Multimodal Classification on AVE (test)
71.28Multi AccPDMP
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PDMPBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 71.28 | — | — | 67.49 | |
| MLABackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 70.92 | — | — | 67.23 | |
| D&RBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 69.62 | — | — | 64.93 | |
| MMParetoBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 68.22 | — | — | 64.54 | |
| Grad-BlendingBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 67.4 | — | — | 63.87 | |
| ConcatenationBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 66.15 | — | — | 62.46 | |
| OGM-GEBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 65.62 | — | — | 62.97 | |
| QMF2026.02 | 65.1 | 55.1 | 37 | — | |
| TCMaxFusion Head=Share Head2026.02 | 64.5 | 54.2 | 36.7 | — | |
| AGMBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 64.5 | — | — | 61.49 | |
| PMRBackbone=ResNet-18, Modality=Multimodal (Audio + Visual), Number of frames=3, Visual input resolution=224x224, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 63.62 | — | — | 60.36 | |
| OGM-GE + OPM2026.02 | 63.3 | 48.2 | 35.3 | — | |
| TCMaxFusion Head=Concat2026.02 | 63.2 | 53.8 | 33.5 | — | |
| OPM2026.02 | 63.1 | 48.8 | 36.2 | — | |
| MMPareto2026.02 | 63.1 | 54 | 41.1 | — | |
| Unimodal Ensemble2026.02 | 62.9 | 54.1 | 36.7 | — | |
| MLA2026.02 | 62.6 | 53.2 | 37.9 | — | |
| Audio-onlyBackbone=ResNet-18, Modality=Audio, Audio input size=257x1004, Batch size=64, Epochs=1002026.04 | 62.16 | — | — | 58.54 | |
| Share Head2026.02 | 61.4 | 49.7 | 22.4 | — | |
| AGM2026.02 | 61.4 | 44.2 | 19.3 | — | |
| OGM-GE2026.02 | 61.3 | 39.5 | 19.3 | — | |
| Concat2026.02 | 60.4 | 48.9 | 17.2 | — | |
| BiGated2026.02 | 59.3 | — | — | — | |
| FiLM2026.02 | 58.8 | — | — | — | |
| Visual-onlyBackbone=ResNet-18, Modality=Visual, Number of frames=3, Visual input resolution=224x224, Batch size=64, Epochs=1002026.04 | 31.4 | — | — | 29.87 |