Skeleton Based Action Recognition On H2O 2
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| ISTA-Net | 89.09±1.21 | Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition | - |
| CHASE(STSA-Net) | 94.77 | CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition | - |
| EffHandEgoNet | 91.32 | In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition | - |
| SHARP | 91.73 | SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition | - |
0 of 4 row(s) selected.