{"id":"https://openalex.org/W4408355767","doi":"https://doi.org/10.1109/icassp49660.2025.10888688","title":"Attention Disentanglement for Semantic Diffusion Modeling in Text-to-Image Generation","display_name":"Attention Disentanglement for Semantic Diffusion Modeling in Text-to-Image Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355767","doi":"https://doi.org/10.1109/icassp49660.2025.10888688"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888688","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":"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/A5101469059","display_name":"Hongliang Yu","orcid":"https://orcid.org/0000-0002-4097-186X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiang-Chun Yu","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112791692","display_name":"J. C. W. Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tsung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8069999814033508,"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/T10799","display_name":"Data Visualization and Analytics","score":0.7529000043869019,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183013558387756},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5554797053337097},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5196117758750916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4102243483066559},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40688684582710266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38410595059394836},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07847142219543457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183013558387756},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5554797053337097},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5196117758750916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4102243483066559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40688684582710266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38410595059394836},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07847142219543457},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888688","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":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2952122856","https://openalex.org/W2998462233","https://openalex.org/W4220758154","https://openalex.org/W4285152678","https://openalex.org/W4312933868","https://openalex.org/W4375868971","https://openalex.org/W4385270985","https://openalex.org/W4385488739","https://openalex.org/W4385823060","https://openalex.org/W4386075490","https://openalex.org/W4390874566","https://openalex.org/W4392903108","https://openalex.org/W4396982391","https://openalex.org/W4400905918","https://openalex.org/W4402111238","https://openalex.org/W4402111729","https://openalex.org/W4402753884","https://openalex.org/W4408354606","https://openalex.org/W6752051073","https://openalex.org/W6767996718","https://openalex.org/W6779459370","https://openalex.org/W6779823529","https://openalex.org/W6786267757","https://openalex.org/W6786375611","https://openalex.org/W6790494085","https://openalex.org/W6790978476","https://openalex.org/W6795288823","https://openalex.org/W6802517614","https://openalex.org/W6810940779","https://openalex.org/W6811013733","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6847405979","https://openalex.org/W6853612337","https://openalex.org/W6853693339"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2386796262","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-to-image":[0],"model":[1,94],"has":[2],"been":[3],"recently":[4],"improved":[5],"to":[6,78,97,101,135],"generate":[7],"the":[8,26,34,43,58,68,80,87,104,111,118,125,137,144,149,153],"semantically":[9],"rich":[10],"high-quality":[11],"images":[12,106,151],"by":[13],"strengthening":[14],"natural":[15],"language":[16],"processing":[17],"via":[18],"transformer":[19],"in":[20,31,40,45,71,152],"a":[21,92],"stable":[22,72],"diffusion":[23,56,123],"process.":[24],"However,":[25],"challenges":[27],"are":[28,107,133],"still":[29],"remained":[30],"accurately":[32],"rendering":[33],"objects,":[35],"colors":[36],"and":[37,39,130,140,146],"compositions,":[38],"precisely":[41],"resolving":[42],"ambiguities":[44],"textual":[46],"descriptions.":[47],"This":[48,114],"paper":[49],"presents":[50,117],"an":[51],"attention":[52,119],"disentanglment":[53],"for":[54,63,89,121],"semantic":[55,59,81,122,138],"where":[57,124],"consistency":[60],"is":[61,76,95],"enhanced":[62],"text-to-image":[64],"generation.":[65],"By":[66],"utilizing":[67],"cross-attention":[69],"maps":[70],"diffusion,":[73],"this":[74,99],"method":[75],"feasible":[77],"control":[79],"features":[82],"during":[83],"generation":[84],"process":[85,100],"without":[86],"need":[88],"retraining.":[90],"Additionally,":[91],"vision-language":[93],"merged":[96],"implement":[98],"ensure":[102],"that":[103],"generated":[105,150],"closely":[108],"aligned":[109],"with":[110],"input":[112],"prompts.":[113],"study":[115],"further":[116],"disentanglement":[120],"schemes":[126],"of":[127,148],"syntax":[128],"parsing":[129],"information-theoretic":[131],"learning":[132],"implemented":[134],"separate":[136],"attributes":[139],"relations,":[141],"thereby":[142],"improving":[143],"accuracy":[145],"coherence":[147],"experiments.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}