Skeleton Based Action Recognition On Jhmdb 2D
Métriques
Average accuracy of 3 splits
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Average accuracy of 3 splits | Paper Title | Repository |
|---|---|---|---|
| EHPI | 65.5 | Simple yet efficient real-time pose-based action recognition | - |
| Chained | 56.8 | Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection | - |
| DD-Net | 77.2 | Make Skeleton-based Action Recognition Model Smaller, Faster and Better | - |
| JMRN (No GT pose) | 68.55 | Pose And Joint-Aware Action Recognition | - |
| HT-ConvNet | 86.1 | Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition | |
| PoTion | 67.9 | PoTion: Pose MoTion Representation for Action Recognition | - |
0 of 6 row(s) selected.