learning
• Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
• PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
• MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
• FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
• UntrimmedNets for Weakly Supervised Action Recognition and Detection
• Unsupervised Learning of Long-Term Motion Dynamics for Videos
• StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs
• Video Action Understanding
• CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
• Hypergraph-based Multi-View Action Recognition using Event Cameras
• Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video
• CCVS: Context-aware Controllable Video Synthesis
• Correlation Net: Spatiotemporal multimodal deep learning for action recognition
• Learn to cycle: Time-consistent feature discovery for action recognition
• The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• Can Temporal Information Help with Contrastive Self-Supervised Learning?
• STAIR Actions: A Video Dataset of Everyday Home Actions
• Action Machine: Rethinking Action Recognition in Trimmed Videos
• Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
• Fusing Multi-Stream Deep Networks for Video Classification
• Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
• TEINet: Towards an Efficient Architecture for Video Recognition
• Going Deeper into First-Person Activity Recognition
• Unsupervised Representation Learning by Sorting Sequences
• Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects
• Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
• Connectionist Temporal Modeling for Weakly Supervised Action Labeling
• Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts
• Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles
• Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
• Scaling Laws for Deep Learning
• Video Imagination from a Single Image with Transformation Generation
• Video Understanding as Machine Translation
• Domain Adaptation without Source Data
• Video-based Human Action Recognition using Deep Learning: A Review
• Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
• Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges
• LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN
• StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
• Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
• Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos
• DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks
• Video action detection by learning graph-based spatio-temporal interactions
• Cross Modal Distillation for Supervision Transfer
• A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection
• VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
• A Review of Emerging Research Directions in Abstract Visual Reasoning
• Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses
• Learning Representations from Audio-Visual Spatial Alignment
• Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
• Actionness Estimation Using Hybrid Fully Convolutional Networks
• Grouped Spatial-Temporal Aggregation for Efficient Action Recognition
• Lattice Long Short-Term Memory for Human Action Recognition
• Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition
• Dual Contrastive Learning for Spatio-temporal Representation
• From Here to There: Video Inbetweening Using Direct 3D Convolutions
• Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
• Feature sampling and partitioning for visual vocabulary generation on large action classification datasets
• Deep Learning for Vision-based Prediction: A Survey
• All About Knowledge Graphs for Actions
• Central Similarity Quantization for Efficient Image and Video Retrieval
• Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition
• ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
• Unsupervised Semantic Parsing of Video Collections
• Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
• Unsupervised learning from videos using temporal coherency deep networks
• The Open World of Micro-Videos
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Generalized Rank Pooling for Activity Recognition
• Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
• Learning Discriminative Motion Features Through Detection
• Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution
• Recognizing Exercises and Counting Repetitions in Real Time
• Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video
• Omni-sourced Webly-supervised Learning for Video Recognition
• Learning Human Optical Flow
• Music-oriented Dance Video Synthesis with Pose Perceptual Loss
• Stories for Images-in-Sequence by using Visual and Narrative Components
• Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
• Copycat CNN: Are Random Non-Labeled Data Enough to Steal Knowledge from Black-box Models?
• Dense Optical Flow Prediction from a Static Image
• Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
• Local plasticity rules can learn deep representations using self-supervised contrastive predictions
• Clean-Label Backdoor Attacks on Video Recognition Models
• Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
• CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• VideoPro: A Visual Analytics Approach for Interactive Video Programming
• Few-shot Action Recognition with Permutation-invariant Attention
• ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
• Unsupervised Learning of Video Representations via Dense Trajectory Clustering
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• Self-supervised Learning of Audio Representations from Audio-Visual Data using Spatial Alignment
• Few-Shot Video Classification via Temporal Alignment
• Learning Video Representations from Textual Web Supervision
• Semantic Embedding Space for Zero-Shot Action Recognition
• VideoCapsuleNet: A Simplified Network for Action Detection
• Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
• Towards Universal Representation for Unseen Action Recognition
• Dual Motion GAN for Future-Flow Embedded Video Prediction
• Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
• Sparse Adversarial Perturbations for Videos
• Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
• Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube
• REPAIR: Removing Representation Bias by Dataset Resampling
• Deep Adaptive Temporal Pooling for Activity Recognition
• VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
• Pose from Action: Unsupervised Learning of Pose Features based on Motion
• Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
• Deep Keyframe Detection in Human Action Videos
• Moviescope: Large-scale Analysis of Movies using Multiple Modalities
• Mobile Video Action Recognition
• COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis
• Rethinking Full Connectivity in Recurrent Neural Networks
• Fine-grained Activity Recognition with Holistic and Pose based Features
• DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
• Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild
• Few-Shot Action Recognition with Compromised Metric via Optimal Transport
• Let's Dance: Learning From Online Dance Videos
• EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video
• Where and What: Driver Attention-based Object Detection
• Action Recognition with Joint Attention on Multi-Level Deep Features
• Neighbor Correspondence Matching for Flow-based Video Frame Synthesis
• Temporal Dynamic Graph LSTM for Action-driven Video Object Detection
• CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing
• Video Generation from Single Semantic Label Map
• Multi-Fiber Networks for Video Recognition
• $A^2$-Nets: Double Attention Networks
• Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
• Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
• Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis
• Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
• End-to-end Video-level Representation Learning for Action Recognition
• BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• Attend and Interact: Higher-Order Object Interactions for Video Understanding
• Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
• Human Action Forecasting by Learning Task Grammars
• Treatment Learning Causal Transformer for Noisy Image Classification
• Visual Text Correction
• Spatio-Temporal Fusion Networks for Action Recognition
• BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
• Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
• Hierarchical Contrastive Motion Learning for Video Action Recognition
• Deep Temporal Linear Encoding Networks
• Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation
• Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
• Action Recognition with Dynamic Image Networks
• Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking
• PaStaNet: Toward Human Activity Knowledge Engine
• VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
• Unsupervised Learning from Video with Deep Neural Embeddings
• ACTION-Net: Multipath Excitation for Action Recognition
• Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
• Visual Data Synthesis via GAN for Zero-Shot Video Classification
• Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
• Identifying and Resisting Adversarial Videos Using Temporal Consistency
• Temporal Interlacing Network
• Effect of Architectures and Training Methods on the Performance of Learned Video Frame Prediction
• Automatic learning of gait signatures for people identification
• Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes
• Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
• Appending Adversarial Frames for Universal Video Attack
• Im2Flow: Motion Hallucination from Static Images for Action Recognition
• The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA)
• Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care
• Localizing Actions from Video Labels and Pseudo-Annotations
• Learning Person Trajectory Representations for Team Activity Analysis
• Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers
• Spatio-temporal Action Recognition: A Survey
• DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
• Similarity R-C3D for Few-shot Temporal Activity Detection
• IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
• Spatio-Temporal Perturbations for Video Attribution
• Evidential Deep Learning for Open Set Action Recognition
• Video 3D Sampling for Self-supervised Representation Learning
• MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs
• Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
• Unsupervised Learning and Segmentation of Complex Activities from Video
• DramaQA: Character-Centered Video Story Understanding with Hierarchical QA
• Listen to Look: Action Recognition by Previewing Audio
• Identifying Visible Actions in Lifestyle Vlogs
• Interpretable Spatio-temporal Attention for Video Action Recognition
• Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
• Pose Guided Human Video Generation
• Deep Hashing with Category Mask for Fast Video Retrieval
• Differential Angular Imaging for Material Recognition
• Deep End2End Voxel2Voxel Prediction
• Probing the State of the Art: A Critical Look at Visual Representation Evaluation
• AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
• EV-Action: Electromyography-Vision Multi-Modal Action Dataset
• Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
• DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild
• FASTER Recurrent Networks for Efficient Video Classification
• Compact Global Descriptor for Neural Networks
• Revisiting Few-shot Activity Detection with Class Similarity Control
• Handcrafted Local Features are Convolutional Neural Networks
• PERF-Net: Pose Empowered RGB-Flow Net
• ActionFlowNet: Learning Motion Representation for Action Recognition
• Black-box Adversarial Attacks on Video Recognition Models
• Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
• Non-local NetVLAD Encoding for Video Classification
• Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition
• Learning from Temporal Gradient for Semi-supervised Action Recognition
• Zero-Shot Visual Recognition via Bidirectional Latent Embedding
• Asynchronous Temporal Fields for Action Recognition
• Sparse Adversarial Video Attacks with Spatial Transformations
• Deep Motion Features for Visual Tracking
• Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
• Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
• FSD-10: A Dataset for Competitive Sports Content Analysis
• Multi-Scale Video Frame-Synthesis Network with Transitive Consistency Loss
• Conditional Extreme Value Theory for Open Set Video Domain Adaptation
• Intra- and Inter-Action Understanding via Temporal Action Parsing
• Two-Stream AMTnet for Action Detection
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
• Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
• Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
• Compressed Video Action Recognition with Refined Motion Vector
• Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
• Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
• HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
• Cross-media Structured Common Space for Multimedia Event Extraction
• Towards Context-aware Interaction Recognition
• Adversarial Cross-Domain Action Recognition with Co-Attention
• In the Eye of the Beholder: Gaze and Actions in First Person Video
• Progressive Motion Context Refine Network for Efficient Video Frame Interpolation
• Relational Action Forecasting
• Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification
• Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition
• Interpretable Deep Feature Propagation for Early Action Recognition
• Self-supervised Motion Learning from Static Images
• FMM-X3D: FPGA-based modeling and mapping of X3D for Human Action Recognition
• Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
• Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations
• PV-NAS: Practical Neural Architecture Search for Video Recognition
• MAiVAR: Multimodal Audio-Image and Video Action Recognizer
• Recognizing Activities of Daily Living with a Wrist-mounted Camera
• Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning
• Actions as Moving Points
• Video Is Graph: Structured Graph Module for Video Action Recognition
• Datasets on object manipulation and interaction: a survey
• Shifted Chunk Transformer for Spatio-Temporal Representational Learning
• Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
• Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
• ReHAR: Robust and Efficient Human Activity Recognition
• Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
• MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
• IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
• Action Completion: A Temporal Model for Moment Detection
• Learning to score the figure skating sports videos
• CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
• Relational Long Short-Term Memory for Video Action Recognition
• Self-Supervised Video Representation Learning With Odd-One-Out Networks
• A Deep Ranking Model for Spatio-Temporal Highlight Detection from a 360 Video
• GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
• Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video
• Discriminative convolutional Fisher vector network for action recognition
• Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
• Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
• Spatio-temporal Person Retrieval via Natural Language Queries
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• Towards Structured Analysis of Broadcast Badminton Videos
• Spatio-Temporal Action Detection with Multi-Object Interaction
• Unsupervised Bi-directional Flow-based Video Generation from one Snapshot
• Beyond Caption To Narrative: Video Captioning With Multiple Sentences
• Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation
• TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos
• Multi-Level Recurrent Residual Networks for Action Recognition
• Attention Distillation for Learning Video Representations
• Learning Dynamic Generator Model by Alternating Back-Propagation Through Time
• Making CNNs for Video Parsing Accessible
• Temporal Human Action Segmentation via Dynamic Clustering
• Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
• MVFNet: Multi-View Fusion Network for Efficient Video Recognition
• Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification
• The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition
• Self-Supervised Learning via multi-Transformation Classification for Action Recognition
• Audio-visual Representation Learning for Anomaly Events Detection in Crowds
• Volterra Neural Networks (VNNs)
• CDFI: Compression-Driven Network Design for Frame Interpolation
• RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression
• Eigen Evolution Pooling for Human Action Recognition
• Subjective Annotation for a Frame Interpolation Benchmark using Artefact Amplification
• Deep Multimodal Feature Encoding for Video Ordering
• Asynchronous Interaction Aggregation for Action Detection
• Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
• DAP3D-Net: Where, What and How Actions Occur in Videos?
• Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset
• Visual Forecasting by Imitating Dynamics in Natural Sequences
• PIC: Permutation Invariant Convolution for Recognizing Long-range Activities
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
• O2A: One-shot Observational learning with Action vectors
• LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
• Learning Discriminative Features via Label Consistent Neural Network
• Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition
• What can human minimal videos tell us about dynamic recognition models?
• Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
• Detection of Audio-Video Synchronization Errors Via Event Detection
• Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
• BAR: Bayesian Activity Recognition using variational inference
• Low-light Environment Neural Surveillance
• Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition
• Federated Action Recognition on Heterogeneous Embedded Devices
• Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning
• Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
• Pillar Networks++: Distributed non-parametric deep and wide networks
• Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
• Learning long-term dependencies for action recognition with a biologically-inspired deep network
• Action Classification and Highlighting in Videos
• Busy-Quiet Video Disentangling for Video Classification
• Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction
• Fully Automated Hand Hygiene Monitoring\\in Operating Room using 3D Convolutional Neural Network
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
• Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos
• KIT MOMA: A Mobile Machines Dataset
• VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products
• Actor-Action Semantic Segmentation with Grouping Process Models
• Enhanced Quadratic Video Interpolation
• fpgaHART: A toolflow for throughput-oriented acceleration of 3D CNNs for HAR onto FPGAs
• Self-supervised Video Representation Learning by Context and Motion Decoupling
• Detection of Object Throwing Behavior in Surveillance Videos
• Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines
• MLtuner: System Support for Automatic Machine Learning Tuning
• Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking
• Video Frame Interpolation by Plug-and-Play Deep Locally Linear Embedding
• SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong
• Deep RNN Framework for Visual Sequential Applications
• Multi-shot Temporal Event Localization: a Benchmark
• Space-Time-Aware Multi-Resolution Video Enhancement
• Learning from Videos with Deep Convolutional LSTM Networks
• Decoupling Localization and Classification in Single Shot Temporal Action Detection
• Single Image Action Recognition by Predicting Space-Time Saliency
• STEP: Spatio-Temporal Progressive Learning for Video Action Detection
• Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms
• Event and Activity Recognition in Video Surveillance for Cyber-Physical Systems
• An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
• Spatio-Temporal Instance Learning: Action Tubes from Class Supervision
• Modeling Spatio-Temporal Human Track Structure for Action Localization
• Unified Generator-Classifier for Efficient Zero-Shot Learning
• Synthetic Defocus and Look-Ahead Autofocus for Casual Videography
• Viewpoint-aware Video Summarization
• Video Action Recognition Via Neural Architecture Searching
• Global Semantic Descriptors for Zero-Shot Action Recognition
• Action Class Relation Detection and Classification Across Multiple Video Datasets
• TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
• From Detection to Action Recognition: An Edge-Based Pipeline for Robot Human Perception
• Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web
• Order-aware Convolutional Pooling for Video Based Action Recognition
• Temporal Query Networks for Fine-grained Video Understanding
• Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
• P-CNN: Pose-based CNN Features for Action Recognition
• Elaborative Rehearsal for Zero-shot Action Recognition
• On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study
• VidTr: Video Transformer Without Convolutions
• Asymmetric Bilateral Motion Estimation for Video Frame Interpolation
• Context-aware and Scale-insensitive Temporal Repetition Counting
• Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
• Self-Supervised Representation Learning for Visual Anomaly Detection
• SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments
• Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
• Dense Relational Image Captioning via Multi-task Triple-Stream Networks
• Context-Aware RCNN: A Baseline for Action Detection in Videos
• Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition
• Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
• ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction
• Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction
• Symmetry and Group in Attribute-Object Compositions
• Temporal Tessellation: A Unified Approach for Video Analysis
• STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition
• Constraint Solving with Deep Learning for Symbolic Execution
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Projection Bank: From High-dimensional Data to Medium-length Binary Codes
• Stacked dense optical flows and dropout layers to predict sperm motility and morphology
• Cross-Class Relevance Learning for Temporal Concept Localization
• Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
• A spatiotemporal model with visual attention for video classification
• Tensor Analysis with n-Mode Generalized Difference Subspace
• Cooperative Cross-Stream Network for Discriminative Action Representation
• Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
• ActionVLAD: Learning spatio-temporal aggregation for action classification
• Manipulation-skill Assessment from Videos with Spatial Attention Network
• Vision-based Behavioral Recognition of Novelty Preference in Pigs
• 3DPalsyNet: A Facial Palsy Grading and Motion Recognition Framework using Fully 3D Convolutional Neural Networks
• Efficient Video Classification Using Fewer Frames
• A Structured Model For Action Detection
• Spatiotemporal Pyramid Network for Video Action Recognition
• Leveraging Random Label Memorization for Unsupervised Pre-Training
• Alternative Semantic Representations for Zero-Shot Human Action Recognition
• Large-Scale YouTube-8M Video Understanding with Deep Neural Networks
• Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
• AVD: Adversarial Video Distillation
• Predicting the Future: A Jointly Learnt Model for Action Anticipation
• Temporal Attentive Alignment for Video Domain Adaptation
• Towards an Unequivocal Representation of Actions
• Technical Report on Visual Quality Assessment for Frame Interpolation
• Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
• Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks
• Recognizing Video Events with Varying Rhythms
• Re-Identification Supervised Texture Generation
• Prediction-assistant Frame Super-Resolution for Video Streaming
• Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
• Action Detection from a Robot-Car Perspective
• Attention Transfer from Web Images for Video Recognition
• Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos
• P-ODN: Prototype based Open Deep Network for Open Set Recognition
• Action Tubelet Detector for Spatio-Temporal Action Localization
• A Temporally-Aware Interpolation Network for Video Frame Inpainting
• TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
• Extreme Low Resolution Activity Recognition with Confident Spatial-Temporal Attention Transfer
• Representing Videos as Discriminative Sub-graphs for Action Recognition
• Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
• Pooled Motion Features for First-Person Videos
• ContextVP: Fully Context-Aware Video Prediction
• Motion Feature Network: Fixed Motion Filter for Action Recognition
• Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
• Cross-Modal Message Passing for Two-stream Fusion
• Scheduled Differentiable Architecture Search for Visual Recognition
• Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
• Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination
• Disentangling Motion, Foreground and Background Features in Videos
• Spatial-Temporal Alignment Network for Action Recognition and Detection
• Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach
• Compositional Kronecker Context Optimization for Vision-Language Models
• KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
• Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
• Directional Temporal Modeling for Action Recognition
• Social Adaptive Module for Weakly-supervised Group Activity Recognition
• Universal-to-Specific Framework for Complex Action Recognition
• Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
• RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
• GradMix: Multi-source Transfer across Domains and Tasks
• Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
• Dance with Flow: Two-in-One Stream Action Detection
• Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
• TSI: Temporal Saliency Integration for Video Action Recognition
• Graph Distillation for Action Detection with Privileged Modalities
• Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
• VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
• Deep Learned Frame Prediction for Video Compression
• Learning Temporal Embeddings for Complex Video Analysis
• Learning Class Regularized Features for Action Recognition
• Video retrieval based on deep convolutional neural network
• Towards Visually Explaining Video Understanding Networks with Perturbation
• Future Frame Prediction of a Video Sequence
• Fast Video Classification via Adaptive Cascading of Deep Models
• Learning Cross-modal Contrastive Features for Video Domain Adaptation
• Multimodal Explanations by Predicting Counterfactuality in Videos
• Wide and Narrow: Video Prediction from Context and Motion
• 2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework
• Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations
• Unsupervised Semantic Action Discovery from Video Collections
• Video Time: Properties, Encoders and Evaluation
• Semi-Supervised Few-Shot Atomic Action Recognition
• Improved Dense Trajectory with Cross Streams
• Beat-Event Detection in Action Movie Franchises
• Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization
• Effective Action Recognition with Embedded Key Point Shifts
• Improving Human Action Recognition by Non-action Classification
• From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
• Latent Neural Differential Equations for Video Generation
• Understanding the Perceived Quality of Video Predictions
• Visual Recognition Using Directional Distribution Distance
• Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
• From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
• Targeted Attack for Deep Hashing based Retrieval
• Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations
• Learning from a Lightweight Teacher for Efficient Knowledge Distillation
• Evolution-Preserving Dense Trajectory Descriptors
• Contrastive Learning of Global-Local Video Representations
• Diverse Video Generation using a Gaussian Process Trigger
• Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
• Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
• CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition
• Learning spatio-temporal representations with temporal squeeze pooling
• Efficient Action Recognition Using Confidence Distillation
• Temporal Bilinear Networks for Video Action Recognition
• TimeGate: Conditional Gating of Segments in Long-range Activities
• Video Frame Interpolation Transformer
• Crowd Video Captioning
• DFPN: Deformable Frame Prediction Network
• CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
• Few Shot Activity Recognition Using Variational Inference
• VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
• Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification
• Repetitive Activity Counting by Sight and Sound
• Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding
• Self-Supervised Video Representation Learning with Meta-Contrastive Network
• Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
• Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention
• LIGAR: Lightweight General-purpose Action Recognition
• Ordered Pooling of Optical Flow Sequences for Action Recognition
• Compositional Structure Learning for Action Understanding
• An Experimentation Platform for Explainable Coalition Situational Understanding
• Falls Prediction Based on Body Keypoints and Seq2Seq Architecture
• Explainable Video Action Reasoning via Prior Knowledge and State Transitions
• Knowledge Integration Networks for Action Recognition
• The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
• Reinforcement Learning with Latent Flow
• iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
• Two-Stream Video Classification with Cross-Modality Attention
• Survey: Transformer based Video-Language Pre-training
• Discriminatively Learned Hierarchical Rank Pooling Networks
• Temporal Action Localization by Structured Maximal Sums
• From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
• Learning Spatio-Temporal Representation with Local and Global Diffusion
• Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
• Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach
• Efficient On-the-fly Category Retrieval using ConvNets and GPUs
• Video Modeling with Correlation Networks
• Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
• EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation
• Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification
• Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows
• Random Temporal Skipping for Multirate Video Analysis
• Detecting Human-to-Human-or-Object (H2O) Interactions with DIABOLO
• Spatio-Temporal Channel Correlation Networks for Action Classification
• Spatio-temporal Video Re-localization by Warp LSTM
• Deep Architectures and Ensembles for Semantic Video Classification
• Human Action Recognition with Deep Temporal Pyramids
• Informed Democracy: Voting-based Novelty Detection for Action Recognition
• AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos
• Self-Supervised Video Representation Learning by Video Incoherence Detection
• Recent Progress in Appearance-based Action Recognition
• Token Shift Transformer for Video Classification
• Video Contrastive Learning with Global Context
• Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
• Batch Normalization with Enhanced Linear Transformation
• Personalizing Pre-trained Models
• A multimodal deep learning framework for scalable content based visual media retrieval
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates
• Machine-Generated Hierarchical Structure of Human Activities to Reveal How Machines Think
• GCF-Net: Gated Clip Fusion Network for Video Action Recognition
• Efficient data-driven encoding of scene motion using Eccentricity
• Time and Frequency Network for Human Action Detection in Videos
• Deep set conditioned latent representations for action recognition
• PDWN: Pyramid Deformable Warping Network for Video Interpolation
• Efficient Spatialtemporal Context Modeling for Action Recognition
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
• Video Frame Interpolation via Structure-Motion based Iterative Fusion
• Unsupervised Visual Representation Learning by Tracking Patches in Video
• AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results
• Three-stream network for enriched Action Recognition
• Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
• Towards human-agent knowledge fusion (HAKF) in support of distributed coalition teams
• CS-MCNet:A Video Compressive Sensing Reconstruction Network with Interpretable Motion Compensation
• HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN
• Group Activity Prediction with Sequential Relational Anticipation Model
• Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation
• Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
• DeepLandscape: Adversarial Modeling of Landscape Video
• Spatiotemporal Action Recognition in Restaurant Videos
• Temporal Action Localization with Variance-Aware Networks
• Channel Pruning Guided by Classification Loss and Feature Importance
• Learning Temporal Action Proposals With Fewer Labels
• A Spectral Nonlocal Block for Neural Networks
• Exploiting Motion Information from Unlabeled Videos for Static Image Action Recognition
• Out the Window: A Crowd-Sourced Dataset for Activity Classification in Security Video
• Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
• Improvements of Motion Estimation and Coding using Neural Networks
• Robustness Guarantees for Deep Neural Networks on Videos
• UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition
• Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
• ODN: Opening the Deep Network for Open-set Action Recognition
• Video Summarization via Actionness Ranking
• Cross-Database Micro-Expression Recognition: A Benchmark
• Coupled Recurrent Network (CRN)
• Semantic Adversarial Network with Multi-scale Pyramid Attention for Video Classification
• Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
• Multi-Task Learning of Generalizable Representations for Video Action Recognition
• Human Activity Recognition for Edge Devices
• Ontology Based Global and Collective Motion Patterns for Event Classification in Basketball Videos
• Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression
• Temporal-Spatial Mapping for Action Recognition
• Articulated motion discovery using pairs of trajectories
• Action Anticipation By Predicting Future Dynamic Images
• Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition
• Memory-Augmented Temporal Dynamic Learning for Action Recognition
• Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning
• Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
• M-PACT: An Open Source Platform for Repeatable Activity Classification Research
• Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection
• Predicting the Future with Transformational States
• Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model
• Deep-Temporal LSTM for Daily Living Action Recognition
• Deep Spatio-temporal Manifold Network for Action Recognition
• Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
• Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes
• Multi-kernel learning of deep convolutional features for action recognition
• Action Understanding with Multiple Classes of Actors
• Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition
• Action Representation Using Classifier Decision Boundaries
• Unsupervised Human Action Detection by Action Matching
• Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach
• Dimensionality Reduction on Grassmannian via Riemannian Optimization: A Generalized Perspective
• Temporally Robust Global Motion Compensation by Keypoint-based Congealing
• Dynamic Concept Composition for Zero-Example Event Detection
• From Pose to Activity: Surveying Datasets and Introducing CONVERSE
• Collecting and Annotating the Large Continuous Action Dataset
• Tubelets: Unsupervised action proposals from spatiotemporal super-voxels
• Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos
• LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
• Gradient Boundary Histograms for Action Recognition
• A stepped sampling method for video detection using LSTM
• Using phase instead of optical flow for action recognition
• Multi-View Intact Space Learning
• Temporal Action Detection by Joint Identification-Verification
• Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks
• Discovering Spatio-Temporal Action Tubes
• Circulant temporal encoding for video retrieval and temporal alignment
• The Untold Secrets of Operational Wi-Fi Calling Services: Vulnerabilities, Attacks, and Countermeasures
• Deep Multimodal Learning: An Effective Method for Video Classification
• Action Quality Assessment Across Multiple Actions
• An Improved Video Analysis using Context based Extension of LSH
• Exploring Frame Segmentation Networks for Temporal Action Localization
• Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures
• Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation
• Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
• Adaptive Future Frame Prediction with Ensemble Network
• Face-Focused Cross-Stream Network for Deception Detection in Videos
• Learning to Estimate Pose by Watching Videos
• Open Set Domain Adaptation for Image and Action Recognition
• Deep Learning for Fitness
• Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• Image to Video Domain Adaptation Using Web Supervision
• Multi-Stream Single Shot Spatial-Temporal Action Detection
• CTM: Collaborative Temporal Modeling for Action Recognition
• Discriminative Video Representation Learning Using Support Vector Classifiers
• Multi-Modal Three-Stream Network for Action Recognition
• Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
• Global Temporal Representation based CNNs for Infrared Action Recognition
• Action Anticipation with RBF Kernelized Feature Mapping RNN
• A Proposed Artificial intelligence Model for Real-Time Human Action Localization and Tracking
• Predictive Coding Networks Meet Action Recognition
• Adaptive and Iteratively Improving Recurrent Lateral Connections
• ViP: Video Platform for PyTorch
• Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recogntion
• On Compositions of Transformations in Contrastive Self-Supervised Learning
• Knowledge Fusion Transformers for Video Action Recognition
• Long Short-Term Relation Networks for Video Action Detection
• Temporal Accumulative Features for Sign Language Recognition
• Nuisance-Label Supervision: Robustness Improvement by Free Labels
• Learning To Score Olympic Events
• Online Spatiotemporal Action Detection and Prediction via Causal Representations
• Finding Action Tubes with a Sparse-to-Dense Framework
• VideoMCC: a New Benchmark for Video Comprehension
• CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
• SegCodeNet: Color-Coded Segmentation Masks for Activity Detection from Wearable Cameras
• Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos
• Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
• Long Short View Feature Decomposition via Contrastive Video Representation Learning
• Approximated Bilinear Modules for Temporal Modeling
• Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic
• PersonRank: Detecting Important People in Images
• Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
• FREGAN : an application of generative adversarial networks in enhancing the frame rate of videos
• Spot On: Action Localization from Pointly-Supervised Proposals
• Learning to Sort Image Sequences via Accumulated Temporal Differences
• Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
• A Real-time Action Representation with Temporal Encoding and Deep Compression
• Physical Context and Timing Aware Sequence Generating GANs
• PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
• Modelling Temporal Information Using Discrete Fourier Transform for Video Classification
• Deep hierarchical pooling design for cross-granularity action recognition
• Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
• PreViTS: Contrastive Pretraining with Video Tracking Supervision
• Few-Shot Transformation of Common Actions into Time and Space
• 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
• Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
• CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
• Unsupervised Motion Representation Enhanced Network for Action Recognition
• Advancing Video Self-Supervised Learning via Image Foundation Models
• Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting
• Efficient Modelling Across Time of Human Actions and Interactions
• GTM: Gray Temporal Model for Video Recognition
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• Smoothed Gaussian Mixture Models for Video Classification and Recommendation
• Boosting Video Representation Learning with Multi-Faceted Integration
• Action parsing using context features
• Detecting Biological Locomotion in Video: A Computational Approach
• Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
• Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification
• Long-Short Temporal Modeling for Efficient Action Recognition
• Efficient Clustering on Riemannian Manifolds: A Kernelised Random Projection Approach
• Empowering cyberphysical systems of systems with intelligence
• Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
• Delta Sampling R-BERT for limited data and low-light action recognition
• T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition
• MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks
• Layout-induced Video Representation for Recognizing Agent-in-Place Actions
• Exploring Feature Representation and Training strategies in Temporal Action Localization
• Exploring Temporal Information for Improved Video Understanding
• Recurrent Residual Module for Fast Inference in Videos
• On Flow Profile Image for Video Representation
• Deep Discriminative Model for Video Classification
• Learning Single/Multi-Attribute of Object with Symmetry and Group
• Sidekick Policy Learning for Active Visual Exploration
• Motion Representation with Acceleration Images
• Feature-Supervised Action Modality Transfer
• TraMNet - Transition Matrix Network for Efficient Action Tube Proposals
• DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
• Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
• Channel-Temporal Attention for First-Person Video Domain Adaptation
• Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
• Large-Scale Mapping of Human Activity using Geo-Tagged Videos
• Stochastic Dynamics for Video Infilling