{"total":19,"rows":[{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2406.12252","title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","created":"2024-06-18","cited_by_count":10,"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":"2510.17364","title":"Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs","created":"2025-10-20","cited_by_count":9,"area":null},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2406.14877","title":"Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video","created":"2024-06-21","cited_by_count":6,"area":null},{"id":"2504.19514","title":"FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2510.01247","title":"Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2503.15887","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2510.14617","title":"Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2604.00677","title":"CL-VISTA: Benchmarking Continual Learning in Video Large Language Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2512.01853","title":"COACH: Collaborative Agents for Contextual Highlighting -- A Multi-Agent Framework for Sports Video Analysis","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2604.15736","title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2608.23435","title":"Towards Comprehensive Basketball Understanding","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2409.09348","title":"QTG-VQA: Question-Type-Guided Architectural for VideoQA Systems","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2606.09181","title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.14377","title":"A Survey of Large Models in Sports","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}