{"id":"https://openalex.org/W4324290964","doi":"https://doi.org/10.1109/tmm.2023.3256798","title":"InDecGAN: Learning to Generate Complex Images From Captions via Independent Object-Level Decomposition and Enhancement","display_name":"InDecGAN: Learning to Generate Complex Images From Captions via Independent Object-Level Decomposition and Enhancement","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4324290964","doi":"https://doi.org/10.1109/tmm.2023.3256798"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3256798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3256798","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/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3131-3275","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054902681","display_name":"Fuxiang Wu","orcid":"https://orcid.org/0000-0002-4542-4486"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Fuxiang Wu","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4542-4486","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324286","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-8128-2788"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8128-2788","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011954673","display_name":"Qieshi Zhang","orcid":"https://orcid.org/0000-0001-6358-1840"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Qieshi Zhang","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6358-1840","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043134796","display_name":"Leszek Rutkowski","orcid":"https://orcid.org/0000-0001-6960-9525"},"institutions":[{"id":"https://openalex.org/I66083562","display_name":"Systems Research Institute","ror":"https://ror.org/0111cp837","country_code":"PL","type":"facility","lineage":["https://openalex.org/I66083562","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Leszek Rutkowski","raw_affiliation_strings":["Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0001-6960-9525","affiliations":[{"raw_affiliation_string":"Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I66083562","https://openalex.org/I99542240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409300","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0002-5979-578X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5979-578X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33259755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":null,"first_page":"8279","last_page":"8293"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9930999875068665,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9585999846458435,"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":0.8300930261611938},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6912881731987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6829409599304199},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6071423888206482},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.550951361656189},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5164594650268555},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5062686204910278},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5042728185653687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4466995298862457},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44295769929885864},{"id":"https://openalex.org/keywords/method","display_name":"Method","score":0.4367640018463135},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42212215065956116},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36492210626602173},{"id":"https://openalex.org/keywords/object-oriented-programming","display_name":"Object-oriented programming","score":0.18015044927597046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08368426561355591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300930261611938},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6912881731987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6829409599304199},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6071423888206482},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.550951361656189},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5164594650268555},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5062686204910278},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5042728185653687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4466995298862457},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44295769929885864},{"id":"https://openalex.org/C512554520","wikidata":"https://www.wikidata.org/wiki/Q815844","display_name":"Method","level":3,"score":0.4367640018463135},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42212215065956116},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36492210626602173},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.18015044927597046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08368426561355591},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3256798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3256798","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/11","display_name":"Sustainable cities and communities","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2544253145","display_name":null,"funder_award_id":"U1913202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5258257467","display_name":null,"funder_award_id":"U21A20487","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G874158310","display_name":null,"funder_award_id":"[2017]476","funder_id":"https://openalex.org/F4320327719","funder_display_name":"3D Digital Media Technology Engineering Laboratory"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327719","display_name":"3D Digital Media Technology Engineering Laboratory","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2125389028","https://openalex.org/W2131774270","https://openalex.org/W2618017917","https://openalex.org/W2768799425","https://openalex.org/W2797029597","https://openalex.org/W2798819017","https://openalex.org/W2890718122","https://openalex.org/W2962845008","https://openalex.org/W2963047368","https://openalex.org/W2963163163","https://openalex.org/W2963184176","https://openalex.org/W2963402808","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2964149283","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2979672901","https://openalex.org/W2982450728","https://openalex.org/W2983248633","https://openalex.org/W2984854289","https://openalex.org/W2993433871","https://openalex.org/W3008728787","https://openalex.org/W3015857268","https://openalex.org/W3034633089","https://openalex.org/W3035083401","https://openalex.org/W3035316078","https://openalex.org/W3035500781","https://openalex.org/W3035574324","https://openalex.org/W3041579012","https://openalex.org/W3099268463","https://openalex.org/W3108367042","https://openalex.org/W3174525637","https://openalex.org/W3174711319","https://openalex.org/W3196878101","https://openalex.org/W3205866742","https://openalex.org/W3214744507","https://openalex.org/W4214597499","https://openalex.org/W4214931354","https://openalex.org/W4225307095","https://openalex.org/W4312438583","https://openalex.org/W6618372016","https://openalex.org/W6629028937","https://openalex.org/W6678815747","https://openalex.org/W6679434410","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6734209382","https://openalex.org/W6738248287","https://openalex.org/W6745903366","https://openalex.org/W6747733185","https://openalex.org/W6748582592","https://openalex.org/W6748596569","https://openalex.org/W6755312952","https://openalex.org/W6758114194","https://openalex.org/W6767137312","https://openalex.org/W6771867658","https://openalex.org/W6790978476","https://openalex.org/W6810125463"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Text-to-image":[0],"synthesis":[1,33],"is":[2],"a":[3,8,72,171],"challenging":[4],"problem,":[5],"in":[6,37,41,71,90],"which":[7],"complex":[9,43,65,73],"scene":[10,140],"contains":[11],"diverse":[12,27],"objects":[13,20,40,70,89,122],"of":[14,19,88,121,151,162,191],"various":[15],"sizes":[16],"and":[17,55,67,85,111,141,155],"sub-images":[18],"belonging":[21],"to":[22,63,97,116,136,177],"the":[23,42,79,112,118,125,129,133,138,148,152,157,160,163,180],"same":[24],"class":[25],"have":[26,35],"forms":[28],"from":[29,159],"different":[30],"perspectives.":[31],"Thus,":[32],"models":[34],"difficulty":[36],"capturing":[38],"varied":[39,69,99],"scene.":[44,74],"To":[45],"alleviate":[46],"these":[47],"problems,":[48],"we":[49,146],"devise":[50],"an":[51,106,184],"independent":[52,80,94,102,107,185],"object-level":[53,81,95,103,108,134,186],"decomposing":[54],"enhancing":[56],"generative":[57],"adversarial":[58,109],"networks,":[59],"denoted":[60],"as":[61],"InDecGAN,":[62],"synthesize":[64,98,142],"images":[66,87,190],"capture":[68],"Specifically,":[75],"InDecGAN":[76,154],"fully":[77],"utilizes":[78],"information,":[82],"bounding":[83,113],"boxes":[84],"high-resolution":[86],"training,":[91],"by":[92,132],"employing":[93],"pathways":[96],"objects.":[100],"The":[101],"pathway":[104,127,135,187],"integrates":[105],"loss":[110],"box":[114],"information":[115],"learn":[117],"visual":[119],"features":[120,130],"independently,":[123],"then,":[124],"main":[126],"exploits":[128],"provided":[131],"compose":[137],"full":[139],"images.":[143],"In":[144],"addition,":[145],"analyze":[147],"generalization":[149],"properties":[150],"proposed":[153,181],"demonstrate":[156,178],"improvement":[158],"perspective":[161],"model":[164,182],"architecture.":[165],"Moreover,":[166],"extensive":[167],"experiments":[168],"conducted":[169],"on":[170],"widely":[172],"used":[173],"dataset":[174],"are":[175],"presented":[176],"that":[179],"with":[183],"produces":[188],"synthesized":[189],"significantly":[192],"improved":[193],"quality.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}