List your company

Classification on VB100 (test)

18.2Accuracy (%)CLIP
0.6245.1879.7514.313Nov 26, 2025

Evaluation results

MethodLinks
CLIPModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.1118.2
Tri-CLIPModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.1117.7
ConFuModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.1116.7
ConFuModality=Audio+Visual fusion, Protocol=Zero-shot2025.1116.4
SymileModality=Audio+Visual fusion, Protocol=Zero-shot2025.1113.2
GRAMModality=Vision, Protocol=Zero-shot, Frames=19 uniformly sampled2025.1112.9
TRIANGLEModality=Audio+Visual fusion, Protocol=Zero-shot2025.118.7
GRAMModality=Audio+Visual fusion, Protocol=Zero-shot2025.117.6
CLIPModality=Audio, Protocol=Zero-shot2025.114.2
Tri-CLIPModality=Audio, Protocol=Zero-shot2025.113.9
ConFuModality=Audio, Protocol=Zero-shot2025.113.4
GRAMModality=Audio, Protocol=Zero-shot2025.111.3