Classification on SSW60 (test)
65.5AccuracyConFu
Evaluation Results
| Method | Links | |
|---|---|---|
| ConFuModality=Audio+Visual fusion, Protocol=Zero-shot2025.11 | 65.5 | |
| SymileModality=Audio+Visual fusion, Protocol=Zero-shot2025.11 | 61.4 | |
| CLIPModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.11 | 60.3 | |
| ConFuModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.11 | 59.8 | |
| Tri-CLIPModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.11 | 59.7 | |
| GRAMModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.11 | 59 | |
| TRIANGLEModality=Audio+Visual fusion, Protocol=Zero-shot2025.11 | 58.6 | |
| GRAMModality=Audio+Visual fusion, Protocol=Zero-shot2025.11 | 54.9 | |
| Tri-CLIPModality=Audio, Protocol=Zero-shot2025.11 | 31.1 | |
| ConFuModality=Audio, Protocol=Zero-shot2025.11 | 30.3 | |
| CLIPModality=Audio, Protocol=Zero-shot2025.11 | 29.9 | |
| GRAMModality=Audio, Protocol=Zero-shot2025.11 | 0.7 |