{"id":"https://openalex.org/W4392903044","doi":"https://doi.org/10.1109/icassp48485.2024.10448207","title":"Language-Free Compositional Action Generation via Decoupling Refinement","display_name":"Language-Free Compositional Action Generation via Decoupling Refinement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903044","doi":"https://doi.org/10.1109/icassp48485.2024.10448207"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100441085","display_name":"Xiao Liu","orcid":"https://orcid.org/0000-0002-8073-0534"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","Eindhoven University of Technology, NL","Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Eindhoven University of Technology, NL","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088257057","display_name":"Guangyi Chen","orcid":"https://orcid.org/0000-0001-7542-5378"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Guangyi Chen","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926293","display_name":"Yansong Tang","orcid":"https://orcid.org/0000-0002-1534-4549"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Tang","raw_affiliation_strings":["Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110927580","display_name":"Guangrun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangrun Wang","raw_affiliation_strings":["University of Oxford,UK","University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363146","display_name":"Xiao\u2013Ping Zhang","orcid":"https://orcid.org/0000-0001-5241-0069"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Ping Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113969216","display_name":"Ser-Nam Lim","orcid":"https://orcid.org/0000-0001-9525-0288"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ser-Nam Lim","raw_affiliation_strings":["University of Central Florida,USA","University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"2910","last_page":"2914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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":0.8007528781890869},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7538844347000122},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7373253107070923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577954053878784},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5488000512123108},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49368414282798767},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48126715421676636},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4696713387966156},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4351212680339813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4073953330516815},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4030192792415619},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3851117491722107},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35193705558776855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007528781890869},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7538844347000122},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7373253107070923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577954053878784},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5488000512123108},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49368414282798767},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48126715421676636},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4696713387966156},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4351212680339813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4073953330516815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4030192792415619},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3851117491722107},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35193705558776855},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/icassp48485.2024.10448207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6505763180","display_name":null,"funder_award_id":"EP/W002981/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1967554269","https://openalex.org/W2188365844","https://openalex.org/W2897682634","https://openalex.org/W2908510526","https://openalex.org/W2963090522","https://openalex.org/W2963305465","https://openalex.org/W2971856312","https://openalex.org/W2987025184","https://openalex.org/W2992308087","https://openalex.org/W2999455429","https://openalex.org/W3015233197","https://openalex.org/W3034514130","https://openalex.org/W3103720336","https://openalex.org/W3129576130","https://openalex.org/W3153832461","https://openalex.org/W3166396011","https://openalex.org/W3206084531","https://openalex.org/W3207932648","https://openalex.org/W4224035735","https://openalex.org/W4288079574","https://openalex.org/W4295312788","https://openalex.org/W4307084265","https://openalex.org/W4312244484","https://openalex.org/W4313145975","https://openalex.org/W4313156423","https://openalex.org/W4320013936","https://openalex.org/W4390872247","https://openalex.org/W6610566761","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6758720093","https://openalex.org/W6766978945","https://openalex.org/W6785773631","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6803075331","https://openalex.org/W6803302148","https://openalex.org/W6803870738","https://openalex.org/W6809885388"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Composing":[0],"simple":[1],"actions":[2,5,38],"into":[3],"complex":[4],"is":[6,23,71],"crucial":[7],"yet":[8],"challenging.":[9],"Existing":[10],"methods":[11],"largely":[12],"rely":[13],"on":[14],"language":[15,40],"annotations":[16],"to":[17,35,61,73,86,96,124],"discern":[18],"composable":[19],"latent":[20],"semantics,":[21],"which":[22],"costly":[24],"and":[25,53,92,105,115,119],"labor-intensive.":[26],"In":[27],"this":[28],"study,":[29],"we":[30,108],"introduce":[31],"a":[32,66,81],"novel":[33],"framework":[34],"generate":[36,62],"compositional":[37,93,106],"without":[39],"auxiliaries.":[41],"Our":[42],"approach":[43],"consists":[44],"of":[45,99],"three":[46],"components:":[47],"Action":[48,51,56],"Coupling,":[49],"Conditional":[50],"Generation,":[52],"Decoupling":[54,78],"Refinement.":[55],"Coupling":[57],"integrates":[58],"two":[59,110],"sub-actions":[60,91,104],"pseudo-training":[63],"examples.":[64],"Then,":[65],"conditional":[67],"generative":[68],"model,":[69],"CVAE":[70],"employed":[72],"facilitate":[74],"the":[75,97],"diverse":[76],"generation.":[77],"Refinement":[79],"leverages":[80],"self-supervised":[82],"pre-trained":[83],"model":[84],"MAE":[85],"ensure":[87],"semantic":[88],"consistency":[89],"between":[90],"actions.":[94],"Due":[95],"lack":[98],"existing":[100],"datasets":[101],"containing":[102],"both":[103],"actions,":[107],"create":[109],"new":[111],"datasets,":[112],"named":[113],"HumanAct-C":[114],"UESTC-C.":[116],"Both":[117],"qualitative":[118],"quantitative":[120],"assessments":[121],"are":[122],"conducted":[123],"show":[125],"our":[126],"efficacy.":[127],"<sup":[128],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}