List your company

Audio-Visual Captioning on Audioset

16.23CsVanilla
6.18368.791811.414.0082May 11, 2026

Evaluation results

MethodLinks
VanillaModel=Qwen2.5-Omni(3B)2026.0516.2315.7970.8—
ASDModel=Qwen2.5-Omni(3B)2026.0515.515.3470.28—
VCDModel=Qwen2.5-Omni(7B)2026.0512.2814.8871.1236.98
PAIModel=Qwen2.5-Omni(7B)2026.0511.8413.0973.2236.94
VanillaModel=video-SALMONN-o1 (7B)2026.0511.3914.9167.2736.81
PAIModel=video-SALMONN-o1 (7B)2026.0510.9514.5467.6436.05
VCDModel=video-SALMONN-o1 (7B)2026.059.3412.5267.7432.5
VanillaModel=Qwen2.5-Omni(7B)2026.058.9210.9369.7338.24
ASDModel=Qwen2.5-Omni(7B)2026.058.5410.272.9838.32
ASDModel=video-SALMONN-o1 (7B)2026.056.579.567.2939.64