{"id":"https://openalex.org/W4413017466","doi":"https://doi.org/10.1109/tcsvt.2025.3596325","title":"Unsupervised Action Segmentation via Multi-Scale Temporal-Interaction Enhancement","display_name":"Unsupervised Action Segmentation via Multi-Scale Temporal-Interaction Enhancement","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4413017466","doi":"https://doi.org/10.1109/tcsvt.2025.3596325"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3596325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3596325","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103002365","display_name":"Zhiying Song","orcid":"https://orcid.org/0000-0003-3786-653X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiying Song","raw_affiliation_strings":["Qiushi Academy for Advanced Studies and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Qiushi Academy for Advanced Studies, and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632847","display_name":"Kaixuan Chen","orcid":"https://orcid.org/0000-0002-2492-5230"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Chen","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049532103","display_name":"Pengfei Wang","orcid":"https://orcid.org/0000-0001-7251-7349"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wang","raw_affiliation_strings":["School of Software Technology, the College of Computer Science and Technology, and the Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","the College of Computer Science and Technology, and the Qiushi Academy for Advanced Studies, School of Software Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, the College of Computer Science and Technology, and the Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"the College of Computer Science and Technology, and the Qiushi Academy for Advanced Studies, School of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040143894","display_name":"Nenggan Zheng","orcid":"https://orcid.org/0000-0002-0211-8817"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenggan Zheng","raw_affiliation_strings":["Qiushi Academy for Advanced Studies and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Qiushi Academy for Advanced Studies and the College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103002365"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1810797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"1","first_page":"747","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9832000136375427,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9811000227928162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6423454880714417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5838015079498291},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5771823525428772},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4799128472805023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4782073497772217},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46501782536506653},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4100798964500427},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3394811153411865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6423454880714417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838015079498291},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5771823525428772},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4799128472805023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4782073497772217},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46501782536506653},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4100798964500427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3394811153411865},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3596325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3596325","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G805608925","display_name":null,"funder_award_id":"LZ24F020003","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8628682313","display_name":null,"funder_award_id":"T2293723","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1898340191","https://openalex.org/W2099614498","https://openalex.org/W2105101328","https://openalex.org/W2109698606","https://openalex.org/W2151617679","https://openalex.org/W2799087757","https://openalex.org/W2887412014","https://openalex.org/W2896457183","https://openalex.org/W2951866553","https://openalex.org/W2962795934","https://openalex.org/W2963524571","https://openalex.org/W2963853051","https://openalex.org/W2982335217","https://openalex.org/W2982673782","https://openalex.org/W3009622574","https://openalex.org/W3021013305","https://openalex.org/W3035557275","https://openalex.org/W3115964123","https://openalex.org/W3174587031","https://openalex.org/W3174700686","https://openalex.org/W3180945712","https://openalex.org/W3208431284","https://openalex.org/W3211316995","https://openalex.org/W4200633745","https://openalex.org/W4214612132","https://openalex.org/W4290098626","https://openalex.org/W4292963524","https://openalex.org/W4312322722","https://openalex.org/W4312626235","https://openalex.org/W4313165677","https://openalex.org/W4313291202","https://openalex.org/W4379927854","https://openalex.org/W4380303514","https://openalex.org/W4385245566","https://openalex.org/W4385800691","https://openalex.org/W4386076624","https://openalex.org/W4386522183","https://openalex.org/W4387917672","https://openalex.org/W4390872435","https://openalex.org/W4390873751","https://openalex.org/W4393148541","https://openalex.org/W4394593032","https://openalex.org/W4394597446","https://openalex.org/W4399880811","https://openalex.org/W4402125445","https://openalex.org/W4402670135","https://openalex.org/W4402753974","https://openalex.org/W4402780112","https://openalex.org/W4406727986","https://openalex.org/W4409366633"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Unsupervised":[0],"action":[1,7,34,62,148],"segmentation":[2,27],"(UAS)":[3],"aims":[4,134],"to":[5,29,86,111,135,162,172],"identify":[6,147],"boundaries":[8],"in":[9,54,203],"long,":[10],"untrimmed":[11],"videos":[12],"without":[13],"the":[14,39,43,50,88,93,116,164,174],"use":[15],"of":[16,38,45],"annotations.":[17],"This":[18],"involves":[19],"learning":[20],"discriminative":[21],"frame":[22,57,84],"features":[23],"and":[24,60,83,159,167,184,197,205,211],"applying":[25],"a":[26,55,71,105,122,129,169],"mechanism":[28,171],"organize":[30],"frames":[31],"into":[32],"coherent":[33],"segments.":[35],"However,":[36],"most":[37],"common":[40],"approaches":[41],"ignore":[42],"importance":[44],"multi-scale":[46,77],"temporal":[47,78,107],"interactions":[48,79],"within":[49],"video":[51],"sequence,":[52],"resulting":[53],"limited":[56,94],"representation":[58,95],"capability":[59],"inaccurate":[61],"boundary":[63],"detection.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,97,120,150],"propose":[69],"MulSclTE,":[70],"novel":[72],"UAS":[73],"framework":[74],"that":[75,133,187],"incorporates":[76],"across":[80,115,194],"global,":[81],"clip,":[82],"levels":[85],"enhance":[87],"overall":[89],"performance.":[90],"To":[91,145],"address":[92],"capability,":[96],"first":[98],"present":[99,168],"global-level":[100],"interaction":[101,131],"enhancement":[102],"by":[103,154],"implementing":[104],"bi-directional":[106],"encoding":[108],"mechanism,":[109],"designed":[110],"capture":[112],"comprehensive":[113,152],"information":[114,153],"entire":[117],"sequence.":[118],"Then,":[119],"devise":[121],"hierarchical":[123],"self-supervised":[124],"loss":[125],"function":[126],"equipped":[127],"with":[128],"clip-level":[130],"constraint":[132],"bring":[136],"temporally":[137],"adjacent":[138],"clips":[139],"closer":[140],"while":[141],"separating":[142],"non-adjacent":[143],"ones.":[144],"precisely":[146],"boundaries,":[149],"provide":[151],"integrating":[155],"frame-level":[156],"prediction":[157],"errors":[158],"similarity":[160],"scores":[161],"alleviate":[163],"under-segmentation":[165],"issue,":[166],"refinement":[170],"mitigate":[173],"over-segmentation":[175],"issue.":[176],"Extensive":[177],"experiments":[178],"on":[179],"Breakfast,":[180],"YouTube":[181],"Instructions,":[182],"50Salads,":[183],"EPIC-KITCHENS":[185],"show":[186],"MulSclTE":[188],"attains":[189],"leading":[190],"or":[191],"second-best":[192],"performance":[193],"all":[195],"datasets,":[196],"even":[198],"exceeds":[199],"some":[200],"supervised":[201],"methods":[202],"MoF":[204],"F1":[206],"metrics,":[207],"underscoring":[208],"its":[209],"robustness":[210],"effectiveness.":[212]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}