Video-to-Text Retrieval on MSR-VTT (Test1k-Miech)
25.1Recall@1Dual Encoding
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Dual EncodingSource=Proposed, Visual Feature=ResNeXt-ResNet2020.09 | 25.1 | 52.1 | 64.6 | 5 | 37.7 | 277.9 | |
| HGRSource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 20 | 48.3 | 60.9 | 6 | 33.2 | 265.9 | |
| W2VV++Source=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 18.6 | 46.4 | 59.1 | 6 | 31.7 | 255.3 | |
| VSE++Source=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 18.1 | 40.4 | 52.1 | 9 | 29.2 | 220.5 | |
| CESource=Original Paper2020.09 | 18 | 46 | 60.3 | 6.5 | — | 249.2 | |
| CESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 17.4 | 42.9 | 56.1 | 8 | 29.8 | 233.1 | |
| W2VVSource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 17.3 | 42 | 53.5 | 9 | 29.3 | 145.3 | |
| fpoSESource=Original Paper2020.09 | 16.4 | 41.3 | 54.4 | 8.7 | — | 217.5 | |
| MEESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 15.3 | 41.9 | 54.5 | 8 | 28.1 | 218.7 | |
| TCESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 15.1 | 43.3 | 58.2 | 7 | 28.3 | 236.6 |