{"id":"https://openalex.org/W7115932494","doi":"https://doi.org/10.1109/tcsvt.2025.3645812","title":"Customized Multi-Subject Text-to-Image Generation With Causal Tuning","display_name":"Customized Multi-Subject Text-to-Image Generation With Causal Tuning","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W7115932494","doi":"https://doi.org/10.1109/tcsvt.2025.3645812"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3645812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3645812","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":null,"display_name":"Chaoyang Li","orcid":"https://orcid.org/0009-0001-3614-9371"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-3614-9371","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I158809036","https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"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":"Xin Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"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":"Wenwu Zhu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lingzhi Wang","orcid":"https://orcid.org/0000-0002-1346-2437"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingzhi Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1346-2437","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I158809036","https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Hu","orcid":"https://orcid.org/0000-0002-8355-0969"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Hu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8355-0969","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qing Liao","orcid":"https://orcid.org/0000-0003-1012-5301"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Liao","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1012-5301","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I158809036","https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51341949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"7020","last_page":"7034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9398999810218811,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9398999810218811,"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":0.0142000000923872,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6870999932289124},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.647599995136261},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5562000274658203},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.35989999771118164},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.34459999203681946},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.3425000011920929},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3337000012397766},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3262999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565000057220459},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.647599995136261},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3645812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3645812","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/G3009425511","display_name":null,"funder_award_id":"PCL2024A05","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6396121924","display_name":null,"funder_award_id":"62227808","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Subject-driven":[0],"text-to-image":[1,74,171],"generation":[2,75,167,172],"aims":[3],"to":[4,35,119,147],"generate":[5],"customized":[6,72,185],"high-fidelity":[7],"images":[8],"based":[9],"on":[10],"text":[11],"descriptions":[12],"for":[13,99,183],"specific":[14],"subjects,":[15],"which":[16,90],"has":[17,165],"gained":[18],"increasing":[19],"attention.":[20],"Despite":[21],"recent":[22],"advancements":[23],"in":[24,37,169],"single-subject":[25],"customization,":[26],"existing":[27,174],"methods":[28,176],"often":[29],"struggle":[30],"with":[31,77,133],"multi-subject":[32,73,186],"scenarios,":[33],"leading":[34],"distortions":[36],"subject":[38,51,132],"identity.":[39],"This":[40],"challenge":[41],"arises":[42],"because":[43],"entangled":[44],"identity-relevant":[45,135],"and":[46,53,96,104,156,177,181],"irrelevant":[47,97],"information":[48,98],"can":[49,56,91],"obscure":[50],"identities,":[52],"inter-subject":[54],"interference":[55,121],"cause":[57],"confusion":[58],"or":[59],"loss":[60],"of":[61,130],"individual":[62],"identities.":[63],"To":[64],"address":[65],"these":[66],"issues,":[67],"we":[68,81,110,139],"propose":[69,82],"CausalT2I,":[70],"a":[71,83,105,112,141],"framework":[76],"causal":[78,87,102,106],"tuning.":[79],"First,":[80],"<italic":[84,113,142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[85,114,143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">subject-aware":[86],"disentanglement</i>":[88],"method,":[89],"self-adaptively":[92],"distinguish":[93],"causally":[94],"relevant":[95],"subjects":[100,124],"through":[101],"intervention":[103],"disentangled":[107],"objective.":[108],"Then,":[109],"design":[111],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">soft":[115],"cross-attention":[116],"guidance</i>":[117],"strategy":[118],"mitigate":[120],"among":[122],"different":[123],"by":[125],"aligning":[126],"the":[127,149],"textual":[128,154],"attributes":[129],"each":[131],"its":[134],"visual":[136,158],"attributes.":[137],"Last,":[138],"introduce":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">causal":[144],"denoising":[145,150],"objective</i>":[146],"optimize":[148],"process":[151],"using":[152],"identity-preserved":[153],"embeddings":[155],"identity-irrelevant":[157],"embeddings.":[159],"Extensive":[160],"experiments":[161],"show":[162],"that":[163],"CausalT2I":[164],"superior":[166],"ability":[168],"subject-driven":[170],"over":[173],"baseline":[175],"brings":[178],"more":[179],"flexibility":[180],"controllability":[182],"generating":[184],"images.":[187]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2025-12-19T00:00:00"}
