Skeleton Based Action Recognition On Uwa3D
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| ESV (Synthesized + Pre-trained) | 73.8% | Enhanced skeleton visualization for view invariant human action recognition | - |
| VA-fusion (aug.) | 81.4% | View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition | |
| HOJ3D | 17.7% | View invariant human action recognition using histograms of 3D joints | - |
0 of 3 row(s) selected.