Video Captioning on MSR-VTT 3 modal
26.8BLEU@1Ours
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OursModality configuration=3 modal2026.01 | 26.8 | 9.6 | 64.4 | |
| CLIP (LT)Evaluation protocol=Locked-Tuning (LT), Modality configuration=3 modal2026.01 | 26.7 | 9.5 | 63.6 | |
| CLIP (FT)Evaluation protocol=Fine-Tuning (FT), Modality configuration=3 modal2026.01 | 26.2 | 9.4 | 63.2 | |
| NotAGapModality configuration=3 modal2026.01 | 24.3 | 8.7 | 53.8 |