{"total":89,"rows":[{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"area":null},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40,"area":null},{"id":"2106.08827","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","created":"2021-06-16","cited_by_count":39,"area":null},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2204.02148","title":"Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition","created":"2022-04-05","cited_by_count":27,"area":null},{"id":"2401.14535","title":"CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process","created":"2024-01-25","cited_by_count":23,"area":null},{"id":"2103.01933","title":"PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception","created":"2021-03-02","cited_by_count":22,"area":null},{"id":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","cited_by_count":22,"area":null},{"id":"2203.02281","title":"A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2204.02139","title":"Detector-Free Weakly Supervised Group Activity Recognition","created":"2022-04-05","cited_by_count":20,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2108.04186","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","created":"2021-08-09","cited_by_count":16,"area":null},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2303.12149","title":"SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition","created":"2023-03-06","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2203.03806","title":"Panoramic Human Activity Recognition","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2409.03142","title":"Causal Temporal Representation Learning with Nonstationary Sparse Transition","created":"2024-09-05","cited_by_count":13,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2101.08967","title":"Human Interaction Recognition Framework based on Interacting Body Part Attention","created":"2021-01-22","cited_by_count":11,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2312.02878","title":"Towards More Practical Group Activity Detection: A New Benchmark and Model","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2512.11016","title":"SoccerMaster: A Vision Foundation Model for Soccer Understanding","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2311.05237","title":"Widely Applicable Strong Baseline for Sports Ball Detection and Tracking","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2305.06310","title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","created":"2023-04-27","cited_by_count":8,"area":null},{"id":"2207.06235","title":"Entry-Flipped Transformer for Inference and Prediction of Participant Behavior","created":"2022-07-13","cited_by_count":7,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2309.12067","title":"Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives","created":"2023-09-21","cited_by_count":7,"area":null},{"id":"2504.08222","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2209.13846","title":"VREN: Volleyball Rally Dataset with Expression Notation Language","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2308.05382","title":"Interaction-aware Joint Attention Estimation Using People Attributes","created":"2023-08-10","cited_by_count":6,"area":null},{"id":"2407.19497","title":"Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph","created":"2024-07-28","cited_by_count":6,"area":null},{"id":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2209.00451","title":"Group Activity Recognition in Basketball Tracking Data -- Neural Embeddings in Team Sports (NETS)","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2306.16772","title":"M3Act: Learning from Synthetic Human Group Activities","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2312.00188","title":"REACT: Recognize Every Action Everywhere All At Once","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2105.06754","title":"Learning Group Activities from Skeletons without Individual Action Labels","created":"2021-05-14","cited_by_count":4,"area":null},{"id":"2108.11149","title":"A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games","created":"2021-08-25","cited_by_count":4,"area":null},{"id":"2312.07740","title":"HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2405.18012","title":"Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2104.14131","title":"Actor-centered Representations for Action Localization in Streaming Videos","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2410.07153","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2507.14807","title":"Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2106.05891","title":"Temporal and Object Quantification Networks","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2302.14350","title":"Knowledge Augmented Relation Inference for Group Activity Recognition","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2303.06439","title":"DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image","created":"2023-03-11","cited_by_count":2,"area":null},{"id":"2308.11142","title":"Graph Encoding and Neural Network Approaches for Volleyball Analytics: From Game Outcome to Individual Play Predictions","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2403.02753","title":"Learning Group Activity Features Through Person Attribute Prediction","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2406.01551","title":"ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2511.12606","title":"Pixels or Positions? Benchmarking Modalities in Group Activity Recognition","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2208.05034","title":"Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2309.11445","title":"SkeleTR: Towrads Skeleton-based Action Recognition in the Wild","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2401.03262","title":"Group Activity Recognition using Unreliable Tracked Pose","created":"2024-01-06","cited_by_count":1,"area":null},{"id":"2403.14113","title":"Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2404.09964","title":"Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2410.21108","title":"LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2101.08581","title":"Hierarchical Graph-RNNs for Action Detection of Multiple Activities","created":"2021-01-21","cited_by_count":0,"area":null},{"id":"2101.10857","title":"Indoor Group Activity Recognition using Multi-Layered HMMs","created":"2021-01-23","cited_by_count":0,"area":null},{"id":"2104.11931","title":"Adaptive Appearance Rendering","created":"2021-04-24","cited_by_count":0,"area":null},{"id":"2110.04931","title":"BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning","created":"2021-10-10","cited_by_count":0,"area":null},{"id":"2208.14847","title":"Attentive pooling for Group Activity Recognition","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2302.05763","title":"Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2305.05583","title":"Group Activity Recognition via Dynamic Composition and Interaction","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2306.06078","title":"Cheating off your neighbors: Improving activity recognition through corroboration","created":"2023-05-27","cited_by_count":0,"area":null},{"id":"2307.13541","title":"Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2407.19820","title":"ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2502.09967","title":"VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.08933","title":"PromptGAR: Flexible Promptive Group Activity Recognition","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2509.00490","title":"Multi-Focused Video Group Activities Hashing","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.03157","title":"Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.04467","title":"Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.10078","title":"Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2605.20838","title":"USV: Towards Understanding the User-generated Short-form Videos","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.21267","title":"BasketEvent: Understanding Who Did What and When in Basketball Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.23077","title":"Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoning","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.27879","title":"What Do Interaction Representations Actually Measure? Pre-Event Separability in Weakly-Supervised Violence Detection","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.04716","title":"Counting Beyond Instances: A Benchmark for Group-Individual Object Counting","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32454","title":"De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}