ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911560799092736 |
|---|---|
| author | Zaidi, Syed Ahsan Masud Hsu, William Dietrich, Scott |
| author_facet | Zaidi, Syed Ahsan Masud Hsu, William Dietrich, Scott |
| contents | Early identification of hazardous actions in contact sports enables timely intervention and improves player safety. We present a method for detecting risky tackles in American football practice videos and introduce a substantially expanded dataset for this task. Our work contains 733 single-athlete-dummy tackle clips, each temporally localized around first point contact and labeled with a strike zone component of the standardized Assessment for Tackling Technique (SATT-3), extending prior work that reported 178 annotated videos. Using a Vision transformer-based model with imbalance-aware training, we obtain risky recall of 0.67 and Risky F1 of 0.59 under crossvalidation. Relative to the previous baseline in a smaller subset (risky recall of 0.58; Risky F1 0.56 ), our approach improves risky recall by more than 8% points on a much larger dataset. These results indicate that the vision transformer-based video analysis, coupled with careful handling of class imbalance, can reliably detect rare but safety-critical tackling patterns, offering a practical pathway toward coach-centered injury prevention tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01318 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos Zaidi, Syed Ahsan Masud Hsu, William Dietrich, Scott Computer Vision and Pattern Recognition Early identification of hazardous actions in contact sports enables timely intervention and improves player safety. We present a method for detecting risky tackles in American football practice videos and introduce a substantially expanded dataset for this task. Our work contains 733 single-athlete-dummy tackle clips, each temporally localized around first point contact and labeled with a strike zone component of the standardized Assessment for Tackling Technique (SATT-3), extending prior work that reported 178 annotated videos. Using a Vision transformer-based model with imbalance-aware training, we obtain risky recall of 0.67 and Risky F1 of 0.59 under crossvalidation. Relative to the previous baseline in a smaller subset (risky recall of 0.58; Risky F1 0.56 ), our approach improves risky recall by more than 8% points on a much larger dataset. These results indicate that the vision transformer-based video analysis, coupled with careful handling of class imbalance, can reliably detect rare but safety-critical tackling patterns, offering a practical pathway toward coach-centered injury prevention tools. |
| title | ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01318 |