Audio-Visual Captioning on AVCaps (test)
57CIDEr
VideoLLaMA 2 + AVEX-Prune
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 57 | 23.7 | 49.7 | |
2026.06 | 56.8 | 23.6 | 49.6 | |
2026.06 | 54.6 | 22.6 | 47.1 | |
2026.06 | 54.5 | 22.8 | 47.1 | |
2026.06 | 52.3 | 21.3 | 48.5 | |
2026.06 | 49.5 | 19.8 | 42.2 | |
2026.06 | 48.5 | 19.5 | 40.2 | |
2026.06 | 37.9 | 16.1 | 35.8 | |
2026.06 | 32 | 13.6 | 30.1 | |
2026.06 | 30.8 | 13.1 | 29 | |
2026.06 | 27.7 | 11.8 | 26.1 |