{"id":"https://openalex.org/W3089767655","doi":"https://doi.org/10.1109/icip40778.2020.9191228","title":"Learning Cross-Modal Representations for Language-Based Image Manipulation","display_name":"Learning Cross-Modal Representations for Language-Based Image Manipulation","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3089767655","doi":"https://doi.org/10.1109/icip40778.2020.9191228","mag":"3089767655"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9191228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046802808","display_name":"E.Ak Kenan","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"E.Ak Kenan","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649794","display_name":"Ying Sun","orcid":"https://orcid.org/0000-0002-7224-6726"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ying Sun","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo Hwee Lim","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0252,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84062628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1601","last_page":"1605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9944999814033508,"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":0.9819999933242798,"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":0.8407148122787476},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6650554537773132},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6393818855285645},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6308021545410156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5929532051086426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5472596883773804},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5337648391723633},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5176218152046204},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5049861073493958},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4597179889678955},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4252403974533081},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4247037172317505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40182602405548096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3721693158149719},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07051360607147217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407148122787476},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6650554537773132},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6393818855285645},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6308021545410156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929532051086426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5472596883773804},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5337648391723633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5176218152046204},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5049861073493958},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4597179889678955},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4252403974533081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4247037172317505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40182602405548096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3721693158149719},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07051360607147217},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9191228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1797268635","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2150856297","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2405756170","https://openalex.org/W2530372461","https://openalex.org/W2561715562","https://openalex.org/W2798951647","https://openalex.org/W2802650881","https://openalex.org/W2804078698","https://openalex.org/W2884870985","https://openalex.org/W2885537606","https://openalex.org/W2891417743","https://openalex.org/W2893749619","https://openalex.org/W2905544595","https://openalex.org/W2911340057","https://openalex.org/W2911599361","https://openalex.org/W2949999304","https://openalex.org/W2950404765","https://openalex.org/W2952716587","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963684088","https://openalex.org/W2963767194","https://openalex.org/W2963800363","https://openalex.org/W2963836885","https://openalex.org/W2963966654","https://openalex.org/W2963971656","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2964050021","https://openalex.org/W2964121744","https://openalex.org/W2964313012","https://openalex.org/W2964318046","https://openalex.org/W2970067499","https://openalex.org/W2972374322","https://openalex.org/W2984809863","https://openalex.org/W2993158499","https://openalex.org/W3008297462","https://openalex.org/W3012404734","https://openalex.org/W3012498027","https://openalex.org/W3012970712","https://openalex.org/W3025192522","https://openalex.org/W3037695135","https://openalex.org/W4300838842","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6713645886","https://openalex.org/W6728889164","https://openalex.org/W6744040789","https://openalex.org/W6752378368","https://openalex.org/W6755102824","https://openalex.org/W6755312952","https://openalex.org/W6758494947","https://openalex.org/W6765779288","https://openalex.org/W6779841522"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,104],"propose":[4],"a":[5,17,58,92],"generative":[6,22,117],"architecture":[7],"for":[8],"manipulating":[9],"images/scenes":[10],"with":[11],"natural":[12],"language":[13],"descriptions.":[14],"This":[15],"is":[16,24],"challenging":[18],"task":[19],"as":[20],"the":[21,28,34,38,45,62,84,100,116,130,134,147,155],"network":[23,118],"expected":[25],"to":[26,72,82,109,122],"perform":[27],"given":[29],"text":[30,87,113,124],"instruction":[31],"without":[32],"changing":[33],"non-affiliating":[35],"contents":[36],"of":[37,44,51,64,80,95,160],"input":[39,135],"image.":[40,136],"Two":[41],"main":[42],"drawbacks":[43],"existing":[46],"methods":[47],"are":[48],"their":[49],"limitation":[50],"performing":[52],"changes":[53,132],"that":[54,146],"would":[55],"affect":[56],"only":[57,129],"limited":[59],"region":[60],"and":[61,86,112,141,153,162],"inability":[63],"handling":[65],"complex":[66],"instructions.":[67],"The":[68],"proposed":[69,148],"approach,":[70],"designed":[71],"address":[73],"these":[74,96],"limitations":[75],"initially":[76],"uses":[77],"two":[78,97],"sets":[79],"networks":[81],"extract":[83],"image":[85,101,111],"features":[88],"respectively.":[89],"Rather":[90],"than":[91],"simple":[93],"combination":[94],"modalities":[98],"during":[99],"manipulation":[102,125],"process,":[103],"use":[105],"an":[106],"improved":[107],"technique":[108],"compose":[110],"features.":[114],"Additionally,":[115],"utilizes":[119],"similarity":[120],"learning":[121],"improve":[123],"which":[126],"also":[127],"enforces":[128],"text-relevant":[131],"on":[133,139],"Our":[137],"experiments":[138],"CSS":[140],"Fashion":[142],"Synthesis":[143],"datasets":[144],"show":[145],"approach":[149],"performs":[150],"remarkably":[151],"well":[152],"outperforms":[154],"baseline":[156],"frameworks":[157],"in":[158],"terms":[159],"R-precision":[161],"FID.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}