Natural Language Transduction on CAS-VSR-W1k (LRW-1000)

Metric: Top-1 Accuracy (higher is better)

LeaderboardDataset
Loading chart...
#ModelTop-1 AccuracyExtra DataPaperDateCode
1SyncVSR (Word Boundary)58.2NoSyncVSR: Data-Efficient Visual Speech Recognitio...2024-06-18Code
23D Conv + ResNet-18 + MS-TCN + Multi-Head Visual-Audio Memory53.8NoDistinguishing Homophenes Using Multi-Head Visua...2022-04-04Code