{"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/vqa-therapy-exploring-answer-differences-by","title":"VQA Therapy: Exploring Answer Differences by Visually Grounding Answers","arxiv_id":"2308.11662","date":"2023-08-21","proceeding":"ICCV 2023 1","authors":["Chongyan Chen","Samreen Anjum","Danna Gurari"],"abstract":"Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. We introduce the first dataset that visually grounds each unique answer to each visual question, which we call VQAAnswerTherapy. We then propose two novel problems of predicting whether a visual question has a single answer grounding and localizing all answer groundings. We benchmark modern algorithms for these novel problems to show where they succeed and struggle. The dataset and evaluation server can be found publicly at https://vizwiz.org/tasks-and-datasets/vqa-answer-therapy/.","url_abs":"https://arxiv.org/abs/2308.11662v2","url_pdf":"https://arxiv.org/pdf/2308.11662v2.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":"vqa-therapy-exploring-answer-differences-by","repo_url":"https://github.com/ccychongyanchen/vqatherapycrowdsourcing","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":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11662","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}