Text-to-Video Retrieval on ActivityNet → LSMDC
16.72R@1HAT-VTR
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| HAT-VTRBackbone=Xpool2026.02 | 16.72 | 31.93 | 40.84 | |
| READBackbone=CLIP4Clip2026.02 | 16.32 | 28.23 | 35.64 | |
| TentBackbone=Xpool2026.02 | 16.22 | 31.53 | 37.94 | |
| CLIP4ClipBackbone=CLIP4Clip2026.02 | 16.12 | 28.63 | 35.74 | |
| TCRBackbone=CLIP4Clip2026.02 | 16.02 | 29.03 | 36.14 | |
| TentBackbone=CLIP4Clip2026.02 | 15.92 | 28.43 | 35.74 | |
| SARBackbone=CLIP4Clip2026.02 | 15.92 | 28.43 | 35.84 | |
| EATABackbone=CLIP4Clip2026.02 | 15.92 | 29.33 | 36.84 | |
| SARBackbone=Xpool2026.02 | 15.92 | 31.43 | 38.04 | |
| TCRBackbone=Xpool2026.02 | 15.82 | 31.01 | 37.84 | |
| HAT-VTRBackbone=CLIP4Clip2026.02 | 15.72 | 31.33 | 39.64 | |
| XpoolBackbone=Xpool2026.02 | 15.72 | 31.03 | 37.64 | |
| EATABackbone=Xpool2026.02 | 15.72 | 32.23 | 38.04 | |
| READBackbone=Xpool2026.02 | 15.62 | 30.93 | 37.54 |