Video Question Answering on MUSIC-AVQA
80.7AccuracyVAST(1.3B)
Evaluation Results
| Method | Links | |
|---|---|---|
| VAST(1.3B)Sample=442M, extra_modalities=audio or subtitle2023.05 | 80.7 | |
| VALOR-LSample=433.5M, extra_modalities=audio or subtitle2023.05 | 78.9 |
Loading the SOTA2 catalog…