{"total":84,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"area":null},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55,"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":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"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":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"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":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"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":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"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":"2103.16469","title":"Spatiotemporal Transformer for Video-based Person Re-identification","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2111.11535","title":"Ice hockey player identification via transformers and weakly supervised learning","created":"2021-11-22","cited_by_count":14,"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":"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":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","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":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10,"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":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2203.03843","title":"Self-supervised Social Relation Representation for Human Group Detection","created":"2022-03-08","cited_by_count":7,"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":"2310.01232","title":"Modality-aware Transformer for Financial Time series Forecasting","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2506.01890","title":"CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection","created":"2025-06-02","cited_by_count":7,"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":"2502.15462","title":"Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks","created":"2025-02-21","cited_by_count":6,"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":"2211.08144","title":"Monocular BEV Perception of Road Scenes via Front-to-Top View Projection","created":"2022-11-15","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":"2104.14131","title":"Actor-centered Representations for Action Localization in Streaming Videos","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2301.03832","title":"Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2303.16118","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2311.10671","title":"Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2403.16244","title":"On the Equivalency, Substitutability, and Flexibility of Synthetic Data","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","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":"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":"2403.02753","title":"Learning Group Activity Features Through Person Attribute Prediction","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2405.02538","title":"AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2406.14472","title":"Self-supervised Multi-actor Social Activity Understanding in Streaming Videos","created":"2024-06-20","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":"2208.01161","title":"Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer","created":"2022-08-01","cited_by_count":1,"area":null},{"id":"2304.08803","title":"MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition","created":"2023-04-18","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":"2410.18972","title":"Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques","created":"2024-10-24","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":"2104.02439","title":"Few-Shot Transformation of Common Actions into Time and Space","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2301.11880","title":"Optical Flow Estimation in 360$^\\circ$ Videos: Dataset, Model and Application","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2302.09327","title":"Transformadores: Fundamentos teoricos y Aplicaciones","created":"2023-02-18","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":"2305.09539","title":"Learning Higher-order Object Interactions for Keypoint-based Video Understanding","created":"2023-05-16","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":"2511.03666","title":"Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection","created":"2025-11-05","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":"2606.12374","title":"Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration","created":"2026-06-10","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":"2608.01696","title":"Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting","created":"2026-08-03","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":"2609.32454","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}