Metraipolis › archive › dc_b5920e64237d

Revisiting Risky Tackle Detection with Vision Transformers — arXiv:2609.35562

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35562
License (as archived)
CC0-1.0
Archived
2026-10-07T23:54:51.903Z
SHA-256 of the archived text
db5ea95a904a4a943d34cc61d358fa7e828127c26493845a76305311fc0815a6
Stable URL of this page
https://metraipolis.com/documento/dc_b5920e64237d

How to cite

Revisiting Risky Tackle Detection with Vision Transformers — arXiv:2609.35562 — arXiv (en), https://arxiv.org/abs/2609.35562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5920e64237d (Metraipolis archive dc_b5920e64237d, sha256 db5ea95a904a4a943d34cc61d358fa7e828127c26493845a76305311fc0815a6)
BibTeX
@misc{dcb5920e64237d,
  title = {Revisiting Risky Tackle Detection with Vision Transformers — arXiv:2609.35562},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35562},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5920e64237d; sha256 db5ea95a904a4a943d34cc61d358fa7e828127c26493845a76305311fc0815a6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper is a Track 2 reproducibility companion to an ICPR 2026 study on risky tackle detection in American football prac- tice videos. The original work fine-tuned a Video Vision Transformer (ViViT) on 733 clips labeled with the SATT-3 rubric. It used focal loss, Taguchi L18 augmentation, and 5-fold cross-validation. It reported risky- class recall of 0.67 and risky-class F1 of 0.59. This companion documents the released artifact and traces those numbers to specific scripts, fold out- puts, and aggregation files. The reproduced headline is run_15. It com- bines Gaussian noise with static brightness decrease and uses no rotation and no flip. Its fold-mean risky recall is 0.667 and its fold-mean risky F1 is 0.588. These values match the published headline after rounding. The ablation shows that brightness is the dominant factor. Its risky-recall main-effect range is 0.055, which is larger than the ranges for rotation, flip, and noise. Without augmentation, ViViT reaches risky recall of 0.545 and does not exceed the C3D baseline of 0.583. The raw clips show iden- tifiable student athletes, so they cannot be redistributed. The artifact provides a public sample for pipeline checks and a controlled route for full-data review.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35562 — 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 2026-10-07T23:29:27.594Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).