{"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/are-elephants-bigger-than-butterflies","title":"Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects","arxiv_id":"1602.00753","date":"2016-02-02","proceeding":null,"authors":["Hessam Bagherinezhad","Hannaneh Hajishirzi","Yejin Choi","Ali Farhadi"],"abstract":"Human vision greatly benefits from the information about sizes of objects.\nThe role of size in several visual reasoning tasks has been thoroughly explored\nin human perception and cognition. However, the impact of the information about\nsizes of objects is yet to be determined in AI. We postulate that this is\nmainly attributed to the lack of a comprehensive repository of size\ninformation. In this paper, we introduce a method to automatically infer object\nsizes, leveraging visual and textual information from web. By maximizing the\njoint likelihood of textual and visual observations, our method learns reliable\nrelative size estimates, with no explicit human supervision. We introduce the\nrelative size dataset and show that our method outperforms competitive textual\nand visual baselines in reasoning about size comparisons.","url_abs":"http://arxiv.org/abs/1602.00753v1","url_pdf":"http://arxiv.org/pdf/1602.00753v1.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":"relative-size","name":"Relative Size","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.00753","atlas_url":"https://app.syntology.ai/?focus=1602.00753","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}