{"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/incremental-tube-construction-for-human","title":"Incremental Tube Construction for Human Action Detection","arxiv_id":"1704.01358","date":"2017-04-05","proceeding":null,"authors":["Harkirat Singh Behl","Michael Sapienza","Gurkirt Singh","Suman Saha","Fabio Cuzzolin","Philip H. S. Torr"],"abstract":"Current state-of-the-art action detection systems are tailored for offline\nbatch-processing applications. However, for online applications like\nhuman-robot interaction, current systems fall short, either because they only\ndetect one action per video, or because they assume that the entire video is\navailable ahead of time. In this work, we introduce a real-time and online\njoint-labelling and association algorithm for action detection that can\nincrementally construct space-time action tubes on the most challenging action\nvideos in which different action categories occur concurrently. In contrast to\nprevious methods, we solve the detection-window association and action\nlabelling problems jointly in a single pass. We demonstrate superior online\nassociation accuracy and speed (2.2ms per frame) as compared to the current\nstate-of-the-art offline systems. We further demonstrate that the entire action\ndetection pipeline can easily be made to work effectively in real-time using\nour action tube construction algorithm.","url_abs":"http://arxiv.org/abs/1704.01358v2","url_pdf":"http://arxiv.org/pdf/1704.01358v2.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":"incremental-tube-construction-for-human","repo_url":"https://github.com/harkiratbehl/OJLA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}