{"id":"https://openalex.org/W4377715513","doi":"https://doi.org/10.1109/tmm.2023.3278992","title":"Semantic Distance Adversarial Learning for Text-to-Image Synthesis","display_name":"Semantic Distance Adversarial Learning for Text-to-Image Synthesis","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4377715513","doi":"https://doi.org/10.1109/tmm.2023.3278992"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3278992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3278992","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/A5100740413","display_name":"Bowen Yuan","orcid":"https://orcid.org/0000-0002-8051-3070"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Yuan","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102726137","display_name":"Yefei Sheng","orcid":"https://orcid.org/0000-0002-2547-4646"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefei Sheng","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"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":"Bing-Kun Bao","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728316","display_name":"Yi\u2010Ping Phoebe Chen","orcid":"https://orcid.org/0000-0002-4122-3767"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi-Ping Phoebe Chen","raw_affiliation_strings":["La Trobe University, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"La Trobe University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I196829312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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":"Changsheng Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China","Peng Cheng Laboratory, Shenzhen, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100740413"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":1.324,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82474631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"1255","last_page":"1266"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.8075608611106873},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7014375329017639},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6968819499015808},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5964438915252686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5938016176223755},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5638480186462402},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5570275187492371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4496973156929016},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4189731478691101},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41835829615592957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3885144889354706},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33676183223724365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11348313093185425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075608611106873},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7014375329017639},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6968819499015808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5964438915252686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938016176223755},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5638480186462402},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5570275187492371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4496973156929016},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4189731478691101},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41835829615592957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3885144889354706},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33676183223724365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11348313093185425},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3278992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3278992","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":0.6299999952316284,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4317995357","display_name":null,"funder_award_id":"61936005","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":66,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2183341477","https://openalex.org/W2739107216","https://openalex.org/W2745461083","https://openalex.org/W2890718122","https://openalex.org/W2896457183","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963444790","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2982450728","https://openalex.org/W2987809065","https://openalex.org/W3006538026","https://openalex.org/W3013575054","https://openalex.org/W3034633089","https://openalex.org/W3034667500","https://openalex.org/W3035500781","https://openalex.org/W3091653824","https://openalex.org/W3119951344","https://openalex.org/W3127393268","https://openalex.org/W3138516171","https://openalex.org/W3141117710","https://openalex.org/W3174525637","https://openalex.org/W3195003693","https://openalex.org/W3215495615","https://openalex.org/W4205219932","https://openalex.org/W4214485011","https://openalex.org/W4224035735","https://openalex.org/W4224281861","https://openalex.org/W4226374411","https://openalex.org/W4281485151","https://openalex.org/W4308246614","https://openalex.org/W4312388283","https://openalex.org/W4312438583","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4387195417","https://openalex.org/W4388854249","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6728889164","https://openalex.org/W6748733227","https://openalex.org/W6755007375","https://openalex.org/W6765779288","https://openalex.org/W6767384525","https://openalex.org/W6774314701","https://openalex.org/W6775218022","https://openalex.org/W6778883912","https://openalex.org/W6779543726","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6796242362","https://openalex.org/W6798194901","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6846118689"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4323929292"],"abstract_inverted_index":{"Text-to-Image":[0,107],"(T2I)":[1],"synthesis":[2,108],"is":[3,54],"a":[4,9,16,99,189],"cross-modality":[5],"task":[6],"that":[7,220],"requires":[8],"text":[10,29,66,71,127,141,175],"description":[11],"as":[12],"input":[13],"to":[14,130,169,206],"generate":[15],"realistic":[17],"and":[18,34,64,87,125,182,216],"semantically":[19],"consistent":[20],"image.":[21],"To":[22,94],"guarantee":[23],"semantic":[24,60,111,164,171],"consistency,":[25],"previous":[26],"studies":[27],"regenerate":[28],"descriptions":[30],"from":[31,74,90,113],"synthetic":[32],"images":[33],"align":[35],"them":[36],"with":[37,188,203],"the":[38,42,69,79,122,126,135,154,199,221,225],"given":[39,65],"descriptions.":[40],"However,":[41],"existing":[43],"redescription":[44,128,148],"modules":[45],"lack":[46],"explicit":[47],"modeling":[48],"of":[49,59,81,137,149,156],"their":[50],"training":[51,75,201],"objectives,":[52],"which":[53,109],"crucial":[55],"for":[56,106],"reliable":[57],"measurement":[58],"distance":[61,101,165],"between":[62,121,173],"redescriptions":[63,72],"inputs.":[67],"Consequently,":[68],"aligned":[70],"suffer":[73],"bias":[76],"caused":[77],"by":[78],"emergence":[80],"adversarial":[82,119,157],"image":[83,123,139,150,158,177],"samples,":[84],"unseen":[85,180],"semantics,":[86],"mistaken":[88,183],"contents":[89,184],"low-quality":[91],"synthesized":[92],"images.":[93],"this":[95],"end,":[96],"we":[97],"propose":[98],"SEMantic":[100],"Adversarial":[102],"learning":[103,120,144],"(SEMA)":[104],"framework":[105],"strengthens":[110],"consistency":[112],"two":[114],"aspects:":[115],"1)":[116],"We":[117,161],"introduce":[118,162],"generator":[124],"module":[129],"mutually":[131],"promote":[132],"or":[133,140,176],"demote":[134],"quality":[136],"generated":[138],"instances.":[142],"This":[143],"model":[145,200,223],"ensures":[146],"accurate":[147],"contents,":[151],"thus":[152],"diminishing":[153],"generation":[155],"samples.":[159],"2)":[160],"two-fold":[163],"discrimination":[166,195],"(SEM":[167],"distance)":[168],"characterize":[170],"relevance":[172],"matching":[174],"pairs.":[178],"The":[179,193],"semantics":[181],"will":[185],"be":[186],"penalized":[187],"large":[190],"SEM":[191],"distance.":[192],"proposed":[194,222],"method":[196],"also":[197],"simplifies":[198],"process":[202],"no":[204],"need":[205],"optimize":[207],"multiple":[208],"discriminators.":[209],"Experimental":[210],"results":[211],"on":[212],"CUB":[213],"Birds":[214],"200":[215],"MS-COCO":[217],"datasets":[218],"show":[219],"outperforms":[224],"state-of-the-art":[226],"methods.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}