Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

AlphaPose + ST-GCN + SORT.

The combination of face identification and action recognition for fall detection (ICT Journal)

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

Implementation of ST-GCN for continuous inference and a novel lightweight realtime RT-ST-GCN