| phrase-grounding-on-flickr30k-entities-dev | VisualBERT | #3 | R@1: 70.4R@10: 86.31R@5: 84.49 |
| phrase-grounding-on-flickr30k-entities-test | VisualBERT | #9 | R@1: 71.33R@5: 84.98R@10: 86.51 |
| visual-question-answering-on-vcr-q-a-test | VisualBERT | #6 | Accuracy: 71.6 |
| visual-question-answering-on-vcr-q-ar-test | VisualBERT | #5 | Accuracy: 52.4 |
| visual-question-answering-on-vcr-qa-r-test | VisualBERT | #6 | Accuracy: 73.2 |
| visual-question-answering-on-vqa-v2-test-dev | VisualBERT | #25 | Accuracy: 70.8 |
| visual-question-answering-on-vqa-v2-test-std | VisualBERT | #21 | overall: 71 |
| visual-reasoning-on-nlvr2-dev | VisualBERT | #15 | Accuracy: 66.7 |