Audio-Visual Event Classification on VGGSound (test)
69.1Fusion Top-1 AccMIMO
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MIMOt(s)=0.019±0.0042025.11 | 69.1 | 41.47 | 38.2 | — | |
| MMParetot(s)=0.389±0.0532025.11 | 66.07 | 48.07 | 28.87 | — | |
| UAVMmodality-missing results=false2022.07 | 65.8 | — | — | — | |
| Modal-Independent Modeltrained independently=false2022.07 | 65.7 | — | — | — | |
| MBTtrained independently=false2022.07 | 64.1 | — | — | — | |
| EWt(s)=0.006±0.0012025.11 | 63.9 | 48.77 | 25.2 | — | |
| Cross-Modal Attention Model2022.07 | 62.9 | — | — | — | |
| OGM-GEt(s)=0.121±0.0072025.11 | 62.13 | 32.5 | 22 | — | |
| MSLt(s)=0.011±0.0012025.11 | 60.8 | 42.83 | 15.43 | — | |
| TCMaxFusion Head=Concat2026.02 | 47.6 | 33.9 | 22 | — | |
| TCMaxFusion Head=Share Head2026.02 | 47.5 | 36.3 | 24.3 | — | |
| Unimodal Ensemble2026.02 | 46.3 | 34.8 | 26.7 | — | |
| MMPareto2026.02 | 46.2 | 35.5 | 27.5 | — | |
| OPM2026.02 | 45.9 | 31.2 | 23.5 | — | |
| QMF2026.02 | 45.8 | 34.6 | 26.1 | — | |
| OGM-GE + OPM2026.02 | 45.5 | 31.6 | 23.5 | — | |
| AGM2026.02 | 44.7 | 30.5 | 14.7 | — | |
| MLA2026.02 | 44.5 | 35.3 | 25.8 | — | |
| OGM-GE2026.02 | 42.5 | 28.7 | 13.2 | — | |
| Share Head2026.02 | 41.8 | 30.9 | 13 | — | |
| Concat2026.02 | 41.1 | 29.5 | 10.3 | — | |
| FiLM2026.02 | 38.3 | — | — | — | |
| BiGated2026.02 | 38.3 | — | — | — | |
| AudioSlowFast2022.07 | — | 50.1 | — | — | |
| Chen et al.2022.07 | — | 48.8 | — | — | |
| MAVILInput Modalities=Audio + Video2023.11 | — | — | — | 67.1 | |
| MBTtrained independently=true2022.07 | — | 52.3 | 51.2 | — | |
| Mirasol3BInput Modalities=Audio + Video2023.11 | — | — | — | 69.8 | |
| Mirasol3B TTMInput Modalities=Audio + Video, Module Configuration=TTM2023.11 | — | — | — | 66.4 | |
| MMTInput Modalities=Audio + Video2023.11 | — | — | — | 66.2 | |
| Modal-Independent Modeltrained independently=true2022.07 | — | 56.5 | 49.7 | — | |
| ONE-PEACEInput Modalities=Audio + Video2023.11 | — | — | — | 68.2 | |
| UAVMmodality-missing results=true2022.07 | — | 56.5 | 49.9 | — | |
| UAVMInput Modalities=Audio + Video2023.11 | — | — | — | 65.8 |