Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VGG-SS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Sound Source LocalizationVGG-SS (test)
LocAcc39.8
19
Audio-visual localizationVGG-SS Open set (Unheard 110)
AP39.24
14
Audio-visual localizationVGG-SS Open set (Heard 110)
AP40.84
14
Visual Sound Source LocalizationVGG-SS extended (test)
Localization Accuracy39.8
11
Audio referred image groundingVGG-SS (test)
cIoU48.51
10
Showing 5 of 5 rows