| image-text-matching-on-commercialadsdataset | VL-BERT | #4 | ADD(S) AUC: 86.27 |
| visual-question-answering-on-vcr-q-a-test | VL-BERTLARGE | #4 | Accuracy: 75.8 |
| visual-question-answering-on-vcr-q-ar-test | VL-BERTLARGE | #3 | Accuracy: 59.7 |
| visual-question-answering-on-vcr-qa-r-test | VL-BERTLARGE | #4 | Accuracy: 78.4 |
| visual-question-answering-on-vqa-v2-test-dev | VL-BERTLARGE | #21 | Accuracy: 71.79 |
| visual-question-answering-on-vqa-v2-test-dev | VL-BERTBASE | #24 | Accuracy: 71.16 |
| visual-question-answering-on-vqa-v2-test-std | VL-BERTLARGE | #19 | overall: 72.2 |