{"id":"https://openalex.org/W3006538026","doi":"https://doi.org/10.1109/tmm.2020.2972856","title":"Exploring Global and Local Linguistic Representations for Text-to-Image Synthesis","display_name":"Exploring Global and Local Linguistic Representations for Text-to-Image Synthesis","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W3006538026","doi":"https://doi.org/10.1109/tmm.2020.2972856","mag":"3006538026"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.2972856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2972856","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/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["School of Computer Science, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3543-6272","affiliations":[{"raw_affiliation_string":"School of Computer Science, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678974","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0002-6423-3167"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6423-3167","affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4798-4233","affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643936","display_name":"Guangwei Zhang","orcid":"https://orcid.org/0000-0003-3164-9921"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Zhang","raw_affiliation_strings":["Institute of Network Technology, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Network Technology, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0002-6423-3167"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["School of Computer Science, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6423-3167","affiliations":[{"raw_affiliation_string":"School of Computer Science, and the Engineering Research Center of Information Networks, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1325,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93117657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"12","first_page":"3075","last_page":"3087"},"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":0.9955000281333923,"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":0.9955000281333923,"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":0.9649999737739563,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.957099974155426,"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":0.787865400314331},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6757869720458984},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6243737936019897},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5966523289680481},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5881986021995544},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.53874671459198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.535693883895874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220010876655579},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.49315398931503296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4582468867301941},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45391327142715454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3397181034088135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787865400314331},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6757869720458984},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6243737936019897},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5966523289680481},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5881986021995544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.53874671459198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.535693883895874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220010876655579},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49315398931503296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4582468867301941},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45391327142715454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3397181034088135},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2020.2972856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2972856","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","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1150046362","display_name":null,"funder_award_id":"61802026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2044554324","display_name":null,"funder_award_id":"61906018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7470181681","display_name":null,"funder_award_id":"B08004","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1522301498","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2041288440","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2131774270","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2405756170","https://openalex.org/W2530372461","https://openalex.org/W2548275288","https://openalex.org/W2605195953","https://openalex.org/W2687693326","https://openalex.org/W2727849499","https://openalex.org/W2733548594","https://openalex.org/W2747853580","https://openalex.org/W2754689878","https://openalex.org/W2785678896","https://openalex.org/W2787579267","https://openalex.org/W2808663243","https://openalex.org/W2893749619","https://openalex.org/W2923549568","https://openalex.org/W2941765879","https://openalex.org/W2943885184","https://openalex.org/W2946675767","https://openalex.org/W2950776302","https://openalex.org/W2951523806","https://openalex.org/W2952716587","https://openalex.org/W2962754210","https://openalex.org/W2962775818","https://openalex.org/W2962845008","https://openalex.org/W2962879692","https://openalex.org/W2963163163","https://openalex.org/W2963184176","https://openalex.org/W2963281729","https://openalex.org/W2963373786","https://openalex.org/W2963413689","https://openalex.org/W2963684088","https://openalex.org/W2963836885","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2964201867","https://openalex.org/W2964216930","https://openalex.org/W2964219393","https://openalex.org/W2965289598","https://openalex.org/W3037695135","https://openalex.org/W4295274059","https://openalex.org/W4295521014","https://openalex.org/W4300838842","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6631190155","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6728889164","https://openalex.org/W6729482032","https://openalex.org/W6732249622","https://openalex.org/W6735913928","https://openalex.org/W6736155344","https://openalex.org/W6740327194","https://openalex.org/W6743496644","https://openalex.org/W6748582592","https://openalex.org/W6748655329","https://openalex.org/W6755312952","https://openalex.org/W6765631605","https://openalex.org/W6779669310","https://openalex.org/W6779841522"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750"],"abstract_inverted_index":{"The":[0,182],"task":[1,17],"of":[2,33,59,72,200],"text-to-image":[3,201],"synthesis":[4],"is":[5],"to":[6,28,111,119,162],"generate":[7],"photographic":[8],"images":[9,49,115,124],"conditioned":[10,50],"on":[11,40,51,67,172],"given":[12],"textual":[13],"descriptions.":[14],"This":[15],"challenging":[16],"has":[18],"recently":[19],"attracted":[20],"considerable":[21],"attention":[22],"from":[23],"the":[24,34,52,57,60,76,97,102,113,122,127,131,135,140,149,158,169,177,180,198],"multimedia":[25],"community":[26],"due":[27],"its":[29],"potential":[30],"applications.":[31],"Most":[32],"up-to-date":[35],"approaches":[36],"are":[37],"built":[38],"based":[39],"generative":[41,91],"adversarial":[42,92],"network":[43],"(GAN)":[44],"models,":[45],"and":[46,69,87,116,145,151,179],"they":[47],"synthesize":[48,112],"global":[53,61,86,150],"linguistic":[54,89,99,153,190],"representation.":[55],"However,":[56],"sparsity":[58],"representation":[62,100],"results":[63],"in":[64,75],"training":[65],"difficulties":[66],"GANs":[68],"a":[70,109,117],"shortage":[71],"fine-grained":[73,188],"information":[74,191],"generated":[77,123],"images.":[78,207],"To":[79],"address":[80],"this":[81],"problem,":[82],"we":[83,107,133],"propose":[84],"cross-modal":[85,136,193],"local":[88,98,152,189],"representations-based":[90],"networks":[93],"(CGL-GAN)":[94],"by":[95,138],"incorporating":[96,187],"into":[101],"GAN.":[103],"In":[104,130],"our":[105,164],"CGL-GAN,":[106],"construct":[108,134],"generator":[110],"target":[114],"discriminator":[118],"judge":[120],"whether":[121],"conform":[125],"with":[126,192],"text":[128],"description.":[129],"discriminator,":[132],"correlation":[137,194],"projecting":[139],"image":[141],"representations":[142],"at":[143],"high":[144],"low":[146],"levels":[147],"onto":[148],"representations,":[154],"respectively.":[155],"We":[156,167],"design":[157],"hinge":[159],"loss":[160],"function":[161],"train":[163],"CGL-GAN":[165,171],"model.":[166],"evaluate":[168],"proposed":[170],"two":[173],"publicly":[174],"available":[175],"datasets,":[176],"CUB":[178],"MS-COCO.":[181],"extensive":[183],"experiments":[184],"demonstrate":[185],"that":[186],"can":[195],"greatly":[196],"improve":[197],"performance":[199],"synthesis,":[202],"even":[203],"when":[204],"generating":[205],"high-resolution":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}