{"id":"https://openalex.org/W3133431537","doi":"https://doi.org/10.1109/tmm.2021.3060291","title":"Cross-Modal Semantic Matching Generative Adversarial Networks for Text-to-Image Synthesis","display_name":"Cross-Modal Semantic Matching Generative Adversarial Networks for Text-to-Image Synthesis","publication_year":2021,"publication_date":"2021-02-20","ids":{"openalex":"https://openalex.org/W3133431537","doi":"https://doi.org/10.1109/tmm.2021.3060291","mag":"3133431537"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3060291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3060291","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":true,"oa_status":"green","oa_url":"https://digitalcommons.lsu.edu/eecs_pubs/670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072487632","display_name":"Hongchen Tan","orcid":"https://orcid.org/0000-0001-6915-8736"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongchen Tan","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6915-8736","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645085","display_name":"Xiuping Liu","orcid":"https://orcid.org/0000-0003-1712-6083"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuping Liu","raw_affiliation_strings":["School of Mathematical Sciences, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1712-6083","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020527092","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Department of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0144-9489"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["School of Electrical Engineering & Computer Science, and Center for Computation & Technology, Louisiana State University, Baton Rouge, LA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0144-9489","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering & Computer Science, and Center for Computation & Technology, Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":2.6877,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.91018639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"832","last_page":"845"},"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":0.9984999895095825,"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":0.9984999895095825,"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":0.9937000274658203,"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":0.9918000102043152,"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":0.8365732431411743},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5769951939582825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621645450592041},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5353584289550781},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5351492166519165},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.532585620880127},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5068309903144836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5011749267578125},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4790881276130676},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4476251006126404},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4393933117389679},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43677476048469543},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43658146262168884},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.4174618721008301},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39861994981765747},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3837421238422394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365732431411743},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5769951939582825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621645450592041},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5353584289550781},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5351492166519165},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.532585620880127},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5068309903144836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5011749267578125},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4790881276130676},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4476251006126404},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4393933117389679},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43677476048469543},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43658146262168884},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.4174618721008301},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39861994981765747},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3837421238422394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tmm.2021.3060291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3060291","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"},{"id":"pmh:oai:digitalcommons.lsu.edu:eecs_pubs-1669","is_oa":true,"landing_page_url":"https://digitalcommons.lsu.edu/eecs_pubs/670","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-1669","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/670","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.lsu.edu:eecs_pubs-1669","is_oa":true,"landing_page_url":"https://digitalcommons.lsu.edu/eecs_pubs/670","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4439180760","display_name":"RII Track-1: Louisiana Materials Design Alliance (LAMDA)","funder_award_id":"1946231","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7449973229","display_name":null,"funder_award_id":"2018AAA0102003","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G7734861170","display_name":null,"funder_award_id":"61976040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7744321187","display_name":null,"funder_award_id":"U19B2039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1775434803","https://openalex.org/W1797268635","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2125389028","https://openalex.org/W2131774270","https://openalex.org/W2133665775","https://openalex.org/W2138621090","https://openalex.org/W2170240176","https://openalex.org/W2183341477","https://openalex.org/W2250999640","https://openalex.org/W2251427843","https://openalex.org/W2405756170","https://openalex.org/W2566832195","https://openalex.org/W2593768305","https://openalex.org/W2605135824","https://openalex.org/W2605195953","https://openalex.org/W2609296554","https://openalex.org/W2613904329","https://openalex.org/W2804371177","https://openalex.org/W2883311563","https://openalex.org/W2907077346","https://openalex.org/W2925992867","https://openalex.org/W2931831966","https://openalex.org/W2950404765","https://openalex.org/W2950776302","https://openalex.org/W2951359136","https://openalex.org/W2951559648","https://openalex.org/W2962845008","https://openalex.org/W2962849838","https://openalex.org/W2963163163","https://openalex.org/W2963184176","https://openalex.org/W2963373786","https://openalex.org/W2963413689","https://openalex.org/W2963466847","https://openalex.org/W2963467339","https://openalex.org/W2963656735","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964046515","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W3201409833","https://openalex.org/W4288642060","https://openalex.org/W4294170691","https://openalex.org/W4295274059","https://openalex.org/W4295521014","https://openalex.org/W4300838842","https://openalex.org/W4320013936","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6640598943","https://openalex.org/W6682691769","https://openalex.org/W6685053522","https://openalex.org/W6685160515","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6728889164","https://openalex.org/W6729482032","https://openalex.org/W6735013348","https://openalex.org/W6751404249","https://openalex.org/W6755102824","https://openalex.org/W6765779288"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W4394780863","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"Synthesizing":[0],"photo-realistic":[1],"images":[2],"based":[3],"on":[4,148],"text":[5,31,60,103],"descriptions":[6],"is":[7,88],"a":[8,44,66],"challenging":[9],"image":[10,35,64,99],"generation":[11],"problem.":[12],"Although":[13],"many":[14],"recent":[15],"approaches":[16],"have":[17],"significantly":[18],"advanced":[19],"the":[20,30,56,92,95,118,123,154],"performance":[21],"of":[22,94,97,113,125,156],"text-to-image":[23,68],"generation,":[24],"to":[25,54,136],"guarantee":[26],"semantic":[27,57,108,119],"matchings":[28],"between":[29,59],"description":[32,61,104],"and":[33,62,81,100,121,138],"synthesized":[34,63,98],"remains":[36],"very":[37],"challenging.":[38],"In":[39,127],"this":[40],"paper,":[41],"we":[42,129],"propose":[43],"new":[45,71],"model,":[46],"Cross-modal":[47],"Semantic":[48,83],"Matching":[49,84],"Generative":[50],"Adversarial":[51],"Networks":[52,134],"(CSM-GAN),":[53],"improve":[55],"consistency":[58,120],"for":[65],"fine-grained":[67],"generation.":[69],"Two":[70],"modules":[72],"are":[73],"proposed":[74],"in":[75,106,143],"CSM-GAN:":[76],"Text":[77,131],"Encoder":[78],"Module":[79,85],"(TEM)":[80],"Textual-Visual":[82],"(TVSMM).":[86],"TVSMM":[87],"aimed":[89],"at":[90],"making":[91],"distance":[93],"pairs":[96],"its":[101],"corresponding":[102],"closer,":[105],"global":[107],"embedding":[109],"space,":[110],"than":[111],"those":[112],"mismatched":[114],"pairs.":[115],"This":[116],"improves":[117],"consequently,":[122],"generalizability":[124],"CSM-GAN.":[126],"TEM,":[128],"introduce":[130],"Convolutional":[132],"Neural":[133],"(Text_CNNs)":[135],"capture":[137],"highlight":[139],"local":[140],"visual":[141],"features":[142],"textual":[144],"descriptions.":[145],"Thorough":[146],"experiments":[147],"two":[149],"public":[150],"benchmark":[151],"datasets":[152],"demonstrated":[153],"superiority":[155],"CSM-GAN":[157],"over":[158],"other":[159],"representative":[160],"state-of-the-art":[161],"methods.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}