Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51.
computer-vision deep-learning pytorch convolutional-neural-networks transfer-learning pose-estimation video-classification video-recognition human-action-recognition hmdb51 video-analysis ucf-101 r2plus1d mobilenetv3 mediapipe pose-classification video-classification-models timm real-time-inference r3d-18
-
Updated
Jan 19, 2026 - Python