{"id":"https://openalex.org/W3092673631","doi":"https://doi.org/10.1145/3394171.3413777","title":"IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning","display_name":"IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092673631","doi":"https://doi.org/10.1145/3394171.3413777","mag":"3092673631"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.00792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020612509","display_name":"Zhenhuan Liu","orcid":"https://orcid.org/0000-0001-9932-9225"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhuan Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088526694","display_name":"Jincan Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincan Deng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074233262","display_name":"Shaofei Cai","orcid":"https://orcid.org/0000-0002-1195-7276"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Cai","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089092566","display_name":"Qianqian Xu","orcid":"https://orcid.org/0000-0002-3512-7277"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianqian Xu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"322","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9539999961853027,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.8064842224121094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254831790924072},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6894109845161438},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5981854200363159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5250710844993591},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5011107921600342},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47886916995048523},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47749587893486023},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47177696228027344},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.4562895894050598},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.4418218731880188},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4331078827381134},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4210923910140991},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41353821754455566}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.8064842224121094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254831790924072},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6894109845161438},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5981854200363159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250710844993591},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5011107921600342},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47886916995048523},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47749587893486023},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47177696228027344},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.4562895894050598},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.4418218731880188},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4331078827381134},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4210923910140991},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41353821754455566},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413777","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.00792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.00792","pdf_url":"https://arxiv.org/pdf/2204.00792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.00792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.00792","pdf_url":"https://arxiv.org/pdf/2204.00792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2062097648","https://openalex.org/W2125389028","https://openalex.org/W2250539671","https://openalex.org/W2561715562","https://openalex.org/W2734426270","https://openalex.org/W2788768663","https://openalex.org/W2885192629","https://openalex.org/W2903838325","https://openalex.org/W2940460948","https://openalex.org/W2949117887","https://openalex.org/W2949999304","https://openalex.org/W2950404765","https://openalex.org/W2953064936","https://openalex.org/W2962754210","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963163163","https://openalex.org/W2963373786","https://openalex.org/W2963567641","https://openalex.org/W2963836885","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964313012","https://openalex.org/W2987401211","https://openalex.org/W2993158499","https://openalex.org/W2998273021","https://openalex.org/W3009811209","https://openalex.org/W3034973631","https://openalex.org/W3035499919","https://openalex.org/W3107847401","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2366944513","https://openalex.org/W3217069185","https://openalex.org/W3049340819","https://openalex.org/W4308928038","https://openalex.org/W4200430540","https://openalex.org/W3141413246","https://openalex.org/W2808862658","https://openalex.org/W4322709305","https://openalex.org/W3171025045","https://openalex.org/W2918279720"],"abstract_inverted_index":{"Conditional":[0],"image":[1,11,14,29,48,111,118],"generation":[2,30],"is":[3],"an":[4,57],"active":[5],"research":[6],"topic":[7],"including":[8],"text2image":[9],"and":[10,37,41,49,75,85,138,145,156],"translation.":[12],"Recently":[13],"manipulation":[15],"with":[16],"linguistic":[17],"instruction":[18,87],"brings":[19],"new":[20],"challenges":[21],"of":[22,104,109,122,150,165],"multimodal":[23],"conditional":[24,28],"generation.":[25],"However,":[26],"traditional":[27],"models":[31],"mainly":[32],"focus":[33],"on":[34,159],"generating":[35,113],"high-quality":[36],"visually":[38],"realistic":[39],"images,":[40],"lack":[42],"resolving":[43],"the":[44,68,83,102,120,133,147,163],"partial":[45],"consistency":[46,69,134],"between":[47,70,135],"instruction.":[50],"To":[51],"address":[52],"this":[53],"issue,":[54],"we":[55,81,100,126],"propose":[56,127],"Increment":[58],"Reasoning":[59],"Generative":[60],"Adversarial":[61],"Network":[62],"(IR-GAN),":[63],"which":[64,141],"aims":[65],"to":[66,89,131],"reason":[67],"visual":[71,136],"increment":[72,77,106,137],"in":[73,78],"images":[74],"semantic":[76,97,105,139],"instructions.":[79],"First,":[80],"introduce":[82],"word-level":[84],"instruction-level":[86],"encoders":[88],"learn":[90],"user's":[91,143],"intention":[92,144],"from":[93],"history-correlated":[94],"instructions":[95],"as":[96],"increment.":[98],"Second,":[99],"embed":[101],"representation":[103],"into":[107],"that":[108],"source":[110,117],"for":[112],"target":[114,152],"image,":[115],"where":[116],"plays":[119],"role":[121],"referring":[123],"auxiliary.":[124],"Finally,":[125],"a":[128],"reasoning":[129],"discriminator":[130],"measure":[132],"increment,":[140],"purifies":[142],"guarantees":[146],"good":[148],"logic":[149],"generated":[151],"image.":[153],"Extensive":[154],"experiments":[155],"visualization":[157],"conducted":[158],"two":[160],"datasets":[161],"show":[162],"effectiveness":[164],"IR-GAN.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2020-10-22T00:00:00"}