Audio-Visual Captioning on VGGSound Animal
51.52Cs ScoreVCD
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| VCDModel=Qwen2.5-Omni(7B)2026.05 | 51.52 | 41.28 | 52.43 | 40.27 | |
| AVCDBase Model=Qwen2.5-Omni(7B)2026.05 | 51.5 | 38.8 | 53.7 | 38.5 | |
| VanillaModel=Qwen2.5-Omni(3B)2026.05 | 51.24 | 41 | 52.88 | — | |
| PAIModel=Qwen2.5-Omni(7B)2026.05 | 51.24 | 38.11 | 55.11 | 39.52 | |
| FMDBase Model=Qwen2.5-Omni(7B)2026.05 | 50.9 | 40.2 | 52.9 | 37.3 | |
| VanillaModel=Qwen2.5-Omni(7B)2026.05 | 48.21 | 37.13 | 55.24 | 40.71 | |
| VanillaBase Model=Qwen2.5-Omni(7B)2026.05 | 48.2 | 37.1 | 55.2 | 40.7 | |
| ASDModel=Qwen2.5-Omni(3B)2026.05 | 43.25 | 38.52 | 50.44 | — | |
| VCDModel=video-SALMONN-o1 (7B)2026.05 | 39.39 | 33.4 | 53.37 | 36.4 | |
| VanillaModel=video-SALMONN-o1 (7B)2026.05 | 37.74 | 32.09 | 53.68 | 36.21 | |
| ASDModel=Qwen2.5-Omni(7B)2026.05 | 36.91 | 34.15 | 52.44 | 42.77 | |
| ASDBase Model=Qwen2.5-Omni(7B)2026.05 | 36.9 | 34.1 | 52.4 | 42.7 | |
| PAIModel=video-SALMONN-o1 (7B)2026.05 | 35.26 | 31.18 | 53.16 | 36.99 | |
| ASDModel=video-SALMONN-o1 (7B)2026.05 | 25.07 | 25.71 | 50.89 | 43.29 |