Text-to-Video Retrieval on MSVD 1kA (test)
35.07OCRHAT-VTR
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HAT-VTRBackbone=Xpool2026.02 | 35.07 | 16.57 | 13.43 | 22.39 | 14.63 | 54.33 | 56.42 | 56.42 | 57.61 | 57.91 | 55.37 | 59.1 | 57.76 | 56.87 | 58.51 | 44.83 | |
| HAT-VTRBackbone=CLIP4Clip2026.02 | 34.18 | 14.33 | 12.24 | 20.9 | 12.99 | 55.07 | 56.27 | 56.87 | 56.87 | 56.27 | 53.88 | 58.36 | 57.01 | 56.27 | 58.36 | 43.99 | |
| EATABackbone=Xpool2026.02 | 33.58 | 16.72 | 14.78 | 21.49 | 14.18 | 50.6 | 54.48 | 53.73 | 53.58 | 55.22 | 52.24 | 55.37 | 55.37 | 52.39 | 55.82 | 42.64 | |
| TCRBackbone=Xpool2026.02 | 33.43 | 15.97 | 14.18 | 22.09 | 12.84 | 50.45 | 55.07 | 52.84 | 53.58 | 55.07 | 52.84 | 56.27 | 55.22 | 51.94 | 55.97 | 42.52 | |
| SARBackbone=CLIP4Clip2026.02 | 32.99 | 13.88 | 12.69 | 22.24 | 12.24 | 52.84 | 54.63 | 54.03 | 55.37 | 54.93 | 51.79 | 56.42 | 54.48 | 52.99 | 55.52 | 42.47 | |
| TentBackbone=CLIP4Clip2026.02 | 32.84 | 13.88 | 12.54 | 22.24 | 12.24 | 52.84 | 54.48 | 54.03 | 55.22 | 54.93 | 51.79 | 56.27 | 54.48 | 53.28 | 55.37 | 42.43 | |
| TentBackbone=Xpool2026.02 | 32.69 | 16.57 | 14.18 | 21.19 | 13.58 | 51.34 | 55.07 | 53.43 | 54.48 | 56.27 | 52.54 | 56.12 | 55.67 | 51.94 | 55.82 | 42.73 | |
| SARBackbone=Xpool2026.02 | 32.69 | 16.57 | 14.03 | 21.19 | 13.58 | 51.49 | 55.07 | 53.43 | 54.48 | 56.42 | 52.54 | 56.27 | 55.52 | 51.94 | 55.82 | 42.74 | |
| CLIP4ClipBackbone=CLIP4Clip2026.02 | 32.54 | 13.73 | 12.54 | 22.24 | 12.09 | 52.69 | 54.93 | 54.33 | 55.52 | 55.37 | 51.79 | 56.42 | 54.48 | 53.58 | 55.37 | 42.51 | |
| TCRBackbone=CLIP4Clip2026.02 | 32.54 | 13.43 | 12.54 | 22.09 | 12.24 | 53.13 | 54.93 | 53.58 | 54.93 | 55.07 | 52.09 | 55.37 | 55.07 | 53.13 | 55.07 | 42.35 | |
| READBackbone=CLIP4Clip2026.02 | 32.39 | 13.73 | 12.54 | 21.94 | 12.09 | 52.84 | 54.48 | 54.18 | 55.37 | 55.37 | 51.79 | 56.57 | 54.48 | 53.43 | 55.52 | 42.45 | |
| XpoolBackbone=Xpool2026.02 | 32.39 | 16.27 | 13.73 | 20.9 | 13.58 | 51.94 | 54.93 | 53.43 | 54.48 | 56.42 | 52.69 | 56.12 | 55.52 | 51.94 | 55.67 | 42.67 | |
| READBackbone=Xpool2026.02 | 32.39 | 16.12 | 13.88 | 20.9 | 13.43 | 51.79 | 54.93 | 53.73 | 54.33 | 56.42 | 52.69 | 56.12 | 55.37 | 51.94 | 55.82 | 42.66 | |
| EATABackbone=CLIP4Clip2026.02 | 32.24 | 14.03 | 12.54 | 21.64 | 12.69 | 52.09 | 54.78 | 53.43 | 54.93 | 54.48 | 51.19 | 55.07 | 54.48 | 52.99 | 54.93 | 42.1 |