| cross-modal-retrieval-on-coco-2014 | X-VLM (base) | #8 | Text-to-image R@1: 63.4Text-to-image R@5: 85.8… |
| cross-modal-retrieval-on-flickr30k | X-VLM (base) | #5 | Image-to-text R@1: 97.1Image-to-text R@5: 100.0… |
| image-captioning-on-coco-captions | X-VLM (base) | #12 | BLEU-4: 41.3CIDER: 140.8 |
| image-retrieval-on-flickr30k-1k-test | X-VLM (base) | #1 | R@1: 86.9R@5: 97.3R@10: 98.7 |
| open-vocabulary-attribute-detection-on-ovad-1 | X-VLM | #1 | mean average precision: 28.0 |
| visual-grounding-on-refcoco-test-b | X-VLM (base) | #6 | Accuracy (%): 76.91 |
| visual-grounding-on-refcoco-testa | X-VLM (base) | #6 | Accuracy (%): 89.00 |
| visual-grounding-on-refcoco-val | X-VLM (base) | #6 | Accuracy (%): 84.51 |
| visual-question-answering-on-vqa-v2-test-dev | X-VLM (base) | #14 | Accuracy: 78.22 |
| visual-reasoning-on-nlvr2-dev | X-VLM (base) | #9 | Accuracy: 84.41 |
| visual-reasoning-on-nlvr2-test | X-VLM (base) | #8 | Accuracy: 84.76 |