{"total":46,"rows":[{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169,"area":null},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71,"area":null},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2203.16795","title":"Deformable Video Transformer","created":"2022-03-31","cited_by_count":15,"area":null},{"id":"2109.00953","title":"TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction","created":"2021-09-02","cited_by_count":13,"area":null},{"id":"2307.08908","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","created":"2023-07-18","cited_by_count":12,"area":null},{"id":"2402.03019","title":"Taylor Videos for Action Recognition","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2201.10394","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","created":"2022-01-25","cited_by_count":10,"area":null},{"id":"2101.00317","title":"Identity-aware Facial Expression Recognition in Compressed Video","created":"2021-01-01","cited_by_count":9,"area":null},{"id":"2312.02226","title":"Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2201.04022","title":"Condensing a Sequence to One Informative Frame for Video Recognition","created":"2022-01-11","cited_by_count":6,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2506.10516","title":"CogStream: Context-guided Streaming Video Question Answering","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2104.00179","title":"Selective Feature Compression for Efficient Activity Recognition Inference","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2309.15431","title":"Local Compressed Video Stream Learning for Generic Event Boundary Detection","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2103.03465","title":"Unsupervised Motion Representation Enhanced Network for Action Recognition","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2104.09760","title":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2105.06711","title":"REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2401.08609","title":"F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2509.17084","title":"MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2509.21595","title":"Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2112.02523","title":"STSM: Spatio-Temporal Shift Module for Efficient Action Recognition","created":"2021-12-05","cited_by_count":1,"area":null},{"id":"2205.03569","title":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","created":"2022-05-07","cited_by_count":1,"area":null},{"id":"2207.05249","title":"Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling","created":"2022-07-12","cited_by_count":1,"area":null},{"id":"2412.01267","title":"EdgeOAR: Real-time Online Action Recognition On Edge Devices","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2109.03783","title":"Egocentric View Hand Action Recognition by Leveraging Hand Surface and Hand Grasp Type","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2111.03319","title":"KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization","created":"2021-11-05","cited_by_count":0,"area":null},{"id":"2206.08429","title":"Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2211.14449","title":"PatchBlender: A Motion Prior for Video Transformers","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2306.13285","title":"Learning Scene Flow With Skeleton Guidance For 3D Action Recognition","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2503.00796","title":"An Efficient 3D Convolutional Neural Network with Channel-wise, Spatial-grouped, and Temporal Convolutions","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2503.12034","title":"Real-Time Manipulation Action Recognition with a Factorized Graph Sequence Encoder","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2608.10790","title":"MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}