Text-to-Video Retrieval on ActivityNet MSRVTT to ActivityNet adaptation
39.5Recall@1HAT-VTR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| HAT-VTRBase Model=Xpool2026.02 | 39.5 | 64.5 | |
| HAT-VTRBase Model=CLIP4Clip2026.02 | 38.6 | 62.6 | |
| EATABase Model=Xpool2026.02 | 38.6 | 61.9 | |
| TCRBase Model=Xpool2026.02 | 38.5 | 62.2 | |
| XpoolBase Model=Xpool2026.02 | 38.1 | 61.8 | |
| TentBase Model=Xpool2026.02 | 38 | 62.1 | |
| SARBase Model=Xpool2026.02 | 38 | 62 | |
| READBase Model=Xpool2026.02 | 37.8 | 61.4 | |
| HAT-VTRBase Model=CLIP4Clip2026.02 | 36.53 | 65.43 | |
| EATABase Model=CLIP4Clip2026.02 | 36.3 | 59.3 | |
| CLIP4ClipBase Model=CLIP4Clip2026.02 | 35 | 57.5 | |
| TCRBase Model=CLIP4Clip2026.02 | 35 | 58.4 | |
| TentBase Model=CLIP4Clip2026.02 | 34.9 | 58.3 | |
| READBase Model=CLIP4Clip2026.02 | 34.9 | 57.8 | |
| SARBase Model=CLIP4Clip2026.02 | 34.8 | 58.1 | |
| HAT-VTRBase Model=Xpool2026.02 | 34.13 | 61.85 | |
| SARBase Model=Xpool2026.02 | 30.69 | 57.96 | |
| XpoolBase Model=Xpool2026.02 | 30.61 | 57.92 | |
| TentBase Model=Xpool2026.02 | 30.53 | 57.94 | |
| READBase Model=Xpool2026.02 | 30.14 | 56.46 | |
| EATABase Model=Xpool2026.02 | 29.98 | 57.64 | |
| TCRBase Model=Xpool2026.02 | 29.81 | 57.25 | |
| CLIP4ClipBase Model=CLIP4Clip2026.02 | 28.7 | 57.58 | |
| SARBase Model=CLIP4Clip2026.02 | 28.51 | 57.01 | |
| TentBase Model=CLIP4Clip2026.02 | 28.19 | 57.07 | |
| READBase Model=CLIP4Clip2026.02 | 27.98 | 57.25 | |
| EATABase Model=CLIP4Clip2026.02 | 27.7 | 55.26 | |
| TCRBase Model=CLIP4Clip2026.02 | 26.3 | 52.49 |