Action Recognition On Penn Action
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| STAR-Transformer (RGB + Pose) | 98.7 | STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition | - |
| 3DA (RGB + Pose) | 99.7 | Cross-Modal Learning with 3D Deformable Attention for Action Recognition | - |
0 of 2 row(s) selected.