Skeleton Based Action Recognition On Sbu
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| MLGCN | 98.60% | MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition | - |
| ArmaConv | 96.00% | Graph Neural Networks with convolutional ARMA filters | - |
| VA-fusion (aug.) | 98.3% | View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition | - |
| e2eET | 93.96 | Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN | - |
| Joint Line Distance | 99.02% | On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks | |
| DeepGRU | 95.7% | DeepGRU: Deep Gesture Recognition Utility | - |
| ChebyNet | 96.00% | Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering | - |
| ST-LSTM + Trust Gate | 93.3% | Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition | - |
| SGCConv | 94.0% | Simplifying Graph Convolutional Networks | - |
0 of 9 row(s) selected.