{"task":"Person-centric Visual Grounding","dataset":"Who’s Waldo","metric_names":["Accuracy"],"rows":[{"id":115277,"task":"Person-centric Visual Grounding","parent_task":"Visual Grounding","dataset":"Who’s Waldo","model_name":"Who's Waldo","metrics":{"Accuracy":"63.5"},"paper_url":"https://arxiv.org/abs/2108.07253v2","paper_title":"Who's Waldo? Linking People Across Text and Images","paper_date":"2021-08-16","code_links":[{"title":"clairecyq/whos-waldo","url":"https://github.com/clairecyq/whos-waldo"}],"metrics_order":"[\"Accuracy\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]}]}