{"id":"https://openalex.org/W4393260012","doi":"https://doi.org/10.1145/3650033","title":"ISF-GAN: Imagine, Select, and Fuse with GPT-Based Text Enrichment for Text-to-Image Synthesis","display_name":"ISF-GAN: Imagine, Select, and Fuse with GPT-Based Text Enrichment for Text-to-Image Synthesis","publication_year":2024,"publication_date":"2024-03-28","ids":{"openalex":"https://openalex.org/W4393260012","doi":"https://doi.org/10.1145/3650033"},"language":"en","primary_location":{"id":"doi:10.1145/3650033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650033","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650033","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2547-4646","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"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":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4662-7170","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440133","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-8662-9488"},"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":"Jie Wang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8662-9488","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao*","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.9984,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.732255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"20","issue":"7","first_page":"1","last_page":"17"},"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":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9939000010490417,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9793999791145325,"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/fuse","display_name":"Fuse (electrical)","score":0.8836207985877991},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5761118531227112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5622429251670837},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37451252341270447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3309180736541748},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13409143686294556},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13086646795272827}],"concepts":[{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.8836207985877991},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5761118531227112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5622429251670837},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37451252341270447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3309180736541748},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13409143686294556},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13086646795272827}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650033","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3650033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650033","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G1837166742","display_name":null,"funder_award_id":"62325206, 61936005, 62206132","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"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393260012.pdf","grobid_xml":"https://content.openalex.org/works/W4393260012.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2183341477","https://openalex.org/W2525579820","https://openalex.org/W2609130030","https://openalex.org/W2610748790","https://openalex.org/W2751304263","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963373786","https://openalex.org/W2963515894","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2970562079","https://openalex.org/W2972328244","https://openalex.org/W2978223337","https://openalex.org/W2987809065","https://openalex.org/W3006538026","https://openalex.org/W3048484056","https://openalex.org/W3127393268","https://openalex.org/W3159521921","https://openalex.org/W3174807077","https://openalex.org/W3212436340","https://openalex.org/W3216180229","https://openalex.org/W3216237230","https://openalex.org/W4200498145","https://openalex.org/W4205219932","https://openalex.org/W4221157644","https://openalex.org/W4224035735","https://openalex.org/W4247924304","https://openalex.org/W4249502209","https://openalex.org/W4255556797","https://openalex.org/W4288043238","https://openalex.org/W4292941885","https://openalex.org/W4298417552","https://openalex.org/W4300628203","https://openalex.org/W4300838842","https://openalex.org/W4301206121","https://openalex.org/W4302441680","https://openalex.org/W4312933868","https://openalex.org/W4320008790","https://openalex.org/W4361271773","https://openalex.org/W4366668471","https://openalex.org/W4377715513","https://openalex.org/W6718379498","https://openalex.org/W6767384525","https://openalex.org/W6797179183"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Text-to-Image":[0],"synthesis":[1],"aims":[2],"to":[3,24,38,43,61,75,96,118,144,177,185],"generate":[4,25,186],"an":[5],"accurate":[6],"and":[7,78,91,93,109,130,137,171,195,201],"semantically":[8,26,187],"consistent":[9,188],"image":[10,65,152],"from":[11,29,54],"a":[12,30,72,106,115,140,173],"given":[13],"text":[14,42,53,107,121,135,165,183],"description.":[15],"However,":[16],"it":[17],"is":[18,208],"difficult":[19],"for":[20,80,167],"existing":[21],"generative":[22],"methods":[23],"complete":[27],"images":[28],"single":[31],"piece":[32],"of":[33,50,181,203],"text.":[34],"Some":[35],"works":[36],"try":[37],"expand":[39],"the":[40,51,55,98,102,120,124,128,151,163,179,199,204],"input":[41,52,164],"multiple":[44],"captions":[45],"via":[46],"retrieving":[47],"similar":[48],"descriptions":[49,136],"training":[56],"set":[57],"but":[58],"still":[59],"fail":[60],"fill":[62],"in":[63],"missing":[64,169],"semantics.":[66],"In":[67,157],"this":[68],"article,":[69],"we":[70],"propose":[71],"GAN-based":[73],"approach":[74],"Imagine,":[76],"Select,":[77],"Fuse":[79,94,131],"Text-to-image":[81],"synthesis,":[82],"named":[83],"ISF-GAN.":[84],"The":[85],"proposed":[86,160,205],"ISF-GAN":[87],"contains":[88],"Imagine":[89,103],"Stage":[90,95,104,132],"Select":[92,129],"solve":[97],"above":[99],"problems.":[100],"First,":[101],"proposes":[105],"completion":[108],"enrichment":[110],"module.":[111],"This":[112],"module":[113],"guides":[114],"GPT-based":[116],"model":[117,161],"enrich":[119],"expression":[122],"beyond":[123],"original":[125],"dataset.":[126],"Second,":[127],"selects":[133],"qualified":[134],"then":[138],"introduces":[139,172],"cross-modal":[141,174],"attentional":[142,175],"mechanism":[143,176],"interact":[145],"these":[146],"different":[147,155],"sentence":[148],"embeddings":[149],"with":[150],"features":[153],"at":[154,210],"scales.":[156],"short,":[158],"our":[159],"enriches":[162],"information":[166,184],"completing":[168],"semantics":[170],"maximize":[178],"utilization":[180],"enriched":[182],"images.":[189],"Experimental":[190],"results":[191],"on":[192],"CUB,":[193],"Oxford-102,":[194],"CelebA-HQ":[196],"datasets":[197],"prove":[198],"effectiveness":[200],"superiority":[202],"network.":[206],"Code":[207],"available":[209],"https://github.com/Feilingg/ISF-GAN":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}