{"id":"https://openalex.org/W3165787555","doi":"https://doi.org/10.1109/tpami.2021.3085339","title":"Text-Guided Human Image Manipulation via Image-Text Shared Space","display_name":"Text-Guided Human Image Manipulation via Image-Text Shared Space","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3165787555","doi":"https://doi.org/10.1109/tpami.2021.3085339","mag":"3165787555","pmid":"https://pubmed.ncbi.nlm.nih.gov/34061734"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3085339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3085339","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5015910981","display_name":"Xiaogang Xu","orcid":"https://orcid.org/0000-0002-9213-8001"},"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"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xiaogang Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101938761","display_name":"Ying-Cong Chen","orcid":"https://orcid.org/0000-0002-9565-8205"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying-Cong Chen","raw_affiliation_strings":["Computer Science and Artifical Intelligence Lab, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artifical Intelligence Lab, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037702873","display_name":"Xin Tao","orcid":"https://orcid.org/0000-0001-9126-4746"},"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":"Xin Tao","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052856441","display_name":"Jiaya Jia","orcid":"https://orcid.org/0000-0002-1246-553X"},"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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaya Jia","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015910981"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.2596,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81740244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"44","issue":"10","first_page":"6486","last_page":"6500"},"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":0.9973999857902527,"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":0.9973999857902527,"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":0.9957000017166138,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9912999868392944,"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":0.8566404581069946},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7732110023498535},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6735893487930298},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6435047388076782},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5533826947212219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5254087448120117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4550853371620178},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44837674498558044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33258768916130066},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07831612229347229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566404581069946},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7732110023498535},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6735893487930298},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6435047388076782},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5533826947212219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254087448120117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4550853371620178},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44837674498558044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33258768916130066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07831612229347229},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2021.3085339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3085339","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34061734","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34061734","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-141429","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-141429","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W26575457","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1602182271","https://openalex.org/W1686810756","https://openalex.org/W1834627138","https://openalex.org/W1902237438","https://openalex.org/W1982925187","https://openalex.org/W2087681821","https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2331128040","https://openalex.org/W2339827301","https://openalex.org/W2402268235","https://openalex.org/W2405756170","https://openalex.org/W2471768434","https://openalex.org/W2528578439","https://openalex.org/W2559085405","https://openalex.org/W2593414223","https://openalex.org/W2603777577","https://openalex.org/W2788541584","https://openalex.org/W2885537606","https://openalex.org/W2889077639","https://openalex.org/W2890816492","https://openalex.org/W2897946384","https://openalex.org/W2903838325","https://openalex.org/W2921741573","https://openalex.org/W2953421261","https://openalex.org/W2962845008","https://openalex.org/W2962974533","https://openalex.org/W2963145877","https://openalex.org/W2963266880","https://openalex.org/W2963351004","https://openalex.org/W2963413689","https://openalex.org/W2963449390","https://openalex.org/W2963609793","https://openalex.org/W2963734522","https://openalex.org/W2963800363","https://openalex.org/W2963870144","https://openalex.org/W2963890275","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964125246","https://openalex.org/W2964216930","https://openalex.org/W2964313012","https://openalex.org/W2964318046","https://openalex.org/W2984529706","https://openalex.org/W2984809863","https://openalex.org/W2986945954","https://openalex.org/W2989855043","https://openalex.org/W2990307191","https://openalex.org/W2990452356","https://openalex.org/W2993158499","https://openalex.org/W3032562988","https://openalex.org/W3034431451","https://openalex.org/W3034600949","https://openalex.org/W3034950620","https://openalex.org/W3035316078","https://openalex.org/W3035515747","https://openalex.org/W3035644696","https://openalex.org/W3093122931","https://openalex.org/W4288088427","https://openalex.org/W6601069402","https://openalex.org/W6601733005","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6704003556","https://openalex.org/W6713645886","https://openalex.org/W6728889164","https://openalex.org/W6749028901","https://openalex.org/W6752216276","https://openalex.org/W6755102824","https://openalex.org/W6755357105","https://openalex.org/W6765779288","https://openalex.org/W6767384525","https://openalex.org/W6767457696","https://openalex.org/W6769148693"],"related_works":["https://openalex.org/W637626424","https://openalex.org/W2005185696","https://openalex.org/W2161229648","https://openalex.org/W2235753890","https://openalex.org/W2993674027","https://openalex.org/W2130228941","https://openalex.org/W2366116130","https://openalex.org/W2132132164","https://openalex.org/W2889893736","https://openalex.org/W2092957489"],"abstract_inverted_index":{"Text":[0],"is":[1,144],"a":[2,96],"new":[3],"way":[4],"to":[5,46,51,72,115,137,159],"guide":[6],"human":[7,161],"image":[8],"manipulation.":[9],"Albeit":[10],"natural":[11],"and":[12,28,59,75,82,153,157],"flexible,":[13],"text":[14,143],"usually":[15],"suffers":[16],"from":[17],"inaccuracy":[18],"in":[19,23,31,90,105,119],"spatial":[20,60],"description,":[21],"ambiguity":[22,118],"the":[24,55,65,87,117,142],"description":[25],"of":[26,57,77,98,111],"appearance,":[27],"incompleteness.":[29],"We":[30,146],"this":[32,91,106],"paper":[33],"address":[34],"these":[35],"issues.":[36],"To":[37],"overcome":[38],"inaccuracy,":[39],"we":[40,63,131],"use":[41],"structured":[42],"information":[43],"(e.g.,":[44],"poses)":[45],"help":[47],"identify":[48],"correct":[49],"location":[50],"manipulate,":[52],"by":[53,79,101],"disentangling":[54],"control":[56],"appearance":[58],"structure.":[61],"Moreover,":[62],"learn":[64],"image-text":[66],"shared":[67],"space":[68,107],"with":[69,108],"derived":[70],"disentanglement":[71],"improve":[73],"accuracy":[74],"quality":[76],"manipulation,":[78],"separating":[80],"relevant":[81],"irrelevant":[83],"editing":[84,112,139],"directions":[85],"for":[86,126],"textual":[88],"instructions":[89],"space.":[92],"Our":[93],"model":[94,122],"generates":[95,123],"series":[97],"manipulation":[99],"results":[100],"moving":[102],"source":[103],"images":[104],"different":[109],"degrees":[110],"strength.":[113],"Thus,":[114],"reduce":[116],"text,":[120],"our":[121,148],"sequential":[124],"output":[125],"manual":[127],"selection.":[128],"In":[129],"addition,":[130],"propose":[132],"an":[133],"efficient":[134],"pseudo-label":[135],"loss":[136],"enhance":[138],"performance":[140],"when":[141],"incomplete.":[145],"evaluate":[147],"method":[149],"on":[150],"various":[151],"datasets":[152],"show":[154],"its":[155],"precision":[156],"interactiveness":[158],"manipulate":[160],"images.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}