Text-to-Video Retrieval on LSMDC (test) using Linguistic Metrics
11.31OCR ScoreHAT-VTR
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HAT-VTRBase Model=Xpool, Adaptation Strategy=HAT-VTR2026.02 | 11.31 | 3.8 | 4.7 | 5.31 | 4.2 | 15.42 | 16.32 | 15.72 | 16.62 | 16.92 | 15.62 | 16.32 | 16.72 | 15.42 | 17.42 | 12.79 | |
| EATABase Model=Xpool, Adaptation Strategy=EATA2026.02 | 11.01 | 3.5 | 4.2 | 5.91 | 4.3 | 14.41 | 16.42 | 15.52 | 16.52 | 17.12 | 14.31 | 16.62 | 16.12 | 16.52 | 16.32 | 12.59 | |
| XpoolBase Model=Xpool, Adaptation Strategy=None2026.02 | 10.81 | 4.1 | 4.1 | 5.81 | 4.3 | 14.81 | 16.22 | 15.52 | 16.52 | 16.02 | 15.02 | 16.52 | 16.02 | 16.72 | 16.72 | 12.61 | |
| TCRBase Model=Xpool, Adaptation Strategy=TCR2026.02 | 10.81 | 4.2 | 4.3 | 5.71 | 3.9 | 14.41 | 16.52 | 15.12 | 16.52 | 16.32 | 14.51 | 16.32 | 15.82 | 16.62 | 16.62 | 12.51 | |
| TentBase Model=Xpool, Adaptation Strategy=Tent2026.02 | 10.71 | 3.9 | 4.2 | 5.81 | 4.1 | 14.71 | 16.02 | 15.42 | 16.72 | 16.42 | 14.71 | 16.52 | 16.12 | 15.52 | 16.72 | 12.51 | |
| SARBase Model=Xpool, Adaptation Strategy=SAR2026.02 | 10.71 | 4.1 | 4.2 | 5.91 | 4.2 | 14.81 | 16.02 | 15.42 | 16.72 | 16.42 | 14.71 | 16.52 | 16.12 | 16.52 | 16.62 | 12.6 | |
| READBase Model=Xpool, Adaptation Strategy=READ2026.02 | 10.51 | 4.4 | 4 | 5.71 | 4.1 | 15.02 | 16.22 | 15.42 | 16.42 | 16.12 | 14.81 | 16.22 | 16.12 | 16.52 | 16.72 | 12.55 | |
| HAT-VTRBase Model=CLIP4Clip, Adaptation Strategy=HAT-VTR2026.02 | 10.11 | 3.2 | 3.7 | 5.21 | 3.8 | 15.22 | 16.12 | 15.52 | 15.42 | 15.72 | 14.31 | 16.22 | 15.62 | 16.02 | 16.42 | 12.17 | |
| CLIP4ClipBase Model=CLIP4Clip, Adaptation Strategy=None2026.02 | 9.71 | 3.7 | 4 | 5.41 | 4 | 13.71 | 14.51 | 14.71 | 15.02 | 14.51 | 12.71 | 14.91 | 14.51 | 15.12 | 15.32 | 11.46 | |
| TCRBase Model=CLIP4Clip, Adaptation Strategy=TCR2026.02 | 9.71 | 3 | 4.1 | 5.31 | 4.2 | 14.01 | 14.71 | 14.61 | 15.42 | 14.91 | 12.91 | 15.22 | 14.81 | 15.32 | 15.12 | 11.56 | |
| READBase Model=CLIP4Clip, Adaptation Strategy=READ2026.02 | 9.61 | 3.8 | 4.1 | 5.31 | 3.9 | 13.71 | 14.51 | 14.51 | 15.22 | 14.61 | 13.01 | 15.02 | 14.61 | 15.22 | 15.32 | 11.5 | |
| SARBase Model=CLIP4Clip, Adaptation Strategy=SAR2026.02 | 9.61 | 3.6 | 3.9 | 5.31 | 4.2 | 13.91 | 14.61 | 14.71 | 15.52 | 14.81 | 12.71 | 15.02 | 14.81 | 14.91 | 15.42 | 11.54 | |
| TentBase Model=CLIP4Clip, Adaptation Strategy=Tent2026.02 | 9.51 | 3.6 | 4 | 5.41 | 4.1 | 14.01 | 14.41 | 14.71 | 15.52 | 15.02 | 12.71 | 15.02 | 14.91 | 15.02 | 15.52 | 11.56 | |
| EATABase Model=CLIP4Clip, Adaptation Strategy=EATA2026.02 | 9.41 | 3 | 3.5 | 5.11 | 4 | 13.81 | 14.61 | 14.21 | 15.82 | 14.61 | 12.81 | 15.32 | 15.12 | 14.61 | 15.52 | 11.43 |