Sign Language Recognition on AUTSL (test)
98.6Rank-1 AccuracyAudio-visual multi-modal approach
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Audio-visual multi-modal approach2025.05 | 98.6 | — | |
| SAM-SLR2023.02 | 98.53 | 99.73 | |
| SAM-SLR2025.05 | 98.5 | — | |
| Multi-dataset co-trainingco-training dataset=Logos2025.05 | 97.81 | — | |
| Multi-dataset co-trainingco-training dataset=MM-WLAuslan2025.05 | 97.43 | — | |
| ST-GCN2025.05 | 96.7 | — | |
| MViTv2mode=baseline2025.05 | 96.58 | — | |
| SL-GDN2025.05 | 96.5 | — | |
| One Model is Not Enough2025.05 | 96.4 | — | |
| HWGAT2025.05 | 95.8 | — | |
| MVIT-RSLvariant=small2023.02 | 95.72 | 99.41 | |
| Swin-RSLvariant=tiny2023.02 | 95.38 | 99.65 | |
| VTN-PF2023.02 | 92.92 | — | |
| CNN+FPM+BLSTM+AttentionInput Modality=RGB-D2023.02 | 62.03 | — |