Isolated Sign Language Recognition on NMFS-CSL Normal (test)
98.7Top-1 AccStepNet (R + F)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| StepNet (R + F)Modality=Fusion-based, Input Details=RGB data (R) + Optical flow data (F)2022.12 | 98.7 | 99.9 | 100 | |
| BEST (H + R)Modality=Fusion-based, Input Details=H + RGB-based features (R)2022.12 | 97.5 | — | 99.9 | |
| Signbert (H + R)Modality=Fusion-based, Input Details=H + RGB-based features (R)2022.12 | 97.4 | 99.3 | 99.9 | |
| StepNetModality=RGB-based2022.12 | 96.9 | 99.7 | 99.9 | |
| Signbert (H + P)Modality=Fusion-based, Input Details=H + Skeleton-based features (P)2022.12 | 96.7 | 99.3 | 99.9 | |
| BESTModality=Skeleton-based2022.12 | 94.6 | — | 99.7 | |
| Signbert (H)Modality=Skeleton-based, Input Details=Reconstructed hand representation (H) by MANO2022.12 | 94.5 | 98.1 | 99.6 | |
| GLE-NetModality=RGB-based2022.12 | 93.6 | 97.6 | 99.3 | |
| TSMModality=RGB-based2022.12 | 93.3 | 97.5 | 99 | |
| SlowfastModality=RGB-based2022.12 | 92 | 96.7 | 98.9 | |
| 3D-R50Modality=RGB-based2022.12 | 87.4 | 93.4 | 97 | |
| I3DModality=RGB-based2022.12 | 87.1 | 94.3 | 97.3 | |
| DNFModality=RGB-based2022.12 | 86.3 | 93.1 | 97 | |
| ST-GCNModality=Skeleton-based2022.12 | 83.4 | 91.3 | 96.7 |