{"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/boundary-aware-cascade-networks-for-temporal","title":"Boundary-Aware Cascade Networks for Temporal Action Segmentation","arxiv_id":null,"date":"2020-08-01","proceeding":"ECCV 2020 8","authors":["Zhenzhi Wang","Ziteng Gao","Li-Min Wang","Zhifeng Li","Gangshan Wu"],"abstract":"Identifying human action segments in an untrimmed video is still challenging due to boundary ambiguity and over-segmentation issues. To address these problems, we present a new boundary-aware cascade network by introducing two novel components. First, we devise a new cascading paradigm, called Stage Cascade, to enable our model to have adaptive receptive fields and more confident predictions for ambiguous frames. Second, we design a general and principled smoothing operation, termed as local barrier pooling, to aggregate local predictions by leveraging semantic boundary information. Moreover, these two components can be jointly fine-tuned in an end-to-end manner. We perform experiments on three challenging datasets: 50Salads, GTEA and Breakfast dataset, demonstrating that our framework significantly out-performs the current state-of-the-art methods. The code is available at https://github.com/MCG-NJU/BCN.","url_abs":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/4845_ECCV_2020_paper.php","url_pdf":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123700035.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":"boundary-aware-cascade-networks-for-temporal","repo_url":"https://github.com/MCG-NJU/BCN","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":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"BCN","rank_in_archive_order":17,"of":28,"metrics":{"Acc":"84.4","Edit":"74.3","F1@10%":"82.3","F1@25%":"81.3","F1@50%":"74"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"BCN","rank_in_archive_order":23,"of":37,"metrics":{"Acc":"70.4","Average F1":"63.1","Edit":"66.2","F1@10%":"68.7","F1@25%":"65.5","F1@50%":"55.0"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"BCN","rank_in_archive_order":16,"of":28,"metrics":{"Acc":"79.8","Edit":"84.4","F1@10%":"88.5","F1@25%":"87.1","F1@50%":"77.3"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}