{"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/zero-shot-activity-recognition-with-verb","title":"Zero-Shot Activity Recognition with Verb Attribute Induction","arxiv_id":"1707.09468","date":"2017-07-29","proceeding":"EMNLP 2017 9","authors":["Rowan Zellers","Yejin Choi"],"abstract":"In this paper, we investigate large-scale zero-shot activity recognition by\nmodeling the visual and linguistic attributes of action verbs. For example, the\nverb \"salute\" has several properties, such as being a light movement, a social\nact, and short in duration. We use these attributes as the internal mapping\nbetween visual and textual representations to reason about a previously unseen\naction. In contrast to much prior work that assumes access to gold standard\nattributes for zero-shot classes and focuses primarily on object attributes,\nour model uniquely learns to infer action attributes from dictionary\ndefinitions and distributed word representations. Experimental results confirm\nthat action attributes inferred from language can provide a predictive signal\nfor zero-shot prediction of previously unseen activities.","url_abs":"http://arxiv.org/abs/1707.09468v2","url_pdf":"http://arxiv.org/pdf/1707.09468v2.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":"zero-shot-activity-recognition-with-verb","repo_url":"https://github.com/uwnlp/verb-attributes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"zero-shot-activity-recognition-with-verb","repo_url":"https://github.com/rowanz/verb-attributes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.09468","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}