Image Captioning on MSCOCO 2 modal
46.1BLEU-1Ours
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OursModality configuration=2 modal2026.01 | 46.1 | 23.2 | 160.9 | |
| CLIP (FT)Evaluation protocol=Fine-Tuning (FT), Modality configuration=2 modal2026.01 | 45.9 | 23 | 155 | |
| CLIP (LT)Evaluation protocol=Locked-Tuning (LT), Modality configuration=2 modal2026.01 | 45.8 | 22.5 | 153.2 | |
| NotAGapModality configuration=2 modal2026.01 | 45.4 | 22.2 | 153.3 |