Text-to-Video Retrieval on MSRVTT-10
25.98Recall@1StructAlign
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| StructAlign2026.01 | 25.98 | 46.51 | 57.13 | 6.67 | 73.27 | -0.47 | |
| StableFusion2026.01 | 25.87 | 45.91 | 56.03 | 7 | 74.7 | -0.45 | |
| Upper Bound2026.01 | 25.86 | 48.34 | 58.96 | 6 | 65.1 | -0.17 | |
| VR-LwF2026.01 | 24.49 | 45.59 | 55.45 | 7.33 | 74.89 | 1.22 | |
| ZSCL2026.01 | 23.99 | 45.15 | 54.77 | 8 | 79.69 | 0.1 | |
| LwF2026.01 | 23.85 | 45.3 | 55.68 | 7.33 | 76.46 | 1.68 | |
| CLIP4Clip2026.01 | 23.57 | 44.76 | 54.48 | 8 | 80.23 | 0.61 | |
| MoE-Adapter2026.01 | 22.92 | 42.76 | 52.11 | 9 | 105.7 | 0.14 | |
| TVR+CL2026.01 | 22.47 | 43.71 | 53.59 | 8 | 82.97 | 0.46 | |
| ZS CLIPMode=Zero-Shot2026.01 | 22.14 | 41.24 | 51.34 | 10 | 117.48 | 0 | |
| CLIP-ViP2026.01 | 21.56 | 44.19 | 53.43 | 8 | 86.71 | 0.49 | |
| X-Pool2026.01 | 19.6 | 39.8 | 49.49 | 11 | 94.89 | 0.28 |