{"id":"https://openalex.org/W4365421094","doi":"https://doi.org/10.1109/tmm.2023.3266607","title":"Recurrent Affine Transformation for Text-to-Image Synthesis","display_name":"Recurrent Affine Transformation for Text-to-Image Synthesis","publication_year":2023,"publication_date":"2023-04-12","ids":{"openalex":"https://openalex.org/W4365421094","doi":"https://doi.org/10.1109/tmm.2023.3266607"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3266607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3266607","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":"https://openalex.org/A5035849886","display_name":"Senmao Ye","orcid":"https://orcid.org/0000-0002-1978-3805"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senmao Ye","raw_affiliation_strings":["School of Software Engineering, South China University of Technolody, Guangzhou, China","School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1978-3805","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technolody, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331980","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0001-6951-901X"},"institutions":[{"id":"https://openalex.org/I4210101880","display_name":"Institute of Scientific and Technical Information","ror":"https://ror.org/0170b6c09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210101880","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Wang","raw_affiliation_strings":["Industrial Technology Research Center, Guangdong Institute of Scientific &amp; Technical Information, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Center, Guangdong Institute of Scientific &amp; Technical Information, Guangzhou, China","institution_ids":["https://openalex.org/I4210101880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":"https://orcid.org/0000-0001-8856-756X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["School of Software Engineering, South China University of Technolody, Guangzhou, China","School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8856-756X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technolody, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394589","display_name":"Fei Liu","orcid":"https://orcid.org/0000-0001-9415-0496"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Liu","raw_affiliation_strings":["School of Software Engineering, South China University of Technolody, Guangzhou, China","School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9415-0496","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technolody, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5016,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97039701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"462","last_page":"473"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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":0.9876999855041504,"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/discriminator","display_name":"Discriminator","score":0.739367663860321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733654797077179},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7263090014457703},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7002490162849426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086615681648254},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4911310374736786},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4764973521232605},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.47473272681236267},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4717465341091156},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47124940156936646},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45629218220710754},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4395419955253601},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4369141161441803},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36190393567085266},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3393931984901428},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.21003073453903198},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15583446621894836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15472465753555298}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.739367663860321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733654797077179},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7263090014457703},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7002490162849426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086615681648254},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4911310374736786},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4764973521232605},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.47473272681236267},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4717465341091156},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47124940156936646},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45629218220710754},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4395419955253601},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4369141161441803},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36190393567085266},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3393931984901428},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.21003073453903198},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15583446621894836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15472465753555298},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3266607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3266607","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2203038425","display_name":null,"funder_award_id":"U1901222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6926612094","display_name":"\u9762\u5411\u5168\u7ec6\u80de\u6a21\u578b\u7684\u591a\u5f62\u5f0f\u5efa\u6a21\u4e0e\u4eff\u771f\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61873094","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":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2125389028","https://openalex.org/W2298992465","https://openalex.org/W2533598788","https://openalex.org/W2887272576","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2965289598","https://openalex.org/W2965364151","https://openalex.org/W2966543375","https://openalex.org/W2966792645","https://openalex.org/W2987761193","https://openalex.org/W2997109336","https://openalex.org/W3003301247","https://openalex.org/W3133431537","https://openalex.org/W3141117710","https://openalex.org/W3159521921","https://openalex.org/W3199535391","https://openalex.org/W3203312420","https://openalex.org/W4214485011","https://openalex.org/W4226055713","https://openalex.org/W4292828873","https://openalex.org/W4303633609","https://openalex.org/W6600609147","https://openalex.org/W6639118987","https://openalex.org/W6678815747","https://openalex.org/W6679434410","https://openalex.org/W6683074461","https://openalex.org/W6684821475","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6728889164","https://openalex.org/W6729110096","https://openalex.org/W6755312952","https://openalex.org/W6765779288","https://openalex.org/W6781951827"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4321441197","https://openalex.org/W4281618574","https://openalex.org/W4308217387","https://openalex.org/W2970620799","https://openalex.org/W2946818007"],"abstract_inverted_index":{"Text-to-image":[0],"synthesis":[1],"aims":[2],"to":[3,36,111,137,142,167,171,193],"generate":[4],"realistic":[5],"images":[6,76],"conditioned":[7,77],"on":[8,78,179,200],"text":[9,13,79,165],"descriptions.":[10],"To":[11,58,99],"fuse":[12],"information":[14],"into":[15],"synthesized":[16],"images,":[17],"conditional":[18,24,29,119,147],"affine":[19,71],"transformations":[20],"(CATs),":[21],"such":[22],"as":[23],"batch":[25,38,49],"normalization":[26,31],"(CBN)":[27],"and":[28,123,183],"instance":[30],"(CIN),":[32],"are":[33],"usually":[34],"used":[35],"predict":[37],"statistics":[39,50],"of":[40,103,131],"different":[41],"layers.":[42,57],"However,":[43],"ordinary":[44],"CAT":[45,85,97],"blocks":[46,86],"control":[47],"the":[48,53,60,84,93,101,129,160,164,169,180,187],"independently":[51],"disregarding":[52],"consistency":[54,95],"among":[55],"neighboring":[56],"address":[59],"above":[61],"issue,":[62],"we":[63,105,151],"propose":[64,106,152],"a":[65,107,139,153],"new":[66],"fusion":[67],"approach":[68],"names":[69],"recurrent":[70,88],"transformation":[72],"(RAT)":[73],"for":[74,90,159],"synthesizing":[75],"information.":[80,120,148],"RAT":[81,132],"connects":[82],"all":[83],"with":[87],"connections":[89],"explicitly":[91],"fitting":[92],"temporal":[94],"between":[96],"blocks.":[98],"verify":[100],"effectiveness":[102,130],"RAT,":[104],"novel":[108],"visualization":[109],"method":[110],"show":[112],"how":[113,144],"generative":[114],"adversarial":[115],"network":[116],"(GAN)":[117],"fuses":[118,146],"Our":[121,196],"microscopic":[122],"macroscopic":[124],"visualizations":[125],"not":[126],"only":[127],"demonstrate":[128,186],"but":[133],"also":[134],"turn":[135],"out":[136],"be":[138],"useful":[140],"perspective":[141],"analyze":[143],"GAN":[145],"In":[149],"addition,":[150],"more":[154,173],"stable":[155],"spatial":[156],"attention":[157],"mechanism":[158],"discriminator,":[161],"which":[162],"helps":[163],"description":[166],"supervise":[168],"generator":[170],"synthesize":[172],"relevant":[174],"image":[175],"contents.":[176],"Extensive":[177],"experiments":[178],"CUB,":[181],"Oxford-102,":[182],"COCO":[184],"datasets":[185],"proposed":[188],"model's":[189],"superiority":[190],"in":[191],"comparison":[192],"state-of-the-art":[194],"models.":[195],"code":[197],"is":[198],"available":[199],"<uri":[201],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[202],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/senmaoy/RAT-GAN</uri>":[203],".":[204]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
