{"task":"Visual Question Answering (VQA)","dataset":"VCR (Q-A) dev","metric_names":["Accuracy"],"rows":[{"id":25865,"task":"Visual Question Answering (VQA)","parent_task":null,"dataset":"VCR (Q-A) dev","model_name":"VL-BERTLARGE","metrics":{"Accuracy":"75.5"},"paper_url":"https://arxiv.org/abs/1908.08530v4","paper_title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","paper_date":"2019-08-22","code_links":[{"title":"jackroos/VL-BERT","url":"https://github.com/jackroos/VL-BERT"},{"title":"ImperialNLP/BertGen","url":"https://github.com/ImperialNLP/BertGen"},{"title":"jules-samaran/vl-bert","url":"https://github.com/jules-samaran/vl-bert"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":25866,"task":"Visual Question Answering (VQA)","parent_task":null,"dataset":"VCR (Q-A) dev","model_name":"VL-BERTBASE","metrics":{"Accuracy":"73.8"},"paper_url":"https://arxiv.org/abs/1908.08530v4","paper_title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","paper_date":"2019-08-22","code_links":[{"title":"jackroos/VL-BERT","url":"https://github.com/jackroos/VL-BERT"},{"title":"ImperialNLP/BertGen","url":"https://github.com/ImperialNLP/BertGen"},{"title":"jules-samaran/vl-bert","url":"https://github.com/jules-samaran/vl-bert"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":25867,"task":"Visual Question Answering (VQA)","parent_task":null,"dataset":"VCR (Q-A) dev","model_name":"VisualBERT","metrics":{"Accuracy":"70.8"},"paper_url":"https://arxiv.org/abs/1908.03557v1","paper_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","paper_date":"2019-08-09","code_links":[{"title":"uclanlp/visualbert","url":"https://github.com/uclanlp/visualbert"},{"title":"YIKUAN8/Transformers-VQA","url":"https://github.com/YIKUAN8/Transformers-VQA"},{"title":"lalithjets/surgical_vqa","url":"https://github.com/lalithjets/surgical_vqa"},{"title":"gchhablani/multilingual-vqa","url":"https://github.com/gchhablani/multilingual-vqa"},{"title":"longbai1006/surgical-vqla","url":"https://github.com/longbai1006/surgical-vqla"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"chenkangyang/paddle_visual_bert","url":"https://github.com/chenkangyang/paddle_visual_bert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/visual_bert"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/visual_bert"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}