List your company

Audio-Visual Captioning on Audioset (ALOHa)

63.7ALOHa ScoreFMD
37.1844.06550.9557.835May 11, 2026

Evaluation results

MethodLinks
FMDBase Model=Qwen2.5-Omni(7B)2026.0563.713.613.571.2
AVCDBase Model=Qwen2.5-Omni(7B)2026.0559.310.812.169.2
VanillaBase Model=Qwen2.5-Omni(7B)2026.0538.28.910.969.7
ASDBase Model=Qwen2.5-Omni(7B)2026.0538.28.510.272.9