Cross Modal Retrieval On Mscoco 1K
Metrics
Image-to-text R@1
Text-to-image R@1
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Image-to-text R@1 | Text-to-image R@1 |
|---|---|---|
| dual-path-convolutional-image-text-embedding | 41.2 | 25.3 |
| napreg-nouns-as-proxies-regularization-for | 81.9 | 66.9 |