RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis
Not on the map. Why?
Abstract (arXiv)
We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket pose alongside traditional ball positions, enabling research into complex human-object interactions. It is designed to tackle three interconnected tasks: fine-grained ball tracking, articulated racket pose estimation, and predictive ball trajectory forecasting. Our evaluation of established baselines reveals a critical insight for multi-modal fusion: while naively concatenating racket pose features degrades performance, a CrossAttention mechanism is essential to unlock their value, leading to trajectory prediction results that surpass strong unimodal baselines. RacketVision provides a versatile resource and a strong starting point for future research in dynamic object tracking, conditional motion forecasting, and multimodal analysis in sports. Project page at https://github.com/OrcustD/RacketVision
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 21 Nov 2025.
Builds on
23 of 37 references.
References · 23
- 2017Attention Is All You Needcited by 60,361
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
- 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
- 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 131
- 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
- 2023TacticAI: an AI assistant for football tacticscited by 44
- 2019TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applicationscited by 33
- 2024Achieving Human Level Competitive Robot Table Tenniscited by 27
- 2022Semi-Supervised Training to Improve Player and Ball Detection in Soccercited by 25
- 2022Blur Interpolation Transformer for Real-World Motion from Blurcited by 25
- 2025Learning coordinated badminton skills for legged manipulatorscited by 19
11 more
- 2022Animation from Blur: Multi-modal Blur Decomposition with Motion Guidancecited by 16
- 2019DeepBall: Deep Neural-Network Ball Detectorcited by 11
- 2024Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequencecited by 11
- 2021Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objectscited by 10
- 2024ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatarscited by 10
- 2024Sequential Gaussian Avatars with Hierarchical Motion Contextcited by 9
- 2023Table Tennis Stroke Detection and Recognition Using Ball Trajectory Datacited by 5
- 2025LATTE-MV: Learning to Anticipate Table Tennis Hits from Monocular Videoscited by 5
- 2025SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tacticcited by 4
- 2025Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfercited by 4
- 2025Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematicscited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.