Audio-Visual Captioning on f-Music (test)
40.49BLEUSSUFormer
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SSUFormertraining_mode=multi-task2026.03 | 40.49 | 48.82 | 40.02 | |
| SSU-Dtraining_mode=Description Only2026.03 | 35.58 | 44.97 | 33.8 | |
| PG-Video-LLaVA2026.03 | 27.01 | 31.34 | 21.47 | |
| AVC2026.03 | 25.46 | 36.5 | 26.68 |