Landmark Based Lipreading On Lrw
Metrics
Top 1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Top 1 Accuracy |
|---|---|
| another-point-of-view-on-visual-speech | 62.7 |
| adaptive-semantic-spatio-temporal-graph | 60.7 |
| lip-graph-assisted-audio-visual-speech | 49.3 |
| syncvsr-data-efficient-visual-speech | 80.3 |
| syncvsr-data-efficient-visual-speech | 75.1 |