{"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/weakly-supervised-dense-action-anticipation","title":"Weakly-Supervised Dense Action Anticipation","arxiv_id":"2111.07593","date":"2021-11-15","proceeding":null,"authors":["Haotong Zhang","Fuhai Chen","Angela Yao"],"abstract":"Dense anticipation aims to forecast future actions and their durations for long horizons. Existing approaches rely on fully-labelled data, i.e. sequences labelled with all future actions and their durations. We present a (semi-) weakly supervised method using only a small number of fully-labelled sequences and predominantly sequences in which only the (one) upcoming action is labelled. To this end, we propose a framework that generates pseudo-labels for future actions and their durations and adaptively refines them through a refinement module. Given only the upcoming action label as input, these pseudo-labels guide action/duration prediction for the future. We further design an attention mechanism to predict context-aware durations. Experiments on the Breakfast and 50Salads benchmarks verify our method's effectiveness; we are competitive even when compared to fully supervised state-of-the-art models. We will make our code available at: https://github.com/zhanghaotong1/WSLVideoDenseAnticipation.","url_abs":"https://arxiv.org/abs/2111.07593v1","url_pdf":"https://arxiv.org/pdf/2111.07593v1.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":"weakly-supervised-dense-action-anticipation","repo_url":"https://github.com/zhanghaotong1/wslvideodenseanticipation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.07593","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}