{"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/learning-to-act-properly-predicting-and","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","arxiv_id":"1712.07576","date":"2017-12-20","proceeding":"CVPR 2018 6","authors":["Ching-Yao Chuang","Jiaman Li","Antonio Torralba","Sanja Fidler"],"abstract":"We address the problem of affordance reasoning in diverse scenes that appear\nin the real world. Affordances relate the agent's actions to their effects when\ntaken on the surrounding objects. In our work, we take the egocentric view of\nthe scene, and aim to reason about action-object affordances that respect both\nthe physical world as well as the social norms imposed by the society. We also\naim to teach artificial agents why some actions should not be taken in certain\nsituations, and what would likely happen if these actions would be taken. We\ncollect a new dataset that builds upon ADE20k, referred to as ADE-Affordance,\nwhich contains annotations enabling such rich visual reasoning. We propose a\nmodel that exploits Graph Neural Networks to propagate contextual information\nfrom the scene in order to perform detailed affordance reasoning about each\nobject. Our model is showcased through various ablation studies, pointing to\nsuccesses and challenges in this complex task.","url_abs":"http://arxiv.org/abs/1712.07576v2","url_pdf":"http://arxiv.org/pdf/1712.07576v2.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":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"ade-affordance","name":"ADE-Affordance","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.07576","atlas_url":"https://app.syntology.ai/?focus=1712.07576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}