Audio-Visual Question Answering on MUSIC-AVQA 2.0 (test)
83.82Accuracy (Audio, Count)LAVisH
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LAVisH2025.06 | 83.82 | 58.19 | 75.72 | 82.81 | 81.73 | 82.3 | 73.26 | 73.45 | 65.64 | 64.26 | 60.82 | 67.75 | 73.28 | |
| DG-SCT2025.06 | 83.13 | 62.54 | 76.62 | 81.61 | 82.76 | 82.19 | 83.43 | 72.7 | 64.65 | 64.78 | 67.34 | 70.38 | 74.53 | |
| Sparsify2025.06 | 82.16 | 76.44 | 79.3 | 82.54 | 85.15 | 83.84 | 80.68 | 82.8 | 84.89 | 76.92 | 80.09 | 81.08 | 81.3 | |
| AVST2025.06 | 81.38 | 61.82 | 75.2 | 78.72 | 77.29 | 78.05 | 71.63 | 68.62 | 64.39 | 64.03 | 60.29 | 65.83 | 70.83 |