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