Text-to-Video Retrieval on MSRVTT (1K-A)
49.3R@1DiffusionRet
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DiffusionRetQB-Norm=true2023.03 | 49.3 | 74.3 | 83.8 | 2 | 8.5 | 207.4 | |
| DiffusionRet2023.03 | 49 | 75.2 | 82.7 | 2 | 12.1 | 206.9 | |
| DiffusionRetQB-Norm=true2023.03 | 48.9 | 75.2 | 83.1 | 2 | 12.1 | 207.2 | |
| HBI2023.03 | 48.6 | 74.6 | 83.4 | 2 | 12 | — | |
| HBI2023.03 | 48.6 | 74.6 | 83.4 | 2 | 12 | 206.6 | |
| DiffusionRet2023.03 | 47.7 | 73.8 | 84.5 | 2 | 8.8 | 206 | |
| DICOSA2023.03 | 47.5 | 74.7 | 83.8 | 2 | 13.2 | 206 | |
| TABLEAdditional expert features=true2023.03 | 47.2 | 74.2 | 84.2 | 2 | 11 | 205.6 | |
| TABLEAdditional expert features=true2023.03 | 47.1 | 74.3 | 82.9 | 2 | 13.4 | 204.3 | |
| TS2-Net2023.03 | 47 | 74.5 | 83.8 | 2 | 13 | — | |
| TS2-Net2023.03 | 47 | 74.5 | 83.8 | 2 | 13 | 205.3 | |
| X-Pool2023.03 | 46.9 | 72.8 | 82.2 | 2 | 14.3 | — | |
| X-Pool2023.03 | 46.9 | 72.8 | 82.2 | 2 | 14.3 | 201.9 | |
| EMCL-Net2023.03 | 46.8 | 73.1 | 83.1 | 2 | — | — | |
| EMCL-Net2023.03 | 46.8 | 73.1 | 83.1 | 2 | 12.8 | 203 | |
| HBI2023.03 | 46.8 | 74.3 | 84.3 | 2 | 8.9 | 205.4 | |
| DICOSA2023.03 | 46.7 | 75.2 | 84.3 | 2 | 8.9 | 206.2 | |
| EMCL-Net2023.03 | 46.5 | 73.5 | 83.5 | 2 | 8.8 | 203.5 | |
| TS2-Net2023.03 | 45.3 | 74.1 | 83.7 | 2 | 9.2 | 203.1 | |
| CLIP4Clip2023.03 | 44.5 | 71.4 | 81.6 | 2 | 15.3 | — | |
| CLIP4Clip2023.03 | 44.5 | 71.4 | 81.6 | 2 | 15.3 | 197.5 | |
| X-Pool2023.03 | 44.4 | 73.3 | 84 | 2 | 9 | 201.7 | |
| CLIP4Clip2023.03 | 42.7 | 70.9 | 80.6 | 2 | 11.6 | 194.2 | |
| TT-CE2023.03 | 32.1 | 62.7 | 75 | 3 | — | 169.8 | |
| T2VLAD2023.03 | 31.8 | 60 | 71.1 | 3 | — | 162.9 | |
| FROZEN2023.03 | 31 | 59.5 | 70.5 | 3 | — | 161 | |
| Support-Set2023.03 | 30.1 | 58.5 | 69.3 | 3 | — | — | |
| Support-Set2023.03 | 30.1 | 58.5 | 69.3 | 3 | — | 157.9 | |
| TT-CE2023.03 | 29.6 | 61.6 | 74.2 | 3 | — | 165.4 | |
| T2VLAD2023.03 | 29.5 | 59 | 70.1 | 4 | — | — | |
| T2VLAD2023.03 | 29.5 | 59 | 70.1 | 4 | — | 158.6 | |
| Support-Set2023.03 | 28.5 | 58.6 | 71.6 | 3 | — | 158.7 | |
| MMT2023.03 | 27 | 57.5 | 69.7 | 3.7 | 21.3 | 154.2 | |
| MMT2023.03 | 26.6 | 57.1 | 69.6 | 4 | 24 | — | |
| MMT2023.03 | 26.6 | 57.1 | 69.6 | 4 | 24 | 153.3 | |
| Multi-modal TransformerPre-training=true2020.07 | 26.6 | 57.1 | 69.6 | 4 | 24 | — | |
| Multi-modal TransformerPre-training=false2020.07 | 24.6 | 54 | 67.1 | 4 | 26.7 | — | |
| CE2020.07 | 20.9 | 48.8 | 62.4 | 6 | 28.2 | — | |
| HT-pretrainedPre-training=true2020.07 | 14.9 | 40.2 | 52.8 | 9 | — | — | |
| HTPre-training=false2020.07 | 12.1 | 35 | 48 | 12 | — | — | |
| JSFusion2020.07 | 10.2 | 31.2 | 43.2 | 13 | — | — | |
| Random baseline2020.07 | 0.1 | 0.5 | 1 | 500 | 500 | — |