{"id":"https://openalex.org/W4409366633","doi":"https://doi.org/10.1609/aaai.v39i7.32751","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","display_name":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409366633","doi":"https://doi.org/10.1609/aaai.v39i7.32751"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i7.32751","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32751","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32751/34906","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32751/34906","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115638343","display_name":"Federico Spurio","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Federico Spurio","raw_affiliation_strings":["University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026496713","display_name":"Emad Bahrami","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emad Bahrami","raw_affiliation_strings":["University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016401744","display_name":"Gianpiero Francesca","orcid":"https://orcid.org/0000-0001-6066-9345"},"institutions":[{"id":"https://openalex.org/I1293612202","display_name":"Toyota Motor Corporation (Switzerland)","ror":"https://ror.org/05p0pbv75","country_code":"CH","type":"company","lineage":["https://openalex.org/I1293612202","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gianpiero Francesca","raw_affiliation_strings":["Toyota Motor Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Europe","institution_ids":["https://openalex.org/I1293612202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012240246","display_name":"J\u00fcergen Gall","orcid":"https://orcid.org/0000-0002-9447-3399"},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juergen Gall","raw_affiliation_strings":["University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn\nLamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I283854653"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"7","first_page":"6996","last_page":"7005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6899430751800537},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6253464818000793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116805672645569},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5195565223693848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4680834412574768}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6899430751800537},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6253464818000793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116805672645569},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5195565223693848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4680834412574768}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i7.32751","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32751","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32751/34906","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i7.32751","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i7.32751","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32751/34906","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G655814273","display_name":null,"funder_award_id":"GA 1927/4-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409366633.pdf","grobid_xml":"https://content.openalex.org/works/W4409366633.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0],"this":[1,39,57,113],"work,":[2],"we":[3,59,115],"address":[4,56],"unsupervised":[5,127],"temporal":[6,49,128],"action":[7,129],"segmentation,":[8],"which":[9],"segments":[10,20,50],"a":[11,35,61,80,91,117],"set":[12],"of":[13,51,71,101,109,151,156],"long,":[14],"untrimmed":[15],"videos":[16],"into":[17],"semantically":[18],"meaningful":[19],"that":[21,69,95],"are":[22],"consistent":[23],"across":[24],"videos.":[25],"While":[26],"recent":[27],"approaches":[28],"combine":[29],"representation":[30],"learning":[31],"and":[32,143,160],"clustering":[33,82],"in":[34,79,154],"single":[36],"step":[37],"for":[38,126],"task,":[40],"they":[41],"do":[42],"not":[43],"cope":[44],"with":[45],"large":[46],"variations":[47,89],"within":[48,90],"the":[52,84,88,99,107,110,122,149,152],"same":[53],"class.":[54],"To":[55,112],"limitation,":[58],"propose":[60],"novel":[62],"method,":[63],"termed":[64],"Hierarchical":[65],"Vector":[66],"Quantization":[67],"(HVQ),":[68],"consists":[70],"two":[72],"subsequent":[73],"vector":[74],"quantization":[75],"modules.":[76],"This":[77],"results":[78],"hierarchical":[81],"where":[83],"additional":[85],"subclusters":[86],"cover":[87],"cluster.":[92],"We":[93,131],"demonstrate":[94],"our":[96,133],"approach":[97,134,147],"captures":[98],"distribution":[100],"segment":[102],"lengths":[103],"much":[104],"better":[105],"than":[106],"state":[108,150],"art.":[111],"end,":[114],"introduce":[116],"new":[118],"metric":[119],"based":[120],"on":[121,135],"Jensen-Shannon":[123],"Distance":[124],"(JSD)":[125],"segmentation.":[130],"evaluate":[132],"three":[136],"public":[137],"datasets,":[138],"namely":[139],"Breakfast,":[140],"YouTube":[141],"Instructional":[142],"IKEA":[144],"ASM.":[145],"Our":[146],"outperforms":[148],"art":[153],"terms":[155],"F1":[157],"score,":[158],"recall":[159],"JSD.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}