{"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/action-completion-a-temporal-model-for-moment","title":"Action Completion: A Temporal Model for Moment Detection","arxiv_id":"1805.06749","date":"2018-05-17","proceeding":null,"authors":["Farnoosh Heidarivincheh","Majid Mirmehdi","Dima Damen"],"abstract":"We introduce completion moment detection for actions - the problem of\nlocating the moment of completion, when the action's goal is confidently\nconsidered achieved. The paper proposes a joint classification-regression\nrecurrent model that predicts completion from a given frame, and then\nintegrates frame-level contributions to detect sequence-level completion\nmoment. We introduce a recurrent voting node that predicts the frame's relative\nposition of the completion moment by either classification or regression. The\nmethod is also capable of detecting incompletion. For example, the method is\ncapable of detecting a missed ball-catch, as well as the moment at which the\nball is safely caught. We test the method on 16 actions from three public\ndatasets, covering sports as well as daily actions. Results show that when\ncombining contributions from frames prior to the completion moment as well as\nframes post completion, the completion moment is detected within one second in\n89% of all tested sequences.","url_abs":"http://arxiv.org/abs/1805.06749v2","url_pdf":"http://arxiv.org/pdf/1805.06749v2.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":"action-completion-a-temporal-model-for-moment","repo_url":"https://github.com/FarnooshHeidari/CompletionDetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"model","task_name":"model"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}