Video Action Recognition on EPIC-KITCHENS-100
63.3Top-1 AccSMILE
Evaluation Results
| Method | Links | |
|---|---|---|
| SMILEEvaluation Protocol=Finetuning, Intermediate Dataset=K400 [35]2025.04 | 63.3 | |
| ILAEvaluation Protocol=Finetuning, Intermediate Dataset=None2025.04 | 60.8 | |
| AIMEvaluation Protocol=Finetuning, Intermediate Dataset=None2025.04 | 58.4 | |
| ViCLIPEvaluation Protocol=Finetuning, Intermediate Dataset=Intervid-10M [84]2025.04 | 55 | |
| X-CLIPEvaluation Protocol=Finetuning, Intermediate Dataset=None2025.04 | 52.7 | |
| CLIPEvaluation Protocol=Finetuning, Intermediate Dataset=None2025.04 | 50.3 | |
| UMTEvaluation Protocol=Finetuning, Intermediate Dataset=K700 [8]2025.04 | 50.1 | |
| ViFi-CLIPEvaluation Protocol=Finetuning, Intermediate Dataset=None2025.04 | 48.9 | |
| SMILEEvaluation Protocol=Linear Probing, Intermediate Dataset=K400 [35]2025.04 | 34.6 | |
| UMTEvaluation Protocol=Linear Probing, Intermediate Dataset=K700 [8]2025.04 | 28.2 | |
| ViCLIPEvaluation Protocol=Linear Probing, Intermediate Dataset=Intervid-10M [84]2025.04 | 27.3 | |
| CLIPEvaluation Protocol=Linear Probing, Intermediate Dataset=None2025.04 | 25.1 |