Lipreading On Lrw 1000
Métriques
Top-1 Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Top-1 Accuracy |
|---|---|
| multi-modality-associative-bridging-through-1 | 50.82% |
| deformation-flow-based-two-stream-network-for | 41.93% |
| syncvsr-data-efficient-visual-speech | 58.2 |
| pseudo-convolutional-policy-gradient-for | 38.7% |
| mutual-information-maximization-for-effective | 38.79% |
| learn-an-effective-lip-reading-model-without | 55.7% |
| distinguishing-homophenes-using-multi-head-1 | 53.8 |
| can-we-read-speech-beyond-the-lips-rethinking | 45.24% |
| learn-an-effective-lip-reading-model-without | 48.3% |