Word-level Sign Language Recognition on WLASL 300
73.2Top-1 AccSignBERT+
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SignBERT+2025.09 | 73.2 | 90.42 | — | |
| SSL-SLR2025.09 | 71.21 | 90.74 | — | |
| Two-stream multistage graph convolutional modelComputing Platform=A two-stream multistage graph convolutional model with attention and residual connections designed to extract spatiotemporal contextual information.2026.01 | 69 | — | — | |
| BEST2025.09 | 67.66 | 89.22 | — | |
| Pose-based temporal graph convolution networksComputing Platform=Pose-based temporal graph convolution networks and comparison with an inflated 3D convolutional network.2026.01 | 64 | — | — | |
| SignBERT2025.09 | 62.72 | 85.18 | — | |
| I3D2019.10 | 56.14 | 79.94 | 86.98 | |
| PSLR2025.09 | 42.18 | 71.71 | — | |
| Pose-TGCN2019.10 | 38.32 | 67.51 | 79.64 | |
| Pose-GRU2019.10 | 33.68 | 64.37 | 76.05 | |
| VGG-GRU2019.10 | 19.31 | 46.56 | 61.08 |