Audio-Visual Classification on CREMA-D (test)
79.7AccuracyMLA
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MLAModality=Multi2023.11 | 79.7 | — | — | — | |
| MLAModality=Multi2023.11 | 79.7 | — | — | — | |
| OGM-GEModality=Multi2023.11 | 68.14 | — | — | — | |
| OGM-GEModality=Multi2023.11 | 68.14 | — | — | — | |
| Late FusionModality=Multi2023.11 | 66.32 | — | — | — | |
| Late FusionModality=Multi2023.11 | 66.32 | — | — | — | |
| MLAModality=Video2023.11 | 64.91 | — | — | — | |
| MLAModality=Video2023.11 | 64.91 | — | — | — | |
| QMFModality=Multi2023.11 | 63.71 | — | — | — | |
| QMFModality=Multi2023.11 | 63.71 | — | — | — | |
| PMRFusion strategy=Film2022.11 | 61.8 | — | — | — | |
| ConcatModality=Multi2023.11 | 61.56 | — | — | — | |
| ConcatModality=Multi2023.11 | 61.56 | — | — | — | |
| PMR w/o PERFusion strategy=Film2022.11 | 61.3 | — | — | — | |
| PMRFusion strategy=Concat2022.11 | 61.1 | — | — | — | |
| SumModality=Multi2023.11 | 60.32 | — | — | — | |
| SumModality=Multi2023.11 | 60.32 | — | — | — | |
| PMR w/o PERFusion strategy=Concat2022.11 | 60.3 | — | — | — | |
| FiLMModality=Multi2023.11 | 60.07 | — | — | — | |
| FiLMModality=Multi2023.11 | 60.07 | — | — | — | |
| QMFModality=Audio2023.11 | 59.41 | — | — | — | |
| QMFModality=Audio2023.11 | 59.41 | — | — | — | |
| MLAModality=Audio2023.11 | 59.27 | — | — | — | |
| MLAModality=Audio2023.11 | 59.27 | — | — | — | |
| BiGatedModality=Multi2023.11 | 59.21 | — | — | — | |
| BiGatedModality=Multi2023.11 | 59.21 | — | — | — | |
| Grad-BlendingFusion strategy=Film2022.11 | 58.7 | — | — | — | |
| Modality-dropFusion strategy=Film2022.11 | 58.3 | — | — | — | |
| OGM-GEFusion strategy=Film2022.11 | 58 | — | — | — | |
| VGMRBackbone=Concatenation2026.06 | 57.8 | — | — | 57.82 | |
| OGM-GEFusion strategy=Concat2022.11 | 57.7 | — | — | — | |
| ARLBackbone=Concatenation2026.06 | 57.53 | — | — | 57.94 | |
| NaiveFusion strategy=Film2022.11 | 57.2 | — | — | — | |
| Grad-BlendingFusion strategy=Concat2022.11 | 56.7 | — | — | — | |
| Modality-dropFusion strategy=Concat2022.11 | 55.8 | — | — | — | |
| ConcatModality=Audio2023.11 | 55.65 | — | — | — | |
| ConcatModality=Audio2023.11 | 55.65 | — | — | — | |
| Late FusionModality=Video2023.11 | 55.48 | — | — | — | |
| Late FusionModality=Video2023.11 | 55.48 | — | — | — | |
| SumModality=Audio2023.11 | 54.14 | — | — | — | |
| SumModality=Audio2023.11 | 54.14 | — | — | — | |
| FiLMModality=Audio2023.11 | 53.89 | — | — | — | |
| FiLMModality=Audio2023.11 | 53.89 | — | — | — | |
| OGM-GEModality=Audio2023.11 | 53.76 | — | — | — | |
| OGM-GEModality=Audio2023.11 | 53.76 | — | — | — | |
| NaiveFusion strategy=Concat2022.11 | 53.2 | — | — | — | |
| Late FusionModality=Audio2023.11 | 52.17 | — | — | — | |
| Late FusionModality=Audio2023.11 | 52.17 | — | — | — | |
| Grad-BlendingBackbone=Concatenation2026.06 | 51.75 | — | — | 51.65 | |
| PMRBackbone=Concatenation2026.06 | 51.75 | — | — | 51.55 | |
| BiGatedModality=Audio2023.11 | 51.49 | — | — | — | |
| BiGatedModality=Audio2023.11 | 51.49 | — | — | — | |
| OGM-GEBackbone=Concatenation2026.06 | 51.48 | — | — | 50.96 | |
| MLABackbone=Concatenation2026.06 | 51.08 | — | — | 50.81 | |
| BaselineBackbone=Concatenation2026.06 | 50.54 | — | — | 50.3 | |
| MMParetoBackbone=Concatenation2026.06 | 49.73 | — | — | 49.63 | |
| AGMBackbone=Concatenation2026.06 | 49.6 | — | — | 49.34 | |
| D&RBackbone=Concatenation2026.06 | 48.52 | — | — | 46.78 | |
| QMFModality=Video2023.11 | 39.11 | — | — | — | |
| QMFModality=Video2023.11 | 39.11 | — | — | — | |
| OGM-GEModality=Video2023.11 | 28.09 | — | — | — | |
| OGM-GEModality=Video2023.11 | 28.09 | — | — | — | |
| ConcatModality=Video2023.11 | 18.68 | — | — | — | |
| ConcatModality=Video2023.11 | 18.68 | — | — | — | |
| FiLMModality=Video2023.11 | 18.67 | — | — | — | |
| FiLMModality=Video2023.11 | 18.67 | — | — | — | |
| SumModality=Video2023.11 | 18.45 | — | — | — | |
| SumModality=Video2023.11 | 18.45 | — | — | — | |
| BiGatedModality=Video2023.11 | 17.34 | — | — | — | |
| BiGatedModality=Video2023.11 | 17.34 | — | — | — |