3D Action Recognition On Assembly101
Métriques
Actions Top-1
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Actions Top-1 | Paper Title | Repository |
|---|---|---|---|
| CHASE(CTR-GCN) | 28.03 | CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition | - |
| RGBPoseConv3D | 33.61 | Revisiting Skeleton-based Action Recognition | - |
| ISTA-Net | 28.07 | Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition | - |
| MS-G3D | 28.7 | Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition | - |
| TSM | 35.27 | TSM: Temporal Shift Module for Efficient Video Understanding | - |
| HandFormer-B/21 | 41.06 | On the Utility of 3D Hand Poses for Action Recognition | - |
| 2s-AGCN | 26.7 | Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition | - |
0 of 7 row(s) selected.