Video-to-Text Retrieval on EPIC-KITCHENS CiA-Retrieval
76.8R@1 (Chiral)TARA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TARAMethod category=MLLMs with fine-tuning, Training dataset size (M)=0.01, Video used during retrieval adaptation=false2025.12 | 76.8 | 19.7 | |
| CLIP (avg.)Method category=Dual encoder models2025.12 | 54.1 | 5 |