{"total":57,"rows":[{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"area":null},{"id":"2404.11335","title":"SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap","created":"2024-04-17","cited_by_count":34,"area":null},{"id":"2404.06332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","created":"2024-04-07","cited_by_count":22,"area":"mllm"},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","cited_by_count":20,"area":null},{"id":"2401.09942","title":"Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2504.17365","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","created":"2025-04-24","cited_by_count":13,"area":"mllm"},{"id":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12,"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":"2512.11016","title":"SoccerMaster: A Vision Foundation Model for Soccer Understanding","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2504.16030","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","created":"2025-04-22","cited_by_count":9,"area":null},{"id":"2407.12483","title":"Towards AI-Powered Video Assistant Referee System (VARS) for Association Football","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2409.10587","title":"SoccerNet 2024 Challenges Results","created":"2024-09-16","cited_by_count":8,"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":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2410.01304","title":"Deep learning for action spotting in association football videos","created":"2024-10-02","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":"2505.13860","title":"Domain Adaptation of VLM for Soccer Video Understanding","created":"2025-05-20","cited_by_count":7,"area":"mllm"},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7,"area":null},{"id":"2509.04602","title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2506.17294","title":"From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary","created":"2025-06-17","cited_by_count":3,"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":"2510.19150","title":"X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2603.06213","title":"Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.11786","title":"GenTac: Generative Modeling and Forecasting of Soccer Tactics","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2401.13888","title":"Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2407.01265","title":"OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videos","created":"2024-07-01","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":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2407.02370","title":"Investigating Event-Based Cameras for Video Frame Interpolation in Sports","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2506.17144","title":"Do We Need Large VLMs for Spotting Soccer Actions?","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2511.09448","title":"MCAD: Multimodal Context-Aware Audio Description Generation For Soccer","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2603.11460","title":"Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.13397","title":"TennisExpert: Towards Expert-Level Analytical Sports Video Understanding","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.25533","title":"BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.00057","title":"Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.05636","title":"Towards Athlete Fatigue Assessment from Association Football Videos","created":"2026-04-07","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":"2605.09598","title":"SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2607.07320","title":"SoccerNet 2026 Challenges Results","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2407.16076","title":"PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clips","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2508.07543","title":"Commentary Generation for Soccer Highlights","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.11569","title":"TrajSV: A Trajectory-based Model for Sports Video Representations and Applications","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2602.08996","title":"Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2604.04419","title":"BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2604.23392","title":"SoccerRef-Agents: Multi-Agent System for Automated Soccer Refereeing","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2606.12106","title":"MSUE: Multi-Modal Soccer Understanding Expert","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.10990","title":"TreeSoc: Tree-Structured Dynamic Reasoning and Tool Synergy for Soccer Video Understanding","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2607.14660","title":"VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance","created":"2026-07-16","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":"2608.09200","title":"NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14016","title":"Content Based Video Narration of Gameplay with Vision Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.14377","title":"A Survey of Large Models in Sports","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.19646","title":"PL-NBA: A Possession-level Universal Basketball Video Dataset Supporting Multiple Visual Understanding Tasks","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.19723","title":"StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.35427","title":"LLMs are General Asynchronous Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}