Video-to-Text Retrieval on Charades CiA-Retrieval (test)
68.3R@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 | 68.3 | 18.8 | |
| CLIP (avg.)Method category=Dual encoder models2025.12 | 51.5 | 5.5 |