{"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/vizwiz-grand-challenge-answering-visual","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","arxiv_id":"1802.08218","date":"2018-02-22","proceeding":"CVPR 2018 6","authors":["Danna Gurari","Qing Li","Abigale J. Stangl","Anhong Guo","Chi Lin","Kristen Grauman","Jiebo Luo","Jeffrey P. Bigham"],"abstract":"The study of algorithms to automatically answer visual questions currently is\nmotivated by visual question answering (VQA) datasets constructed in artificial\nVQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising\nfrom a natural VQA setting. VizWiz consists of over 31,000 visual questions\noriginating from blind people who each took a picture using a mobile phone and\nrecorded a spoken question about it, together with 10 crowdsourced answers per\nvisual question. VizWiz differs from the many existing VQA datasets because (1)\nimages are captured by blind photographers and so are often poor quality, (2)\nquestions are spoken and so are more conversational, and (3) often visual\nquestions cannot be answered. Evaluation of modern algorithms for answering\nvisual questions and deciding if a visual question is answerable reveals that\nVizWiz is a challenging dataset. We introduce this dataset to encourage a\nlarger community to develop more generalized algorithms that can assist blind\npeople.","url_abs":"http://arxiv.org/abs/1802.08218v4","url_pdf":"http://arxiv.org/pdf/1802.08218v4.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":"vizwiz-grand-challenge-answering-visual","repo_url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"vizwiz","name":"VizWiz","full_name":"VizWiz-VQA"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.08218","atlas_url":"https://app.syntology.ai/?focus=1802.08218","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}