{"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/a-multi-world-approach-to-question-answering","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","arxiv_id":"1410.0210","date":"2014-10-01","proceeding":"NeurIPS 2014 12","authors":["Mateusz Malinowski","Mario Fritz"],"abstract":"We propose a method for automatically answering questions about images by\nbringing together recent advances from natural language processing and computer\nvision. We combine discrete reasoning with uncertain predictions by a\nmulti-world approach that represents uncertainty about the perceived world in a\nbayesian framework. Our approach can handle human questions of high complexity\nabout realistic scenes and replies with range of answer like counts, object\nclasses, instances and lists of them. The system is directly trained from\nquestion-answer pairs. We establish a first benchmark for this task that can be\nseen as a modern attempt at a visual turing test.","url_abs":"http://arxiv.org/abs/1410.0210v4","url_pdf":"http://arxiv.org/pdf/1410.0210v4.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"daquar","name":"DAQUAR","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1410.0210","atlas_url":"https://app.syntology.ai/?focus=1410.0210","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}