{"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/autoloc-weakly-supervised-temporal-action","title":"AutoLoc: Weakly-supervised Temporal Action Localization","arxiv_id":"1807.08333","date":"2018-07-22","proceeding":null,"authors":["Zheng Shou","Hang Gao","Lei Zhang","Kazuyuki Miyazawa","Shih-Fu Chang"],"abstract":"Temporal Action Localization (TAL) in untrimmed video is important for many\napplications. But it is very expensive to annotate the segment-level ground\ntruth (action class and temporal boundary). This raises the interest of\naddressing TAL with weak supervision, namely only video-level annotations are\navailable during training). However, the state-of-the-art weakly-supervised TAL\nmethods only focus on generating good Class Activation Sequence (CAS) over time\nbut conduct simple thresholding on CAS to localize actions. In this paper, we\nfirst develop a novel weakly-supervised TAL framework called AutoLoc to\ndirectly predict the temporal boundary of each action instance. We propose a\nnovel Outer-Inner-Contrastive (OIC) loss to automatically discover the needed\nsegment-level supervision for training such a boundary predictor. Our method\nachieves dramatically improved performance: under the IoU threshold 0.5, our\nmethod improves mAP on THUMOS'14 from 13.7% to 21.2% and mAP on ActivityNet\nfrom 7.4% to 27.3%. It is also very encouraging to see that our\nweakly-supervised method achieves comparable results with some fully-supervised\nmethods.","url_abs":"http://arxiv.org/abs/1807.08333v2","url_pdf":"http://arxiv.org/pdf/1807.08333v2.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":"autoloc-weakly-supervised-temporal-action","repo_url":"https://github.com/zhengshou/AutoLoc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"weakly-supervised-temporal-action","task_name":"Weakly-supervised Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}