Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DVSpeaker

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Speech RecognitionDVSpeaker (Cross-scene)
SI (45°)71.68
21
Visual Speech RecognitionDVSpeaker Matched-scene
SI Accuracy (0°)100
21
Showing 2 of 2 rows