Research map / Video / Action recognition
MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
Yixuan Li, Lei Chen, Runyu He, Zhenzhi Wang, Gangshan Wu, Limin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use longer tubelet length K (1 to 11) in MOC (ablation) | MOC · MultiSports val | frame-mAP@0.5: 14.61 -> 25.22 | Improved |
| use longer tubelet length K (1 to 11) in MOC (ablation) | MOC · MultiSports val | video-mAP@0.5: 1.06 -> 0.62 | No clear effect |
| use longer tubelet length K (1 to 7) in MOC (ablation) | MOC · UCF101-24 | frame-mAP@0.5: 68.33 -> 73.14 | Improved |
| use SlowFast Det. instead of SlowOnly Det. | MultiSports detectors · MultiSports val | frame-mAP@0.5: 16.70 -> 27.72 | Improved |
| use SlowFast Det. instead of SlowOnly Det. | AVA detectors · AVA | frame-mAP@0.5: 20.02 -> 24.56 | Improved |
| evaluate only annotated frames (trimmed) instead of all frames (ablation) | SlowFast Det. · MultiSports val | frame-mAP@0.5: 27.72 -> 38.71 | Improved |
| evaluate only annotated frames (trimmed) instead of all frames (ablation) | SlowFast Det. · MultiSports val | video-mAP@0.5: 9.65 -> 18.34 | Improved |
| evaluate only annotated frames (trimmed) instead of all frames (ablation) | SlowFast Det. · MultiSports val | video-mAP@0.2: 24.18 -> 24.95 | No clear effect |
| remove random temporal noise from training GT boundaries (ablation) | MOC (K=7) · MultiSports val | frame-mAP@0.5: 13.71 -> 22.51 | Improved |
| remove random temporal noise from training GT boundaries (ablation) | SlowOnly Det. · MultiSports val | video-mAP@0.5: 3.05 -> 5.50 | Improved |
| remove random temporal noise from training GT boundaries (ablation) | SlowOnly Det. · MultiSports val | video-mAP@0.2: 8.98 -> 15.71 | Improved |
| remove random temporal noise from training GT boundaries (ablation) | MOC (K=7) · MultiSports val | video-mAP@0.2: 8.59 -> 12.13 | Improved |
Closest papers by meaning
- FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding (CVPR 2024 · similarity 0.91)
- SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos (CVPR 2024 · similarity 0.89)
- ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis (AAAI 2024 · similarity 0.87)
- ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition (NeurIPS 2024 · similarity 0.86)
- Towards Universal Soccer Video Understanding (CVPR 2025 · similarity 0.86)
- BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
