Video Recognition on EPIC
63.3AccuracySMILE
Evaluation Results
| Method | Links | |
|---|---|---|
| SMILEProtocol=Finetuning, Pretraining Video Dataset=K4002025.04 | 63.3 | |
| ViCLIPProtocol=Finetuning, Pretraining Video Dataset=Intervid-10M2025.04 | 55 | |
| CLIPProtocol=Finetuning, Pretraining Video Dataset=N/A2025.04 | 50.3 | |
| UMTProtocol=Finetuning, Pretraining Video Dataset=K7002025.04 | 50.1 | |
| SMILEProtocol=Linear Probing, Pretraining Video Dataset=K4002025.04 | 34.6 | |
| UMTProtocol=Linear Probing, Pretraining Video Dataset=K7002025.04 | 28.2 | |
| ViCLIPProtocol=Linear Probing, Pretraining Video Dataset=Intervid-10M2025.04 | 27.3 | |
| CLIPProtocol=Linear Probing, Pretraining Video Dataset=N/A2025.04 | 25.1 |