Video-to-Text Retrieval on LSMDC (Robustness Metrics)
14.31Gaussian Blur R@1HAT-VTR
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HAT-VTRBase Model=Xpool2026.02 | 14.31 | 13.61 | 9.71 | 10.81 | 16.52 | 1.3 | 16.32 | 15.42 | 7.81 | 8.71 | 13.21 | 12.41 | 11.68 | |
| HAT-VTRBase Model=CLIP4Clip2026.02 | 13.81 | 14.21 | 9.51 | 11.51 | 16.62 | 0.8 | 16.02 | 15.12 | 8.71 | 7.61 | 9.91 | 13.01 | 11.4 | |
| EATABase Model=CLIP4Clip2026.02 | 12.01 | 11.11 | 1.2 | 6.61 | 15.22 | 0.1 | 14.61 | 12.61 | 5.21 | 5.11 | 7.11 | 11.71 | 8.55 | |
| TCRBase Model=CLIP4Clip2026.02 | 11.61 | 11.51 | 6.21 | 7.91 | 14.21 | 0.8 | 13.81 | 12.71 | 5.51 | 4.8 | 6.41 | 11.91 | 8.95 | |
| EATABase Model=Xpool2026.02 | 11.61 | 11.31 | 0.6 | 4.5 | 14.81 | 0.3 | 15.12 | 13.21 | 6.11 | 5.11 | 10.61 | 11.01 | 8.69 | |
| TCRBase Model=Xpool2026.02 | 11.51 | 9.81 | 5.51 | 7.01 | 14.31 | 1.1 | 14.81 | 12.41 | 7.71 | 5.51 | 10.61 | 11.31 | 9.3 | |
| SARBase Model=CLIP4Clip2026.02 | 11.01 | 9.61 | 2.7 | 5.41 | 14.01 | 0.3 | 13.61 | 12.61 | 5.31 | 4.4 | 7.31 | 11.41 | 8.14 | |
| TentBase Model=CLIP4Clip2026.02 | 10.91 | 9.41 | 2.4 | 4.9 | 14.11 | 0.1 | 13.71 | 12.71 | 4.6 | 4.4 | 7.21 | 11.31 | 7.98 | |
| CLIP4ClipBase Model=CLIP4Clip2026.02 | 10.61 | 8.61 | 3.6 | 6.11 | 13.51 | 0.4 | 14.01 | 12.61 | 5.11 | 4.4 | 6.91 | 11.21 | 8.09 | |
| READBase Model=CLIP4Clip2026.02 | 10.41 | 7.91 | 4.9 | 6.01 | 12.91 | 0.3 | 13.71 | 12.31 | 5.11 | 4.5 | 6.51 | 11.31 | 7.99 | |
| SARBase Model=Xpool2026.02 | 9.91 | 8.11 | 2.7 | 5.21 | 15.02 | 0.9 | 14.21 | 12.11 | 6.31 | 4.3 | 10.31 | 11.21 | 8.36 | |
| TentBase Model=Xpool2026.02 | 9.71 | 8.01 | 2.7 | 5.01 | 15.22 | 0.8 | 13.91 | 12.21 | 5.91 | 4.1 | 10.31 | 11.31 | 8.27 | |
| XpoolBase Model=Xpool2026.02 | 9.31 | 7.21 | 4 | 5.31 | 14.51 | 0.9 | 13.71 | 11.81 | 6.51 | 4.2 | 10.21 | 11.01 | 8.22 | |
| READBase Model=Xpool2026.02 | 9.21 | 6.71 | 4.2 | 5.41 | 13.71 | 1 | 13.41 | 11.71 | 6.61 | 4.4 | 9.91 | 10.71 | 8.08 |