{"id":"https://openalex.org/W3208722310","doi":"https://doi.org/10.1145/3474085.3475391","title":"Multi-caption Text-to-Face Synthesis: Dataset and Algorithm","display_name":"Multi-caption Text-to-Face Synthesis: Dataset and Algorithm","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3208722310","doi":"https://doi.org/10.1145/3474085.3475391","mag":"3208722310"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5101539774","display_name":"Jianxin Sun","orcid":"https://orcid.org/0000-0003-4632-4783"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianxin Sun","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108616991","display_name":"Qi Li","orcid":"https://orcid.org/0000-0002-7905-2860"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683352","display_name":"Weining Wang","orcid":"https://orcid.org/0000-0001-7299-6431"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Wang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, NLPR, CASIA, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, NLPR, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061636756","display_name":"Jian Zhao","orcid":"https://orcid.org/0000-0002-0619-7866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Zhao","raw_affiliation_strings":["Institute of North Electronic Equipment, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of North Electronic Equipment, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055505703","display_name":"Zhenan Sun","orcid":"https://orcid.org/0000-0003-4029-9935"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, NLPR, CASIA & School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101539774"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.2005,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9343114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2290","last_page":"2298"},"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":0.9991999864578247,"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":0.9991999864578247,"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/T11448","display_name":"Face recognition and analysis","score":0.9986000061035156,"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":0.9968000054359436,"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":0.8626822233200073},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.7044169306755066},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6631033420562744},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6502417325973511},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6132290959358215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6023366451263428},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5853351950645447},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5317610502243042},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45644810795783997},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4268611669540405},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41863030195236206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41429033875465393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626822233200073},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7044169306755066},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6631033420562744},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6502417325973511},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6132290959358215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6023366451263428},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5853351950645447},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5317610502243042},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45644810795783997},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4268611669540405},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41863030195236206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41429033875465393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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:10.1145/3474085.3475391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1797268635","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W2131774270","https://openalex.org/W2165542474","https://openalex.org/W2295130376","https://openalex.org/W2502312327","https://openalex.org/W2533598788","https://openalex.org/W2550553598","https://openalex.org/W2593390416","https://openalex.org/W2603777577","https://openalex.org/W2753407461","https://openalex.org/W2794317666","https://openalex.org/W2798807671","https://openalex.org/W2956018683","https://openalex.org/W2962760235","https://openalex.org/W2962770929","https://openalex.org/W2963163163","https://openalex.org/W2963460857","https://openalex.org/W2963626105","https://openalex.org/W2963767194","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964121744","https://openalex.org/W2964149283","https://openalex.org/W2964261768","https://openalex.org/W2966792645","https://openalex.org/W2970127127","https://openalex.org/W2986670728","https://openalex.org/W2990269423","https://openalex.org/W2994303421","https://openalex.org/W3023742835","https://openalex.org/W3033996551","https://openalex.org/W3034521057","https://openalex.org/W3034667500","https://openalex.org/W3035080866","https://openalex.org/W3035316078","https://openalex.org/W3035500781","https://openalex.org/W3035574324","https://openalex.org/W3093363913","https://openalex.org/W3106333289","https://openalex.org/W3174171554","https://openalex.org/W3174194560"],"related_works":["https://openalex.org/W2125145484","https://openalex.org/W2993300079","https://openalex.org/W159132833","https://openalex.org/W4312046383","https://openalex.org/W4310034804","https://openalex.org/W2335882425","https://openalex.org/W2773616286","https://openalex.org/W2620816324","https://openalex.org/W4375864588","https://openalex.org/W2949267551"],"abstract_inverted_index":{"Text-to-Face":[0],"synthesis":[1],"with":[2,150],"multiple":[3,35,77],"captions":[4,36,59],"is":[5,73,87,121,147],"still":[6],"an":[7,65,88,94],"important":[8],"yet":[9],"less":[10],"addressed":[11],"problem":[12],"because":[13],"of":[14,17,58,158],"the":[15,61,99,156],"lack":[16],"effective":[18],"algorithms":[19],"and":[20,29,80],"large-scale":[21,139],"datasets.":[22],"We":[23],"accordingly":[24],"propose":[25],"a":[26,47,138],"Semantic":[27],"Embedding":[28],"Attention":[30,69],"(SEA-T2F)":[31],"network":[32,100],"that":[33],"allows":[34],"as":[37],"input":[38],"to":[39,75,97,101,117,124,130],"generate":[40,102],"highly":[41],"semantically":[42],"related":[43],"face":[44,133],"images.":[45,134],"With":[46],"novel":[48],"Sentence":[49],"Features":[50],"Injection":[51],"Module,":[52],"SEA-T2F":[53],"can":[54],"integrate":[55],"any":[56],"number":[57],"into":[60],"network.":[62],"In":[63],"addition,":[64],"attention":[66],"mechanism":[67],"named":[68,141],"for":[70,107],"Multiple":[71],"Captions":[72],"proposed":[74],"fuse":[76],"word":[78],"features":[79],"synthesize":[81,131],"fine-grained":[82],"details.":[83],"Considering":[84],"text-to-face":[85,108],"generation":[86],"ill-posed":[89],"problem,":[90],"we":[91,136],"also":[92],"introduce":[93],"attribute":[95,118],"loss":[96],"guide":[98],"sentence-related":[103],"attributes.":[104],"Existing":[105],"datasets":[106],"are":[109],"either":[110],"too":[111],"small":[112],"or":[113],"roughly":[114],"generated":[115],"according":[116],"labels,":[119],"which":[120,144],"not":[122],"enough":[123],"train":[125],"deep":[126],"learning":[127],"based":[128],"methods":[129],"natural":[132],"Therefore,":[135],"build":[137],"dataset":[140],"CelebAText-HQ,":[142],"in":[143],"each":[145],"image":[146],"manually":[148],"annotated":[149],"10":[151],"captions.":[152],"Extensive":[153],"experiments":[154],"demonstrate":[155],"effectiveness":[157],"our":[159],"algorithm.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}