Emotion Classification on VSO
66.81AccuracyCLIP
Evaluation results
| Method | Links | |
|---|---|---|
| CLIPTraining Dataset=Selecta, Architecture=CLIP+MLP2025.12 | 66.81 | |
| CLIPTraining Dataset=EmoSet, Architecture=CLIP+MLP2025.12 | 65.75 | |
| SwinBTraining Dataset=Selecta, Architecture=Swin-B2025.12 | 65.74 | |
| ResNet-101Training Dataset=Selecta, Architecture=ResNet-1012025.12 | 63.92 | |
| SwinBTraining Dataset=EmoSet, Architecture=Swin-B2025.12 | 58.91 | |
| ResNet-101Training Dataset=EmoSet, Architecture=ResNet-1012025.12 | 55.82 |