{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/refining-action-segmentation-with","title":"Refining Action Segmentation With Hierarchical Video Representations","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Hyemin Ahn","Dongheui Lee"],"abstract":"    In this paper, we propose Hierarchical Action Segmentation Refiner (HASR), which can refine temporal action segmentation results from various models by understanding the overall context of a given video in a hierarchical way. When a backbone model for action segmentation estimates how the given video can be segmented, our model extracts segment-level representations based on frame-level features, and extracts a video-level representation based on the segment-level representations. Based on these hierarchical representations, our model can refer to the overall context of the entire video, and predict how the segment labels that are out of context should be corrected. Our HASR can be plugged into various action segmentation models (MS-TCN, SSTDA, ASRF), and improve the performance of state-of-the-art models based on three challenging datasets (GTEA, 50Salads, and Breakfast). For example, in 50Salads dataset, the segmental edit score improves from 67.9% to 77.4% (MS-TCN), from 75.8% to 77.3% (SSTDA), from 79.3% to 81.0% (ASRF). In addition, our model can refine the segmentation result from the unseen backbone model, which was not referred to when training HASR. This generalization performance would make HASR be an effective tool for boosting up the existing approaches for temporal action segmentation. Our code is available at https://github.com/cotton-ahn/HASR_iccv2021.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Ahn_Refining_Action_Segmentation_With_Hierarchical_Video_Representations_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Ahn_Refining_Action_Segmentation_With_Hierarchical_Video_Representations_ICCV_2021_paper.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":"refining-action-segmentation-with","repo_url":"https://github.com/cotton-ahn/hasr_iccv2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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"}],"methods":[{"method_slug":"sstda","method_name":"SSTDA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"ASRF + HASR","rank_in_archive_order":13,"of":28,"metrics":{"Acc":"83.9","Edit":"81.0","F1@10%":"86.6","F1@25%":"85.7","F1@50%":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"ASRF + HASR","rank_in_archive_order":15,"of":37,"metrics":{"Acc":"69.4","Average F1":"67.1","Edit":"71.9","F1@10%":"74.7","F1@25%":"69.5","F1@50%":"57.0"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"SSTDA + HASR","rank_in_archive_order":17,"of":28,"metrics":{"Acc":"78.7","Edit":"87.5","F1@10%":"90.9","F1@25%":"88.6","F1@50%":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"ASRF + HASR","rank_in_archive_order":21,"of":28,"metrics":{"Acc":"76.9","Edit":"84.5","F1@10%":"89.2","F1@25%":"87.2","F1@50%":"74.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"cotton-ahn/hasr_iccv2021","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["Ahn_Refining_Action_Segmentation_With_Hierarchical_Video_Representations_ICCV_2021_paper"],"harvested_for_calls":[]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"64bbcab99055cf98cd4e80d681d75f0f05b67341988edcd4a8e01839f99254f4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}