{"id":"https://openalex.org/W4313157089","doi":"https://doi.org/10.1109/tmm.2022.3219677","title":"From External to Internal: Structuring Image for Text-to-Image Attributes Manipulation","display_name":"From External to Internal: Structuring Image for Text-to-Image Attributes Manipulation","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4313157089","doi":"https://doi.org/10.1109/tmm.2022.3219677"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3219677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3219677","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/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Futher Media, School and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center for Futher Media, School and Technology of China, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035846349","display_name":"Qike Zhao","orcid":"https://orcid.org/0000-0002-7907-0081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qike Zhao","raw_affiliation_strings":["Center for Futher Media, School and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-7907-0081","affiliations":[{"raw_affiliation_string":"Center for Futher Media, School and Technology of China, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087225139","display_name":"Junchen Zhu","orcid":"https://orcid.org/0000-0002-3872-6689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junchen Zhu","raw_affiliation_strings":["Center for Futher Media, School and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-3872-6689","affiliations":[{"raw_affiliation_string":"Center for Futher Media, School and Technology of China, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051338650","display_name":"Sitong Su","orcid":"https://orcid.org/0009-0001-7406-116X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sitong Su","raw_affiliation_strings":["Center for Futher Media, School and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0001-7406-116X","affiliations":[{"raw_affiliation_string":"Center for Futher Media, School and Technology of China, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lechao Cheng","raw_affiliation_strings":["Zhejiang Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101749819","display_name":"Lei Zhao","orcid":"https://orcid.org/0000-0002-8838-164X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhao","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0002-8838-164X","affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3915,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59478155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"7248","last_page":"7261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9932000041007996,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9865999817848206,"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":0.7644500136375427},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.6217781901359558},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6161392331123352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287508368492126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49012479186058044},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4321935176849365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3279564380645752},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1702493131160736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644500136375427},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6217781901359558},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6161392331123352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287508368492126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49012479186058044},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4321935176849365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3279564380645752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1702493131160736},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3219677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3219677","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G6971015501","display_name":null,"funder_award_id":"171106","funder_id":"https://openalex.org/F4320334945","funder_display_name":"Fok Ying Tong Education Foundation"}],"funders":[{"id":"https://openalex.org/F4320334945","display_name":"Fok Ying Tong Education Foundation","ror":"https://ror.org/01mv9t934"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2183341477","https://openalex.org/W2475287302","https://openalex.org/W2519536754","https://openalex.org/W2533598788","https://openalex.org/W2603777577","https://openalex.org/W2903838325","https://openalex.org/W2942729634","https://openalex.org/W2952056941","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963413689","https://openalex.org/W2963612019","https://openalex.org/W2963890275","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964313012","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2975136131","https://openalex.org/W2993158499","https://openalex.org/W2993433871","https://openalex.org/W3008653537","https://openalex.org/W3016121695","https://openalex.org/W3035149916","https://openalex.org/W3035316078","https://openalex.org/W3047371217","https://openalex.org/W3048372515","https://openalex.org/W3092673631","https://openalex.org/W3092713047","https://openalex.org/W3092738440","https://openalex.org/W3092775865","https://openalex.org/W3092906216","https://openalex.org/W3093190933","https://openalex.org/W3093370337","https://openalex.org/W3093392184","https://openalex.org/W3094673569","https://openalex.org/W3095707326","https://openalex.org/W3096601784","https://openalex.org/W3108367042","https://openalex.org/W3133431537","https://openalex.org/W3135254306","https://openalex.org/W3154362247","https://openalex.org/W3159521921","https://openalex.org/W3174194560","https://openalex.org/W3193215774","https://openalex.org/W3193652355","https://openalex.org/W3205398323","https://openalex.org/W4226017838","https://openalex.org/W4285543521","https://openalex.org/W4312977351","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6713645886","https://openalex.org/W6714590955","https://openalex.org/W6718379498","https://openalex.org/W6728889164","https://openalex.org/W6729110096","https://openalex.org/W6739901393","https://openalex.org/W6755102824","https://openalex.org/W6765052341","https://openalex.org/W6765779288","https://openalex.org/W6784364625","https://openalex.org/W6790978476"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W1494563618","https://openalex.org/W2357022711","https://openalex.org/W2358910766"],"abstract_inverted_index":{"Manipulating":[0],"visual":[1],"attributes":[2,14,142,191],"of":[3,102,143,177,263],"an":[4,126,180],"image":[5,29,155],"through":[6],"a":[7,18,37,76,112,197],"natural":[8],"language":[9],"description,":[10,38],"known":[11],"as":[12],"text-to-image":[13],"manipulation":[15],"(T2AM),":[16],"is":[17,237,245,268],"challenging":[19],"task.":[20],"However,":[21],"existing":[22],"approaches":[23],"tend":[24],"to":[25,30,43,66,90,98,167,248],"search":[26],"the":[27,32,47,54,62,71,93,120,140,144,149,160,172,189,221,228,234,250,256,259],"whole":[28],"manipulate":[31,46],"target":[33,121,145,163],"instance":[34],"indicated":[35],"by":[36,169,231],"thus":[39],"they":[40],"often":[41],"fail":[42],"locate":[44],"and":[45,51,59,118,123,128,138,152,174,186,192,217,255,261],"accurate":[48],"text-relevant":[49,141,190],"regions,":[50],"even":[52],"disturb":[53],"text-irrelevant":[55],"contents,":[56],"e.g.":[57],"texture":[58],"background.":[60],"Meanwhile,":[61],"model":[63],"efficiency":[64],"needs":[65],"be":[67],"improved.":[68],"To":[69],"tackle":[70],"above":[72],"issues,":[73],"we":[74],"introduce":[75],"novel":[77],"yet":[78],"simple":[79],"GAN-based":[80],"approach,":[81],"namely":[82],"<italic":[83,107,130,181,198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[84,108,131,182,199,272],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><u>S</u>tructuring":[85],"<u>I</u>mage":[86],"for":[87,116,135],"<u>M</u>anipulating</i>":[88],"(SIMGAN),":[89],"narrow":[91],"down":[92],"optimization":[94],"areas":[95],"from":[96,125,157,165],"external":[97],"internal.":[99],"It":[100],"consists":[101],"two":[103],"major":[104],"components:":[105],"1)":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">External":[109],"Structuring</i>":[110,133,184,201],"(ExST),":[111],"pretrained":[113],"segmentation":[114],"network,":[115],"recognizing":[117],"separating":[119],"instances":[122,146,164,178],"background":[124],"image;":[127],"2)":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Internal":[132],"(InST)":[134],"seeking":[136],"out":[137],"editing":[139],"based":[147],"on":[148,194,205],"given":[150],"description":[151],"masked":[153],"hierarchical":[154],"representations":[156],"ExST.":[158],"Specifically,":[159],"InST":[161],"structures":[162],"outline":[166],"detail":[168],"firstly":[170],"drawing":[171],"sketch":[173],"colors":[175],"underpainting":[176],"with":[179,196,220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Outline-Oriented":[183],"(OuST),":[185],"then":[187],"enhancing":[188],"elaborating":[193],"details":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Detail-Oriented":[200],"(DeST).":[202],"Extensive":[203],"experiments":[204],"benchmark":[206],"datasets":[207],"demonstrate":[208],"that":[209],"our":[210,225,243,264],"framework":[211],"significantly":[212],"outperforms":[213],"state-of-the-art":[214,222],"both":[215],"quantitatively":[216],"qualitatively.":[218],"Compared":[219],"method":[223],"ManiGAN,":[224],"approach":[226,244],"reduces":[227],"training":[229],"time":[230,236],"88%,":[232],"while":[233],"inferring":[235],"three":[238],"times":[239],"faster.":[240],"In":[241],"addition,":[242],"easily":[246],"extended":[247],"solve":[249],"instance-level":[251],"image-to-image":[252],"translation":[253],"problem,":[254],"results":[257],"exhibit":[258],"versatility":[260],"effectiveness":[262],"approach.":[265],"This":[266],"code":[267],"released":[269],"in":[270],"<uri":[271],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/qikizh/SIMGAN</uri>":[273],".":[274]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}