Revisiting Risky Tackle Detection with Vision Transformers

2026-09-28

AI Summary

This study addresses the unverified reproducibility of existing research on dangerous tackle detection in American football. We conduct a systematic reproduction based on the ViViT model, employing focal loss and cross-validation to mitigate class imbalance. Furthermore, we introduce the Taguchi method for orthogonal optimization of data augmentation strategies, revealing brightness enhancement as a critical factor and establishing an optimal configuration without rotation or flipping. The reproduction results align closely with those of the original paper, achieving a recall of 0.667 and an F1-score of 0.588 for dangerous actions. This work validates the reliability of the original methodology and provides transferable empirical evidence for designing data augmentation strategies in video-based action recognition tasks.

Abstract

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.

Problem

• risky tackle detection
• American football
• reproducibility
• video analysis

Innovation

• Vision Transformer
• Reproducibility
• Data Augmentation
• Ablation Study
• Risky Tackle Detection