{"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/think-visually-question-answering-through","title":"Think Visually: Question Answering through Virtual Imagery","arxiv_id":"1805.11025","date":"2018-05-25","proceeding":"ACL 2018 7","authors":["Ankit Goyal","Jian Wang","Jia Deng"],"abstract":"In this paper, we study the problem of geometric reasoning in the context of\nquestion-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new\ndeep network architecture designed for answering questions that admit latent\nvisual representations. DSMN learns to generate and reason over such\nrepresentations. Further, we propose two synthetic benchmarks, FloorPlanQA and\nShapeIntersection, to evaluate the geometric reasoning capability of QA\nsystems. Experimental results validate the effectiveness of our proposed DSMN\nfor visual thinking tasks.","url_abs":"http://arxiv.org/abs/1805.11025v1","url_pdf":"http://arxiv.org/pdf/1805.11025v1.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":"think-visually-question-answering-through","repo_url":"https://github.com/umich-vl/think_visually","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-commonsense-reasoning","task_name":"Visual Commonsense Reasoning"}],"methods":[{"method_slug":"memory-network","method_name":"Memory Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}