{"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/otas-unsupervised-boundary-detection-for","title":"OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation","arxiv_id":"2309.06276","date":"2023-09-12","proceeding":null,"authors":["Yuerong Li","Zhengrong Xue","Huazhe Xu"],"abstract":"Temporal action segmentation is typically achieved by discovering the dramatic variances in global visual descriptors. In this paper, we explore the merits of local features by proposing the unsupervised framework of Object-centric Temporal Action Segmentation (OTAS). Broadly speaking, OTAS consists of self-supervised global and local feature extraction modules as well as a boundary selection module that fuses the features and detects salient boundaries for action segmentation. As a second contribution, we discuss the pros and cons of existing frame-level and boundary-level evaluation metrics. Through extensive experiments, we find OTAS is superior to the previous state-of-the-art method by $41\\%$ on average in terms of our recommended F1 score. Surprisingly, OTAS even outperforms the ground-truth human annotations in the user study. Moreover, OTAS is efficient enough to allow real-time inference.","url_abs":"https://arxiv.org/abs/2309.06276v1","url_pdf":"https://arxiv.org/pdf/2309.06276v1.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":"otas-unsupervised-boundary-detection-for","repo_url":"https://github.com/yl596/otas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.06276","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}