Video-to-Text Retrieval on MSR-VTT (Test1k-Yu)
21.7R@1Dual Encoding
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Dual EncodingSource=Proposed, Visual Feature=ResNeXt-ResNet2020.09 | 21.7 | 49.4 | 61.6 | 6 | 34.7 | 262.7 | |
| CESource=Original Paper2020.09 | 20.6 | 50.3 | 64 | 5.3 | — | 267 | |
| HGRSource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 20.4 | 47.9 | 60.6 | 6 | 33.4 | 259.1 | |
| TCESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 18.9 | 43.5 | 58.8 | 7 | 31.4 | 243.3 | |
| W2VVSource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 17.3 | 39.3 | 50.2 | 10 | 27.8 | 133.8 | |
| W2VV++Source=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 16.9 | 42.7 | 54.6 | 8 | 29 | 236.9 | |
| VSE++Source=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 16.2 | 39.3 | 51.2 | 10 | 27.4 | 212.1 | |
| CESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 15.8 | 44.9 | 59.2 | 7 | 30.4 | 241.8 | |
| MEESource=Re-trained, Visual Feature=ResNeXt-ResNet2020.09 | 15.2 | 40.9 | 53.8 | 9 | 27.9 | 215.3 |