Text-to-Video Retrieval on MSRVTT-20
25.8R@1Upper Bound
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Upper Bound2026.01 | 25.8 | 48.54 | 58.84 | 6 | 65.13 | 0.23 | |
| StructAlign2026.01 | 25.37 | 45.94 | 56.01 | 7 | 76.63 | -0.85 | |
| StableFusion2026.01 | 25.16 | 45.53 | 55.1 | 7.33 | 77.79 | -0.7 | |
| MoE-Adapter2026.01 | 22.7 | 41.96 | 51.82 | 9 | 112.86 | 0.01 | |
| VR-LwF2026.01 | 22.39 | 43.27 | 53.33 | 8.67 | 82.04 | 1.44 | |
| ZS CLIPMode=Zero-Shot2026.01 | 22.14 | 41.24 | 51.34 | 10 | 117.48 | 0 | |
| LwF2026.01 | 22.06 | 42.77 | 52.69 | 9 | 85.27 | 1.65 | |
| CLIP4Clip2026.01 | 21.79 | 42.13 | 52.52 | 9 | 86.07 | 1.02 | |
| ZSCL2026.01 | 21.47 | 41.61 | 52.05 | 9.33 | 88.45 | 0.91 | |
| TVR+CL2026.01 | 21.28 | 42.28 | 51.82 | 9.67 | 89.22 | 1.28 | |
| CLIP-ViP2026.01 | 19.74 | 41.25 | 50.61 | 10 | 93.95 | 0.73 | |
| X-Pool2026.01 | 15.98 | 34.21 | 44.34 | 15.33 | 105.97 | 1.37 |