{"id":"https://openalex.org/W4391578784","doi":"https://doi.org/10.1007/s11063-024-11503-5","title":"RII-GAN: Multi-scaled Aligning-Based Reversed Image Interaction Network for Text-to-Image Synthesis","display_name":"RII-GAN: Multi-scaled Aligning-Based Reversed Image Interaction Network for Text-to-Image Synthesis","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391578784","doi":"https://doi.org/10.1007/s11063-024-11503-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11503-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11503-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11503-5.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11503-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113113582","display_name":"Haofei Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofei Yuan","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005274186","display_name":"Hongqing Zhu","orcid":"https://orcid.org/0000-0002-2122-7066"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongqing Zhu","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086689283","display_name":"Suyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Suyi Yang","raw_affiliation_strings":["Department of Mathematics, Natural, Mathematical and Engineering Sciences, King\u2019s College London, Strand, London, WC2R 2LS, England, UK","Department of Mathematics, Natural, Mathematical and Engineering Sciences, King's College London, Strand, London, WC2R 2LS, England, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Natural, Mathematical and Engineering Sciences, King\u2019s College London, Strand, London, WC2R 2LS, England, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Mathematics, Natural, Mathematical and Engineering Sciences, King's College London, Strand, London, WC2R 2LS, England, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601370","display_name":"Ziying Wang","orcid":"https://orcid.org/0009-0002-8825-0612"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziying Wang","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332754","display_name":"Nan Wang","orcid":"https://orcid.org/0000-0002-4369-0115"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, East China University of Science and Technology, No.130 Meilong Road, Shanghai, 200237, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005274186"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.8175,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70543652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"1","first_page":null,"last_page":null},"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":0.9965000152587891,"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":0.9965000152587891,"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":0.9954000115394592,"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":0.9947999715805054,"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/computational-intelligence","display_name":"Computational intelligence","score":0.7061282992362976},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6902313232421875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5685257911682129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48560041189193726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46773988008499146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3318985402584076}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7061282992362976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6902313232421875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5685257911682129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48560041189193726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46773988008499146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3318985402584076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11063-024-11503-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11503-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11503-5.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11503-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11503-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11503-5.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G4646024371","display_name":null,"funder_award_id":"61872143","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391578784.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2131774270","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W2967307187","https://openalex.org/W3009811209","https://openalex.org/W3096831136","https://openalex.org/W3126750203","https://openalex.org/W3127393268","https://openalex.org/W3141117710","https://openalex.org/W3143894246","https://openalex.org/W3153469116","https://openalex.org/W3174525637","https://openalex.org/W3199535391","https://openalex.org/W3203312420","https://openalex.org/W3214066627","https://openalex.org/W4214485011","https://openalex.org/W4312977351","https://openalex.org/W6600756316","https://openalex.org/W6603717528","https://openalex.org/W6603983777","https://openalex.org/W6608993855","https://openalex.org/W6632604870","https://openalex.org/W6818723395"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"text-to-image":[2],"(T2I)":[3],"model":[4,22,61],"based":[5,23],"on":[6,24,201],"a":[7,71,167,182,190],"single-stage":[8],"generative":[9,75],"adversarial":[10,76],"network":[11,77,89,117],"(GAN)":[12],"has":[13,26],"significantly":[14],"succeeded":[15],"in":[16,140,178],"recent":[17],"years.":[18],"However,":[19],"the":[20,29,45,52,55,60,64,103,108,113,116,119,122,130,141,160,207],"generation":[21,109],"GAN":[25],"two":[27,179],"disadvantages:":[28],"generator":[30,144],"does":[31],"not":[32],"introduce":[33],"any":[34],"image":[35,46,66,73,87,105,124,161],"feature":[36,96,125,172],"manifold":[37,126],"structure,":[38],"which":[39,79],"makes":[40],"it":[41],"challenging":[42],"to":[43,169,205],"align":[44],"and":[47,94,128,159,176],"text":[48,84,148,177],"features.":[49],"Another":[50],"is":[51],"image\u2019s":[53],"diversity;":[54],"text\u2019s":[56],"abstraction":[57],"will":[58],"prevent":[59],"from":[62],"learning":[63,120],"actual":[65,104,123],"distribution.":[67],"This":[68],"paper":[69],"proposes":[70],"reversed":[72,86],"interaction":[74,88],"(RII-GAN),":[78],"consists":[80],"of":[81,121,132,174,209],"four":[82],"components:":[83],"encoder,":[85],"(RIIN),":[90],"adaptive":[91,136],"affine-based":[92,143],"generator,":[93],"dual-channel":[95,183],"alignment":[97],"discriminator":[98],"(DFAD).":[99],"RIIN":[100],"indirectly":[101],"introduces":[102],"distribution":[106,131],"into":[107],"network,":[110],"thus":[111],"overcoming":[112],"problem":[114],"that":[115],"lacks":[118],"structure":[127],"generating":[129],"text-matching":[133],"images.":[134],"Each":[135],"affine":[137],"block":[138],"(AAB)":[139],"proposed":[142],"can":[145],"adaptively":[146],"enhance":[147],"information,":[149],"establishing":[150],"an":[151],"updated":[152],"relation":[153],"between":[154],"original":[155],"independent":[156],"fusion":[157],"blocks":[158],"feature.":[162],"Moreover,":[163],"this":[164],"study":[165],"designs":[166],"DFAD":[168],"capture":[170],"important":[171],"information":[173,194],"images":[175],"channels.":[180],"Such":[181],"backbone":[184],"improves":[185],"semantic":[186],"consistency":[187],"by":[188],"utilizing":[189],"particular":[191],"synchronized":[192],"bi-modal":[193],"extraction":[195],"structure.":[196],"We":[197],"have":[198],"performed":[199],"experiments":[200],"publicly":[202],"available":[203],"datasets":[204],"prove":[206],"effectiveness":[208],"our":[210],"model.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}