{"id":"https://openalex.org/W4408353743","doi":"https://doi.org/10.1109/icassp49660.2025.10887693","title":"Cluster-Refined Optimal Transport for Unsupervised Action Segmentation","display_name":"Cluster-Refined Optimal Transport for Unsupervised Action Segmentation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353743","doi":"https://doi.org/10.1109/icassp49660.2025.10887693"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100374850","display_name":"Shijie Wang","orcid":"https://orcid.org/0000-0002-7990-4883"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijie Wang","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102010367","display_name":"Jinrong Zhang","orcid":"https://orcid.org/0009-0003-4765-7392"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinrong Zhang","raw_affiliation_strings":["Dalian University of Technology,School of Control Science and Engineering,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Control Science and Engineering,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100315247","display_name":"Yule Liu","orcid":"https://orcid.org/0009-0005-4921-4610"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yule Liu","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062680766","display_name":"Shiyao Li","orcid":"https://orcid.org/0000-0002-8053-7005"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyao Li","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108616881","display_name":"Lin Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Feng","raw_affiliation_strings":["Dalian University of Technology,School of Innovation and Entrepreneurship,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Innovation and Entrepreneurship,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100374850"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04229688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9962000250816345,"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":0.9803000092506409,"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/computer-science","display_name":"Computer science","score":0.696499228477478},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6107740998268127},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5631822943687439},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5096151828765869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4921655058860779},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4182784855365753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3421236574649811},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11384746432304382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696499228477478},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6107740998268127},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5631822943687439},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5096151828765869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921655058860779},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4182784855365753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3421236574649811},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11384746432304382},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1836533770","https://openalex.org/W2109698606","https://openalex.org/W2314362175","https://openalex.org/W2417433140","https://openalex.org/W2550143307","https://openalex.org/W2798991696","https://openalex.org/W2962795934","https://openalex.org/W2962916463","https://openalex.org/W2963853051","https://openalex.org/W2982673782","https://openalex.org/W3009622574","https://openalex.org/W3082556740","https://openalex.org/W3083550439","https://openalex.org/W3168371806","https://openalex.org/W3174700686","https://openalex.org/W3174889475","https://openalex.org/W3203752493","https://openalex.org/W3204980132","https://openalex.org/W4312322722","https://openalex.org/W4313165677","https://openalex.org/W4313829323","https://openalex.org/W4385800691","https://openalex.org/W4390872435","https://openalex.org/W4394593032","https://openalex.org/W4402753974","https://openalex.org/W4411245031","https://openalex.org/W6631190155"],"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":{"Action":[0],"segmentation":[1,91],"in":[2,14,88],"untrimmed":[3],"videos":[4],"is":[5],"essential":[6],"for":[7,48],"comprehensive":[8],"video":[9,56],"understanding.":[10],"Despite":[11],"significant":[12],"progress":[13],"unsupervised":[15,49],"methods,":[16],"capturing":[17],"both":[18],"long-range":[19,61],"dependencies":[20,62],"and":[21,45,63,103],"short-duration":[22,75],"actions":[23,76],"simultaneously":[24],"remains":[25],"a":[26],"challenging":[27],"task.":[28],"To":[29],"address":[30],"this":[31,33],"challenge,":[32],"paper":[34],"introduces":[35],"the":[36,85,89],"Cluster-Refined":[37],"Optimal":[38],"Transport":[39],"(CROT)":[40],"method,":[41],"combining":[42],"hierarchical":[43],"clustering":[44],"optimal":[46,72],"transport":[47],"action":[50],"segmentation.":[51],"We":[52],"first":[53],"hierarchically":[54],"cluster":[55],"frame":[57],"representations":[58],"to":[59],"capture":[60],"generate":[64],"pseudo-boundaries.":[65],"Initial":[66],"pseudo-labels":[67,81],"are":[68,77,82],"then":[69],"obtained":[70],"via":[71],"transport,":[73],"ensuring":[74],"recognized.":[78],"Finally,":[79],"these":[80],"refined":[83],"using":[84],"pseudo-boundaries,":[86],"resulting":[87],"final":[90],"output.":[92],"Extensive":[93],"experiments":[94],"on":[95,110],"three":[96],"public":[97],"datasets,":[98],"i.e.,":[99],"YouTube":[100],"Instructions,":[101],"Breakfast,":[102],"50Salads,":[104],"demonstrate":[105],"that":[106],"our":[107],"method":[108],"performs":[109],"par":[111],"with":[112],"or":[113],"better":[114],"than":[115],"previous":[116],"approaches.":[117]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}