List your company

Video Captioning on MSR-VTT 3 modal

26.8BLEU@1Ours
24.224.87525.5526.225Jan 26, 2026

Evaluation results

MethodLinks
OursModality configuration=3 modal2026.0126.89.664.4
CLIP (LT)Evaluation protocol=Locked-Tuning (LT), Modality configuration=3 modal2026.0126.79.563.6
CLIP (FT)Evaluation protocol=Fine-Tuning (FT), Modality configuration=3 modal2026.0126.29.463.2
NotAGapModality configuration=3 modal2026.0124.38.753.8