{"id":"https://openalex.org/W4304091481","doi":"https://doi.org/10.1145/3503161.3548206","title":"LS-GAN: Iterative Language-based Image Manipulation via Long and Short Term Consistency Reasoning","display_name":"LS-GAN: Iterative Language-based Image Manipulation via Long and Short Term Consistency Reasoning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091481","doi":"https://doi.org/10.1145/3503161.3548206"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548206","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548206","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008914315","display_name":"Gaoxiang Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoxiang Cong","raw_affiliation_strings":["Shandong University, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034640518","display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"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"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & Lishui Institute of Hangzhou Dianzi University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & Lishui Institute of Hangzhou Dianzi University, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366","https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020612509","display_name":"Zhenhuan Liu","orcid":"https://orcid.org/0000-0001-9932-9225"},"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":"Zhenhuan Liu","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/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021557044","display_name":"Yunbin Tu","orcid":"https://orcid.org/0000-0002-9525-9060"},"institutions":[{"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":"Yunbin Tu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000394832","display_name":"Weijun Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijun Qin","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013734569","display_name":"Shenyuan Zhang","orcid":"https://orcid.org/0000-0002-8613-7651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenyuan Zhang","raw_affiliation_strings":["People's Daily, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"People's Daily, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061733267","display_name":"Chengang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengang Yan","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338152","display_name":"Wenyu Wang","orcid":"https://orcid.org/0000-0001-9821-3220"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Wang","raw_affiliation_strings":["Shandong University, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007360513","display_name":"Bin Jiang","orcid":"https://orcid.org/0000-0002-5840-9664"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Jiang","raw_affiliation_strings":["Shandong University, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5899,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76716121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4496","last_page":"4504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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":0.998199999332428,"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":0.9891999959945679,"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":0.9868000149726868,"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":0.7998269200325012},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7670170068740845},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6132833957672119},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5998461842536926},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5922852754592896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5451942086219788},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5438992381095886},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5117756724357605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4931413531303406},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.43953707814216614},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4383791983127594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21943241357803345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998269200325012},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7670170068740845},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6132833957672119},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5998461842536926},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5922852754592896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451942086219788},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5438992381095886},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5117756724357605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4931413531303406},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.43953707814216614},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4383791983127594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21943241357803345},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548206","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548206","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548206","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548206","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1875036955","display_name":null,"funder_award_id":"2020YFB1406604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4920418644","display_name":null,"funder_award_id":"61931008","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7801426869","display_name":"\u7aef\u4e91\u534f\u540c\u89c6\u9891\u667a\u80fd\u8ba1\u7b97\u65b9\u6cd5\u4e0e\u82af\u7247\u67b6\u6784\u7814\u7a76","funder_award_id":"61931008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304091481.pdf","grobid_xml":"https://content.openalex.org/works/W4304091481.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2799062770","https://openalex.org/W2905544595","https://openalex.org/W2914393402","https://openalex.org/W2921741573","https://openalex.org/W2962716332","https://openalex.org/W2962845008","https://openalex.org/W2963145877","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W2993158499","https://openalex.org/W3006871679","https://openalex.org/W3035316078","https://openalex.org/W3048835936","https://openalex.org/W3092673631","https://openalex.org/W3099805778","https://openalex.org/W3111278072","https://openalex.org/W3127393268","https://openalex.org/W3132883577","https://openalex.org/W3136792391","https://openalex.org/W3159190399","https://openalex.org/W3167762716","https://openalex.org/W3174525637","https://openalex.org/W3214007456","https://openalex.org/W4210599520","https://openalex.org/W6748655329"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2039546652","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297"],"abstract_inverted_index":{"Iterative":[0],"language-based":[1],"image":[2],"manipulation":[3],"aims":[4],"to":[5,12,37,98,141],"edit":[6],"images":[7,43],"step":[8,10],"by":[9,103],"according":[11],"user's":[13,83,101],"linguistic":[14,147],"instructions.":[15,148],"The":[16,123],"existing":[17],"methods":[18],"mostly":[19],"focus":[20],"on":[21,129,146,171],"aligning":[22],"the":[23,68,79,82,86,100,109,127,139,155,168],"attributes":[24],"and":[25,42,57,76,116,132,164,166],"appearance":[26],"of":[27,70,160],"new-added":[28],"visual":[29,143],"elements":[30],"with":[31,73,81],"current":[32,74],"instruction.":[33,110],"However,":[34],"they":[35],"fail":[36],"maintain":[38],"consistency":[39,60,80],"between":[40],"instructions":[41],"as":[44],"iterative":[45],"rounds":[46],"increase.":[47],"To":[48],"address":[49],"this":[50],"issue,":[51],"we":[52,90,112],"propose":[53],"a":[54,93,114],"novel":[55],"Long":[56,115],"Short":[58,117],"term":[59,118],"reasoning":[61,125,137],"Generative":[62],"Adversarial":[63],"Network":[64],"(LS-GAN),":[65],"which":[66],"enhances":[67],"awareness":[69],"previous":[71],"objects":[72],"instruction":[75],"better":[77],"maintains":[78],"intent":[84],"under":[85],"continuous":[87],"iterations.":[88],"Specifically,":[89],"first":[91],"design":[92],"Context-aware":[94],"Phrase":[95],"Encoder":[96],"(CPE)":[97],"learn":[99],"intention":[102],"extracting":[104],"different":[105],"phrase-level":[106],"information":[107],"about":[108],"Further,":[111],"introduce":[113],"Consistency":[119],"Reasoning":[120],"(LSCR)":[121],"mechanism.":[122],"long-term":[124],"improves":[126,154],"model":[128],"semantic":[130],"understanding":[131],"positional":[133],"reasoning,":[134],"while":[135],"short-term":[136],"ensures":[138],"ability":[140],"construct":[142],"scenes":[144],"based":[145],"Extensive":[149],"results":[150],"show":[151],"that":[152],"LS-GAN":[153],"generation":[156],"quality":[157],"in":[158],"terms":[159],"both":[161],"object":[162],"identity":[163],"position,":[165],"achieves":[167],"state-of-the-art":[169],"performance":[170],"two":[172],"public":[173],"datasets.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}