Video-to-Text Retrieval on MSRVTT (1k-B)
21.1Recall@1
Multi-modal Transformer
Updated 2d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2020.07 | 21.1 | 49.4 | 63.2 | 6 | 24.5 | |
2020.07 | 18 | 46 | 60.3 | 6.5 | 30.6 | |
2020.07 | 16.4 | 41.3 | 54.4 | 8.7 | - | |
2020.07 | 0.1 | 0.5 | 1 | 500 | 500 |
Multi-modal Transformer
| Method | Links | |||||
|---|---|---|---|---|---|---|
2020.07 | 21.1 | 49.4 | 63.2 | 6 | 24.5 | |
2020.07 | 18 | 46 | 60.3 | 6.5 | 30.6 | |
2020.07 | 16.4 | 41.3 | 54.4 | 8.7 | - | |
2020.07 | 0.1 | 0.5 | 1 | 500 | 500 |