{"id":"https://openalex.org/W4386598262","doi":"https://doi.org/10.1109/icip49359.2023.10222100","title":"Structure-Aware Generative Adversarial Network for Text-to-Image Generation","display_name":"Structure-Aware Generative Adversarial Network for Text-to-Image Generation","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598262","doi":"https://doi.org/10.1109/icip49359.2023.10222100"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222100","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-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/A5047216687","display_name":"Wenjie Chen","orcid":"https://orcid.org/0000-0002-1751-6826"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjie Chen","raw_affiliation_strings":["Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032273272","display_name":"Zhangkai Ni","orcid":"https://orcid.org/0000-0003-3682-6288"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangkai Ni","raw_affiliation_strings":["Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China","Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Computer Science and Technology,Shanghai,P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047216687"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52542979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2075","last_page":"2079"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9775000214576721,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9703999757766724,"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/semantic-space","display_name":"Semantic space","score":0.74949049949646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7404016852378845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6676974296569824},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.609398603439331},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5995416641235352},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5954054594039917},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5759605169296265},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5246070623397827},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4993135929107666},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4954158067703247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4901912808418274},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.42218589782714844},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3260350227355957},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16753670573234558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15737244486808777}],"concepts":[{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.74949049949646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404016852378845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6676974296569824},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.609398603439331},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5995416641235352},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5954054594039917},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5759605169296265},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5246070623397827},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4993135929107666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4954158067703247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4901912808418274},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.42218589782714844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3260350227355957},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16753670573234558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15737244486808777},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222100","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2128409098","https://openalex.org/W2746314669","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W3034720584","https://openalex.org/W3035574324","https://openalex.org/W3141117710","https://openalex.org/W3174525637","https://openalex.org/W4214926101","https://openalex.org/W4312438583","https://openalex.org/W4312977351","https://openalex.org/W6638319203","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6743428213","https://openalex.org/W6756444276","https://openalex.org/W6765779288","https://openalex.org/W6789034737","https://openalex.org/W6791353385","https://openalex.org/W6810452849"],"related_works":["https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501","https://openalex.org/W2128807628"],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1],"aims":[2],"at":[3],"synthesizing":[4],"photo-realistic":[5],"images":[6,14,91],"from":[7],"textual":[8],"descriptions.":[9],"Existing":[10],"methods":[11],"typically":[12],"align":[13],"with":[15,122],"the":[16,25,28,32,40,45,74,85,93,114,123],"corresponding":[17],"texts":[18],"in":[19,31,73,78,109],"a":[20,59,79],"joint":[21,33,75],"semantic":[22,34,76],"space.":[23],"However,":[24],"presence":[26],"of":[27,44,53,89,111,116],"modality":[29],"gap":[30],"space":[35,77],"leads":[36,49],"to":[37,50],"misalignment.":[38],"Meanwhile,":[39],"limited":[41],"receptive":[42],"field":[43],"convolutional":[46],"neural":[47],"network":[48,63],"structural":[51],"distortions":[52],"generated":[54,90],"images.":[55],"In":[56],"this":[57],"work,":[58],"structure-aware":[60],"generative":[61],"adversarial":[62],"(SaGAN)":[64],"is":[65],"proposed":[66],"for":[67],"(1)":[68],"semantically":[69],"aligning":[70],"multimodal":[71],"features":[72],"learnable":[80],"manner;":[81],"and":[82,87,106,118],"(2)":[83],"improving":[84],"structure":[86],"contour":[88],"by":[92],"designed":[94],"content-invariant":[95],"negative":[96],"samples.":[97],"Experimental":[98],"results":[99],"show":[100],"that":[101],"SaGAN":[102],"achieves":[103],"over":[104],"30.1%":[105],"8.2%":[107],"improvements":[108],"terms":[110],"FID":[112],"on":[113],"datasets":[115],"CUB":[117],"COCO":[119],"when":[120],"compared":[121],"state-of-the-art":[124],"approaches.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}