Metraipolis › archive › dc_fd663a78f65f
BMASH: Ball-Motion-Aware Soccer Header Spotting — arXiv:2609.39300
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39300
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:02.265Z
- SHA-256 of the archived text
2384eb03c22ddd82ba0bc736a31d8b3e07cd9f0ed387eecbba8306ca34d95476- Stable URL of this page
https://metraipolis.com/documento/dc_fd663a78f65f
How to cite
BMASH: Ball-Motion-Aware Soccer Header Spotting — arXiv:2609.39300 — arXiv (en), https://arxiv.org/abs/2609.39300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd663a78f65f (Metraipolis archive dc_fd663a78f65f, sha256 2384eb03c22ddd82ba0bc736a31d8b3e07cd9f0ed387eecbba8306ca34d95476)
BibTeX
@misc{dcfd663a78f65f,
title = {BMASH: Ball-Motion-Aware Soccer Header Spotting — arXiv:2609.39300},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39300},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd663a78f65f; sha256 2384eb03c22ddd82ba0bc736a31d8b3e07cd9f0ed387eecbba8306ca34d95476},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in computer vision have made broadcast sports videos increasingly useful for event analysis, performance assessment, and player-safety applications. In soccer, however, header spotting remains a challenging problem due to the subtle and short-lived nature of header events. This paper focuses on soccer header spotting: identifying moments in broadcast videos where the ball contacts a player's head. We first adapt and evaluate Video Swin as a strong action-recognition baseline for this task, and then introduce BMASH, a ball-motion-aware fusion framework that integrates detector-derived ball features. BMASH combines Video Swin action representations with ball-presence and motion features from frame-level soccer-ball detection, integrating player-action context with ball dynamics to distinguish headers from visually similar events. We evaluate BMASH using game-level splits with separate test matches and rotating validation folds, considering both centered-window classification and continuous full-video spotting. Results show that Video Swin provides a strong baseline for header spotting, while BMASH improves clip-level AP and ROC-AUC over the corresponding Video Swin baseline. In continuous full-video spotting, BMASH achieves a comparable event-level F1-performance with a different precision--recall trade-off. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39300 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T14:19:00.721Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).