{"total":54,"rows":[{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2403.08506","title":"DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning","created":"2024-03-11","cited_by_count":32,"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":"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":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","cited_by_count":22,"area":null},{"id":"2211.13234","title":"RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer","created":"2022-11-23","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":"2206.06131","title":"Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers","created":"2022-06-10","cited_by_count":18,"area":null},{"id":"2407.12322","title":"Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer","created":"2024-07-17","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":"2202.11423","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","created":"2022-02-23","cited_by_count":13,"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":"2208.05470","title":"EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2206.10157","title":"Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning","created":"2022-06-21","cited_by_count":9,"area":null},{"id":"2307.05358","title":"Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators","created":"2023-07-11","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":"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":"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":"2312.00188","title":"REACT: Recognize Every Action Everywhere All At Once","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2109.14251","title":"Road Network Guided Fine-Grained Urban Traffic Flow Inference","created":"2021-09-29","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":"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":"2507.13305","title":"Boosting Team Modeling through Tempo-Relational Representation Learning","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2206.10095","title":"Pyramid Region-based Slot Attention Network for Temporal Action Proposal Generation","created":"2022-06-21","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":"2305.18724","title":"Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer","created":"2023-05-30","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":"2406.14472","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":"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":"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":"2511.08260","title":"Data-Driven Discovery of Feature Groups in Clinical Time Series","created":"2025-11-11","cited_by_count":1,"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":"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":"2408.00420","title":"MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition","created":"2024-08-01","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":"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}