List your company

Classification on VB100

20.7AccuracyTri-CLIP
0.5245.7621116.238Nov 26, 2025

Evaluation results

MethodLinks
Tri-CLIPInput Modality=Vision, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1120.7
CLIPInput Modality=Vision, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1120.6
ConFuInput Modality=Vision, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1119.3
ConFuInput Modality=Audio-Visual (A+V), Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1118.1
GRAMInput Modality=Vision, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1113.7
SymileInput Modality=Audio-Visual (A+V), Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1113.4
TRIANGLEInput Modality=Audio-Visual (A+V), Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.1112.1
GRAMInput Modality=Audio-Visual (A+V), Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.118
CLIPInput Modality=Audio, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.114.2
Tri-CLIPInput Modality=Audio, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.113.9
ConFuInput Modality=Audio, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.113.4
GRAMInput Modality=Audio, Evaluation Setting=Zero-shot, Evaluation Protocol=Multi-frame2025.111.3