A computer vision tool that analyzes deadlift form from side-on video clips using multiple AI models. It counts reps, measures bar height, tracks hip hinge angle, and evaluates back position (straight vs. rounded) with live probability scores overlaid on the video.
Hiera-Hand is a hand-action recognition AI algorithm that tracks people in videos, localizes their hands, and classifies each hand's action as grasp, hold, operate, or release. The standalone demo uses YOLO pose detection and a fine-tuned Hiera-Base model to process video frames at 224×224 resolution with temporal context windows.