{"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/grounding-answers-for-visual-questions-asked","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","arxiv_id":"2202.01993","date":"2022-02-04","proceeding":"CVPR 2022 1","authors":["Chongyan Chen","Samreen Anjum","Danna Gurari"],"abstract":"Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.","url_abs":"https://arxiv.org/abs/2202.01993v3","url_pdf":"https://arxiv.org/pdf/2202.01993v3.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":"grounding-answers-for-visual-questions-asked","repo_url":"https://github.com/ccychongyanchen/vizwizvqagroundingcrowdsourcing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","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-answer-grounding","name":"VizWiz Answer Grounding","full_name":""},{"slug":"vizwiz-vqa-grounding","name":"VizWiz-VQA-Grounding","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.01993","atlas_url":"https://app.syntology.ai/?focus=2202.01993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01993"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ccychongyanchen/vizwizvqagroundingcrowdsourcing","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"659fc8b13b5e12da","entry":"processDigitArticle","repo":"ccychongyanchen/vizwizvqagroundingcrowdsourcing","repo_kind":"official","path":"static/QA_annotations/Preprocess.py","file_url":"https://github.com/ccychongyanchen/vizwizvqagroundingcrowdsourcing/blob/HEAD/static/QA_annotations/Preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"659fc8b13b5e12da"}},{"code_sha256_prefix":"adc153fe14ba9964","entry":"processPunctuation","repo":"ccychongyanchen/vizwizvqagroundingcrowdsourcing","repo_kind":"official","path":"static/QA_annotations/Preprocess.py","file_url":"https://github.com/ccychongyanchen/vizwizvqagroundingcrowdsourcing/blob/HEAD/static/QA_annotations/Preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"adc153fe14ba9964"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}