{"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/efficient-two-step-networks-for-temporal","title":"Efficient Two-Step Networks for Temporal Action Segmentation","arxiv_id":null,"date":"2021-04-30","proceeding":"Neurocomputing 2021 4","authors":["Yunheng Li","Zhuben Dong","Kaiyuan Liu","Lin Feng","Lianyu Hu","Jie Zhu","Li Xu","YuHan Wang","Shenglan Liu"],"abstract":"Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging. To address these problems, we present the Efficient Two-Step Network (ETSN) with two components. The first step of ETSN is Efficient Temporal Series Pyramid Networks (ETSPNet) that capture both local and global frame-level features and provide accurate predictions of segmentation boundaries. The second step is a novel unsupervised approach called Local Burr Suppression (LBS), which significantly reduces the over-segmentation errors. Our empirical evaluations on the benchmarks including 50Salads, GTEA and Breakfast dataset demonstrate that ETSN outperforms the current state-of-the-art methods by a large margin.","url_abs":"https://www.sciencedirect.com/science/article/pii/S0925231221006998","url_pdf":"https://www.sciencedirect.com/science/article/pii/S0925231221006998","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":"efficient-two-step-networks-for-temporal","repo_url":"https://github.com/lyhisme/ETSN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"ETSN","rank_in_archive_order":16,"of":28,"metrics":{"Acc":"82.0","Edit":"78.8","F1@10%":"85.2","F1@25%":"83.9","F1@50%":"75.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"ETSN","rank_in_archive_order":19,"of":37,"metrics":{"Acc":"67.8","Average F1":"66.4","Edit":"70.3","F1@10%":"74.0","F1@25%":"69.0","F1@50%":"56.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"ETSN","rank_in_archive_order":14,"of":28,"metrics":{"Acc":"78.2","Edit":"86.2","F1@10%":"91.1","F1@25%":"90.0","F1@50%":"77.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}