{"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/who-is-mistaken","title":"Who is Mistaken?","arxiv_id":"1612.01175","date":"2016-12-04","proceeding":null,"authors":["Benjamin Eysenbach","Carl Vondrick","Antonio Torralba"],"abstract":"Recognizing when people have false beliefs is crucial for understanding their\nactions. We introduce the novel problem of identifying when people in abstract\nscenes have incorrect beliefs. We present a dataset of scenes, each visually\ndepicting an 8-frame story in which a character has a mistaken belief. We then\ncreate a representation of characters' beliefs for two tasks in human action\nunderstanding: predicting who is mistaken, and when they are mistaken.\nExperiments suggest that our method for identifying mistaken characters\nperforms better on these tasks than simple baselines. Diagnostics on our model\nsuggest it learns important cues for recognizing mistaken beliefs, such as\ngaze. We believe models of people's beliefs will have many applications in\naction understanding, robotics, and healthcare.","url_abs":"http://arxiv.org/abs/1612.01175v2","url_pdf":"http://arxiv.org/pdf/1612.01175v2.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":"action-understanding","task_name":"Action Understanding"}],"methods":[],"datasets_introduced":[{"slug":"visual-beliefs","name":"Visual Beliefs","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.01175","atlas_url":"https://app.syntology.ai/?focus=1612.01175","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}