3D Conv + EfficientNetV2 + Transformer + TCN

Reported on 2 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

LipreadingonLip Reading in the Wild
Top-1 Accuracy
89.52
best: 95 (SyncVSR (Word Boundary))

Natural Language Processing1 result

Natural Language TransductiononLip Reading in the Wild
Top-1 Accuracy
89.52
best: 95 (SyncVSR (Word Boundary))