BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning

• URL: http://arxiv.org/abs/2603.25533v1
• Date: Thu, 26 Mar 2026 15:09:12 GMT
• Title: BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning
• Abstract summary: We introduce the first Badminton Full Match Dense dataset, with 19 broadcast matches covering over 20 hours of play, each annotated with a shot caption.<n>The dataset provides hierarchical annotations including match segments, rally events, and dense rally-level multimodal annotations such as shot types, shuttle trajectories, player pose keypoints, and shot captions.<n>We develop a VideoMAE-based multimodal captioning framework with a Semantic Feedback mechanism that leverages shot semantics to guide caption generation and improve semantic consistency.
• Score: 10.526240385265256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding tactical dynamics in badminton requires analyzing entire matches rather than isolated clips. However, existing badminton datasets mainly focus on short clips or task-specific annotations and rarely provide full-match data with dense multimodal annotations. This limitation makes it difficult to generate accurate shot captions and perform match-level analysis. To address this limitation, we introduce the first Badminton Full Match Dense (BFMD) dataset, with 19 broadcast matches (including both singles and doubles) covering over 20 hours of play, comprising 1,687 rallies and 16,751 hit events, each annotated with a shot caption. The dataset provides hierarchical annotations including match segments, rally events, and dense rally-level multimodal annotations such as shot types, shuttle trajectories, player pose keypoints, and shot captions. We develop a VideoMAE-based multimodal captioning framework with a Semantic Feedback mechanism that leverages shot semantics to guide caption generation and improve semantic consistency. Experimental results demonstrate that multimodal modeling and semantic feedback improve shot caption quality over RGB-only baselines. We further showcase the potential of BFMD by analyzing the temporal evolution of tactical patterns across full matches.

Related papers

• BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing [9.244368483134101]
  We present BoxComm, a large-scale dataset comprising 445 World Boxing Championship match videos with over 52K commentary sentences from professional broadcasts.<n>We propose a structured commentary taxonomy that categorizes each sentence into play-by-play, tactical, or contextual.<n>We introduce two novel and complementary evaluations tailored to sports commentary generation.
  arXiv  Detail & Related papers  (2026-04-06T04:56:49Z)
• TennisExpert: Towards Expert-Level Analytical Sports Video Understanding [16.625250626542208]
  Tennis is one of the most widely followed sports, generating extensive broadcast footage with strong potential for professional analysis, automated coaching, and real-time commentary.<n>However, automatic tennis understanding remains underexplored due to lack of large-scale benchmarks with fine-grained annotations and expert-level commentary.<n>To address these challenges, we introduce TennisVL, a large-scale tennis benchmark comprising over 200 professional matches (471.9 hours) and 40,000+ rally-level clips.<n>We propose TennisExpert, a multimodal tennis understanding framework that integrates a video semantic with a memory-augmented model built on Qwen3-VL-8B
  arXiv  Detail & Related papers  (2026-03-11T15:12:10Z)
• E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching [87.38371267983263]
  Temporal Video Grounding aims to precisely localize time segments corresponding to query events.<n>E.M.Ground is a novel Vid-LLM for TVG that focuses on holistic and coherent event perception.<n>E.M.Ground consistently outperforms state-of-the-art Vid-LLMs by significant margins.
  arXiv  Detail & Related papers  (2026-02-05T02:16:00Z)
• Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding [10.526240385265256]
  We propose bfShot2Tactic-Caption, a novel framework for semantic and temporal multi-scale video captioning in badminton.<n>Shot2Tactic-Caption adopts a dual-branch design, with both branches including a visual encoder, atemporal Transformer encoder, and a Transformer-based decoder.<n>For tactic captioning, we further incorporate a shot-wise prompt-guided mechanism, where the predicted tactic type state are embedded as prompts and injected into the decoder.
  arXiv  Detail & Related papers  (2025-10-16T12:24:51Z)
• Bridging the Gap: Doubles Badminton Analysis with Singles-Trained Models [0.0]
  badminton is one of the fastest racket sports in the world.<n>Previous research has mainly focused on singles due to the challenges in data availability and multi-person tracking.<n>This work establishes a foundation for doubles-specific datasets to enhance understanding of this predominant yet understudied format of the fast racket sport.
  arXiv  Detail & Related papers  (2025-08-19T04:45:15Z)
• AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation [52.655400705690155]
  AnimeShooter is a reference-guided multi-shot animation dataset.<n>Story-level annotations provide an overview of the narrative, including the storyline, key scenes, and main character profiles with reference images.<n>Shot-level annotations decompose the story into consecutive shots, each annotated with scene, characters, and both narrative and descriptive visual captions.<n>A separate subset, AnimeShooter-audio, offers synchronized audio tracks for each shot, along with audio descriptions and sound sources.
  arXiv  Detail & Related papers  (2025-06-03T17:55:18Z)
• VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models [48.00262713744499]
  VideoComp is a benchmark and learning framework for advancing video-text compositionality understanding.<n>We create challenging negative samples with subtle temporal disruptions such as reordering, action word replacement, partial captioning, and combined disruptions.<n>These benchmarks comprehensively test models' compositional sensitivity across extended, cohesive video-text sequences.
  arXiv  Detail & Related papers  (2025-04-04T22:24:30Z)
• MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions [69.9122231800796]
  We present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions.<n>We propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos.<n>Our dataset potentially paves the path for fine-grained large multimodal-language model training.
  arXiv  Detail & Related papers  (2024-07-30T16:43:24Z)
• P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos [64.57435509822416]
  This work consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads. We formulate two sets of action detection problems -- emphaction localization and emphaction recognition. The results confirm that TheName is still a challenging task and can be used as a special benchmark for dense action detection from videos.
  arXiv  Detail & Related papers  (2022-07-26T08:34:17Z)
• Exploring the Long Short-Term Dependencies to Infer Shot Influence in Badminton Matches [9.553207911311926]
  We introduce a badminton language to fully describe the process of the shot. We propose a deep learning model composed of a novel short-term extractor and a long-term encoder. Our model incorporates an attention mechanism to enable the transparency of the action sequence to the rally result.
  arXiv  Detail & Related papers  (2021-09-14T04:44:40Z)
• Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts [86.56462654572813]
  We focus our analysis on action spotting in soccer broadcast, which consists in temporally localizing the main actions in a soccer game. We propose a novel feature pooling method based on NetVLAD, dubbed NetVLAD++, that embeds temporally-aware knowledge. We train and evaluate our methodology on the recent large-scale dataset SoccerNet-v2, reaching 53.4% Average-mAP for action spotting.
  arXiv  Detail & Related papers  (2021-04-14T11:09:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.