List your company

Audio-Visual Captioning on VGGSound All

40.52CsVanilla
37.119238.002138.88539.7679May 11, 2026

Evaluation results

MethodLinks
VanillaModel=Qwen2.5-Omni(3B)2026.0540.5227.1557.86
ASDModel=Qwen2.5-Omni(3B)2026.0537.2526.0157.59