Upload fight footage. The pipeline runs YOLOv11m detection, YOLOv8m-pose estimation, and AttentionBiLSTM classification across 6 punch types — fully automated.
AttentionBiLSTM · 6 classes
Real-time pipeline log
Per-fighter event stream
Scorecards record outcomes.
We record the mechanics.

Fine-tuned on boxing footage, the detector tracks exactly two fighters using Hungarian-algorithm assignment with a 50,000-point inertia bonus that prevents identity switching mid-match.

17 anatomical landmarks per fighter, per frame. Skeleton integrity validation requires ≥10 visible keypoints before the sequence is passed to the classifier.

A bidirectional LSTM with temporal self-attention processes 30-frame keypoint sequences (51 dimensions per frame) to classify 6 punch types with real-time confidence scoring.
Upload a boxing video and receive a full biomechanical breakdown — punch counts, classifications, and annotated output.
Start analysis