Skeleton Based Action Recognition On Sysu 3D
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Dynamic Skeletons | 75.5% | Jointly learning heterogeneous features for rgb-d activity recognition | - |
| EleAtt-GRU (aug.) | 85.7% | EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks | - |
| Local+LGN | 83.14% | Learning Latent Global Network for Skeleton-based Action Prediction | - |
| VA-LSTM | 77.5% | View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data | - |
| VA-fusion (aug.) | 86.7% | View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition | - |
| DPRL | 76.9% | Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition | - |
| ST-LSTM (Tree) | 73.4% | Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates | - |
| Complete GR-GCN | 77.9% | Optimized Skeleton-based Action Recognition via Sparsified Graph Regression | - |
| SGN | 86.9% | Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition | - |
0 of 9 row(s) selected.