Human Interaction Recognition On Ntu Rgb D 1
Metrics
Accuracy (Cross-Setup)
Accuracy (Cross-Subject)
Results
Performance results of various models on this benchmark
Model Name | Accuracy (Cross-Setup) | Accuracy (Cross-Subject) | Paper Title | Repository |
|---|---|---|---|---|
| ISTA-Net | 91.7 | 90.5 | Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition | |
| LSTM-IRN | 79.6 | 77.7 | Interaction Relational Network for Mutual Action Recognition | |
| SkeleTR | 88.3 | 87.8 | SkeleTR: Towards Skeleton-based Action Recognition in the Wild | - |
| CHASE(CTR-GCN) | 92.3 | 91.3 | CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition | |
| SkateFormer | 93.2 | 92.3 | SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition | |
| IGFormer | 86.5 | 85.4 | IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition | - |
0 of 6 row(s) selected.