{"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/hierarchical-vector-quantization-for","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","arxiv_id":"2412.17640","date":"2024-12-23","proceeding":null,"authors":["Federico Spurio","Emad Bahrami","Gianpiero Francesca","Juergen Gall"],"abstract":"In this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos. While recent approaches combine representation learning and clustering in a single step for this task, they do not cope with large variations within temporal segments of the same class. To address this limitation, we propose a novel method, termed Hierarchical Vector Quantization (HVQ), that consists of two subsequent vector quantization modules. This results in a hierarchical clustering where the additional subclusters cover the variations within a cluster. We demonstrate that our approach captures the distribution of segment lengths much better than the state of the art. To this end, we introduce a new metric based on the Jensen-Shannon Distance (JSD) for unsupervised temporal action segmentation. We evaluate our approach on three public datasets, namely Breakfast, YouTube Instructional and IKEA ASM. Our approach outperforms the state of the art in terms of F1 score, recall and JSD.","url_abs":"https://arxiv.org/abs/2412.17640v2","url_pdf":"https://arxiv.org/pdf/2412.17640v2.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":"hierarchical-vector-quantization-for","repo_url":"https://github.com/fedespu/hvq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"},{"task_slug":"unsupervised-action-segmentation","task_name":"Unsupervised Action Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-action-segmentation-on-breakfast","task":"Unsupervised Action Segmentation","dataset":"Breakfast","model":"HVQ","rank_in_archive_order":1,"of":8,"metrics":{"Acc":"54.4","F1":"39.7","JSD":"82.5","Precision":"35.6","Recall":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-action-segmentation-on-ikea-asm","task":"Unsupervised Action Segmentation","dataset":"IKEA ASM","model":"HVQ","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"51.2","F1":"30.7","JSD":"64.8","Precision":"37.7","Recall":"25.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-action-segmentation-on-youtube","task":"Unsupervised Action Segmentation","dataset":"Youtube INRIA Instructional","model":"HVQ","rank_in_archive_order":3,"of":8,"metrics":{"Acc":"50.3","F1":"35.1","Precision":"32.1","Recall":"38.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.17640","atlas_url":"https://app.syntology.ai/?focus=2412.17640","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2412.17640"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.17640\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.17640"},"call":"get_concepts_for_paper(arxiv_id=\"2412.17640\")"}],"by_repo":[{"repo":"fedespu/hvq","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"6c9d5a45f9eeca86a6752c77667b61a00843660765e64aa9637e3c27451b0145","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}