{"id":"https://openalex.org/W4406613007","doi":"https://doi.org/10.1109/smc54092.2024.10831828","title":"MVESF: Multi-View Enhanced Semantic Fusion for Controllable Text-to-Image Generation","display_name":"MVESF: Multi-View Enhanced Semantic Fusion for Controllable Text-to-Image Generation","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406613007","doi":"https://doi.org/10.1109/smc54092.2024.10831828"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100457336","display_name":"Hai Zhang","orcid":"https://orcid.org/0000-0002-5930-1882"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hai Zhang","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027627793","display_name":"Guitao Cao","orcid":"https://orcid.org/0000-0002-4059-4806"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guitao Cao","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592526","display_name":"Xinke Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinke Wang","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114128176","display_name":"Jiahao Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Quan","raw_affiliation_strings":["East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Key Laboratory of Trustworthy Computing,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100457336"],"corresponding_institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26958721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1610","last_page":"1617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9740999937057495,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9740999937057495,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9678000211715698,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9653000235557556,"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":0.7331773042678833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5738264918327332},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5560886263847351},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5172194242477417},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4896448254585266},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4100264012813568},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4076997637748718},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09635072946548462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331773042678833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738264918327332},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5560886263847351},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5172194242477417},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4896448254585266},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4100264012813568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4076997637748718},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09635072946548462},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6159160774","display_name":null,"funder_award_id":"61871186,61771322","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2896134062","https://openalex.org/W2962845008","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W3141117710","https://openalex.org/W3174525637","https://openalex.org/W4214485011","https://openalex.org/W4297630623","https://openalex.org/W4312388283","https://openalex.org/W4312438583","https://openalex.org/W4312977351","https://openalex.org/W6640362995","https://openalex.org/W6713645886","https://openalex.org/W6767384525","https://openalex.org/W6790978476","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6842690664"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272"],"abstract_inverted_index":{"Text-to-image(T2I)":[0],"synthesis":[1],"aims":[2],"to":[3,21,37,40,93],"generate":[4],"semantically":[5],"consistent":[6,115],"images":[7,70,101,128],"with":[8,33],"texts.":[9],"Currently,":[10],"existing":[11],"methods":[12],"merely":[13],"use":[14],"the":[15,19,64,95,114,126,133,145],"shallow":[16],"semantics":[17,32],"of":[18,67,98,147],"text":[20,45,68,99,118,135],"crudely":[22],"guide":[23],"image":[24,34,42,103,105,108],"generation.":[25],"They":[26],"cannot":[27],"fully":[28],"integrate":[29],"rich":[30],"textual":[31],"features,":[35],"leading":[36],"an":[38],"inability":[39],"control":[41],"generation":[43],"through":[44],"finely.":[46],"To":[47],"address":[48],"this":[49],"issue,":[50],"we":[51,81],"propose":[52],"a":[53],"GAN-based":[54],"method":[55,112],"named":[56],"MVESF":[57],"(Multi-View":[58],"Enhanced":[59],"Semantic":[60,84,87],"Fusion),":[61],"which":[62],"enhances":[63],"semantic":[65,96],"fusion":[66,97],"and":[69,89,100,107,119],"from":[71],"multiple":[72],"perspectives":[73],"for":[74,122],"fine-grained":[75,123],"controllable":[76],"text-to-image":[77],"synthesis.":[78],"In":[79],"multi-view,":[80],"introduce":[82],"Multi-domain":[83],"Guidance,":[85],"Local":[86],"Attention,":[88],"Visual-textual":[90],"Consistency":[91],"Loss":[92],"enhance":[94],"in":[102,125,132],"generation,":[104],"discrimination,":[106],"supervision,":[109],"respectively.":[110],"Our":[111],"promotes":[113],"alignment":[116],"between":[117],"images,":[120],"allowing":[121],"variations":[124],"generated":[127],"when":[129],"subtle":[130],"changes":[131],"input":[134],"without":[136],"affecting":[137],"unrelated":[138],"regions.":[139],"Extensive":[140],"experimental":[141],"results":[142],"have":[143],"demonstrated":[144],"effectiveness":[146],"our":[148],"approach.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}