Text-to-Video Retrieval on Charades CiA-Retrieval
0.718mAP (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 | 0.718 | 0.299 | |
| CLIP (avg.)Method category=Dual encoder models2025.12 | 0.484 | 0.065 |