One Shot 3D Action Recognition On Ntu Rgbd
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Attention Network | 41.0% | Global Context-Aware Attention LSTM Networks for 3D Action Recognition | - |
| Skeleton-DML | 54.2% | Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition | |
| Average Pooling | 42.9% | Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates | - |
| Fully Connected | 42.1% | Global Context-Aware Attention LSTM Networks for 3D Action Recognition | - |
| APSR | 45.3% | NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding | |
| TCN_OneShot | 46.5% | One-shot action recognition in challenging therapy scenarios | |
| MotionBERT (Finetune) | 67.4% | MotionBERT: A Unified Perspective on Learning Human Motion Representations | |
| Deep Metric Learning (Triplet Loss, Signals) | 49.6% | SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition |
0 of 8 row(s) selected.