Cross Modal Retrieval On Recipe1M 1
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 |
|---|---|---|
| recipe1m-a-dataset-for-learning-cross-modal | 17 | 21 |
| structured-vision-language-pretraining-for | 45.2 | 47.3 |