Landmark Based Lipreading On Lrw
Metrics
Top 1 Accuracy
Results
Performance results of various models on this benchmark
Model Name | Top 1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| Another Point of View | 62.7 | Another Point of View on Visual Speech Recognition | - |
| Adaptive GCN | 60.7 | Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading | - |
| Lip Graph Assisted | 49.3 | Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion | - |
| SyncVSR (Word Boundary) | 80.3 | SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization | |
| SyncVSR | 75.1 | SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization |
0 of 5 row(s) selected.