{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dvqa-understanding-data-visualizations-via","title":"DVQA: Understanding Data Visualizations via Question Answering","arxiv_id":"1801.08163","date":"2018-01-24","proceeding":"CVPR 2018 6","authors":["Kushal Kafle","Brian Price","Scott Cohen","Christopher Kanan"],"abstract":"Bar charts are an effective way to convey numeric information, but today's\nalgorithms cannot parse them. Existing methods fail when faced with even minor\nvariations in appearance. Here, we present DVQA, a dataset that tests many\naspects of bar chart understanding in a question answering framework. Unlike\nvisual question answering (VQA), DVQA requires processing words and answers\nthat are unique to a particular bar chart. State-of-the-art VQA algorithms\nperform poorly on DVQA, and we propose two strong baselines that perform\nconsiderably better. Our work will enable algorithms to automatically extract\nnumeric and semantic information from vast quantities of bar charts found in\nscientific publications, Internet articles, business reports, and many other\nareas.","url_abs":"http://arxiv.org/abs/1801.08163v2","url_pdf":"http://arxiv.org/pdf/1801.08163v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dvqa-understanding-data-visualizations-via","repo_url":"https://github.com/kushalkafle/DVQA_dataset","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"chart-question-answering","task_name":"Chart Question Answering"},{"task_slug":"chart-understanding","task_name":"Chart Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"dvqa","name":"DVQA","full_name":"Data Visualizations via Question Answering"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.08163","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}