{"id":"https:\/\/openalex.org\/W4402753861","doi":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00870","title":"Named Entity Driven Zero-Shot Image Manipulation","display_name":"Named Entity Driven Zero-Shot Image Manipulation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https:\/\/openalex.org\/W4402753861","doi":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00870"},"language":"en","primary_location":{"id":"doi:10.1109\/cvpr52733.2024.00870","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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\/A5112395293","display_name":"Zhida Feng","orcid":"https:\/\/orcid.org\/0009-0004-6348-9621"},"institutions":[{"id":"https:\/\/openalex.org\/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https:\/\/ror.org\/00e4hrk88","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I43922553"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhida Feng","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology,Wuhan,China","institution_ids":["https:\/\/openalex.org\/I43922553"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5100379203","display_name":"Li Chen","orcid":"https:\/\/orcid.org\/0000-0001-9899-2535"},"institutions":[{"id":"https:\/\/openalex.org\/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https:\/\/ror.org\/00e4hrk88","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Science and Technology,Wuhan,China","institution_ids":["https:\/\/openalex.org\/I43922553"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5017963893","display_name":"Jing Tian","orcid":"https:\/\/orcid.org\/0000-0002-4084-6911"},"institutions":[{"id":"https:\/\/openalex.org\/I165932596","display_name":"National University of Singapore","ror":"https:\/\/ror.org\/01tgyzw49","country_code":"SG","type":"education","lineage":["https:\/\/openalex.org\/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jing Tian","raw_affiliation_strings":["Institute of Systems Science, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Systems Science, National University of Singapore","institution_ids":["https:\/\/openalex.org\/I165932596"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5054548309","display_name":"JiaXiang Liu","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I98301712","display_name":"Baidu (China)","ror":"https:\/\/ror.org\/03vs3wt56","country_code":"CN","type":"company","lineage":["https:\/\/openalex.org\/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JiaXiang Liu","raw_affiliation_strings":["Baidu Inc"],"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https:\/\/openalex.org\/I98301712"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5005049423","display_name":"Shikun Feng","orcid":"https:\/\/orcid.org\/0009-0009-8300-7649"},"institutions":[{"id":"https:\/\/openalex.org\/I98301712","display_name":"Baidu (China)","ror":"https:\/\/ror.org\/03vs3wt56","country_code":"CN","type":"company","lineage":["https:\/\/openalex.org\/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Feng","raw_affiliation_strings":["Baidu Inc"],"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https:\/\/openalex.org\/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https:\/\/openalex.org\/A5112395293"],"corresponding_institution_ids":["https:\/\/openalex.org\/I43922553"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53958546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9110","last_page":"9119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https:\/\/openalex.org\/T12357","display_name":"Digital Media Forensic Detection","score":0.9955999851226807,"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\/T12357","display_name":"Digital Media Forensic Detection","score":0.9955999851226807,"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\/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919000267982483,"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\/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9878000020980835,"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\/shot","display_name":"Shot (pellet)","score":0.7584749460220337},{"id":"https:\/\/openalex.org\/keywords\/computer-science","display_name":"Computer science","score":0.6445275545120239},{"id":"https:\/\/openalex.org\/keywords\/image","display_name":"Image (mathematics)","score":0.5480794906616211},{"id":"https:\/\/openalex.org\/keywords\/zero","display_name":"Zero (linguistics)","score":0.5454835891723633},{"id":"https:\/\/openalex.org\/keywords\/computer-vision","display_name":"Computer vision","score":0.5377820134162903},{"id":"https:\/\/openalex.org\/keywords\/artificial-intelligence","display_name":"Artificial intelligence","score":0.5111148953437805},{"id":"https:\/\/openalex.org\/keywords\/computer-graphics","display_name":"Computer graphics (images)","score":0.3916594982147217},{"id":"https:\/\/openalex.org\/keywords\/materials-science","display_name":"Materials science","score":0.07229417562484741}],"concepts":[{"id":"https:\/\/openalex.org\/C2778344882","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7584749460220337},{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.6445275545120239},{"id":"https:\/\/openalex.org\/C115961682","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5480794906616211},{"id":"https:\/\/openalex.org\/C2780813799","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5454835891723633},{"id":"https:\/\/openalex.org\/C31972630","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q844240","display_name":"Computer vision","level":1,"score":0.5377820134162903},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5111148953437805},{"id":"https:\/\/openalex.org\/C121684516","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3916594982147217},{"id":"https:\/\/openalex.org\/C192562407","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q228736","display_name":"Materials science","level":0,"score":0.07229417562484741},{"id":"https:\/\/openalex.org\/C191897082","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11467","display_name":"Metallurgy","level":1,"score":0},{"id":"https:\/\/openalex.org\/C41895202","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q8162","display_name":"Linguistics","level":1,"score":0},{"id":"https:\/\/openalex.org\/C138885662","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q5891","display_name":"Philosophy","level":0,"score":0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109\/cvpr52733.2024.00870","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https:\/\/openalex.org\/W1797268635","https:\/\/openalex.org\/W1861492603","https:\/\/openalex.org\/W2911495555","https:\/\/openalex.org\/W2950113871","https:\/\/openalex.org\/W2962770929","https:\/\/openalex.org\/W2964313012","https:\/\/openalex.org\/W2985068832","https:\/\/openalex.org\/W3003162010","https:\/\/openalex.org\/W3009561768","https:\/\/openalex.org\/W3014852036","https:\/\/openalex.org\/W3014859719","https:\/\/openalex.org\/W3034431451","https:\/\/openalex.org\/W3034600949","https:\/\/openalex.org\/W3035316078","https:\/\/openalex.org\/W3035355202","https:\/\/openalex.org\/W3035524453","https:\/\/openalex.org\/W3035574324","https:\/\/openalex.org\/W3035653890","https:\/\/openalex.org\/W3047371217","https:\/\/openalex.org\/W3092775865","https:\/\/openalex.org\/W3122887115","https:\/\/openalex.org\/W3125506761","https:\/\/openalex.org\/W3145450063","https:\/\/openalex.org\/W3166396011","https:\/\/openalex.org\/W3173241699","https:\/\/openalex.org\/W3174194560","https:\/\/openalex.org\/W3176913662","https:\/\/openalex.org\/W3177221875","https:\/\/openalex.org\/W3178406257","https:\/\/openalex.org\/W3181462058","https:\/\/openalex.org\/W3201739204","https:\/\/openalex.org\/W3209830847","https:\/\/openalex.org\/W4214926101","https:\/\/openalex.org\/W4226125322","https:\/\/openalex.org\/W4281485151","https:\/\/openalex.org\/W4286976841","https:\/\/openalex.org\/W4306814521","https:\/\/openalex.org\/W4308163867","https:\/\/openalex.org\/W4312740349","https:\/\/openalex.org\/W4312805760","https:\/\/openalex.org\/W4312933868","https:\/\/openalex.org\/W4386066025","https:\/\/openalex.org\/W4386075639","https:\/\/openalex.org\/W6755102824","https:\/\/openalex.org\/W6763681302","https:\/\/openalex.org\/W6773517458","https:\/\/openalex.org\/W6774314701","https:\/\/openalex.org\/W6774670964","https:\/\/openalex.org\/W6779093361","https:\/\/openalex.org\/W6789645339","https:\/\/openalex.org\/W6789647555","https:\/\/openalex.org\/W6791353385","https:\/\/openalex.org\/W6797179183","https:\/\/openalex.org\/W6810940779","https:\/\/openalex.org\/W6838639034","https:\/\/openalex.org\/W6846000432","https:\/\/openalex.org\/W6846655393"],"related_works":["https:\/\/openalex.org\/W2074502265","https:\/\/openalex.org\/W4214877189","https:\/\/openalex.org\/W2773965352","https:\/\/openalex.org\/W2381179799","https:\/\/openalex.org\/W2980279061","https:\/\/openalex.org\/W2334685461","https:\/\/openalex.org\/W2366718574","https:\/\/openalex.org\/W2359774528","https:\/\/openalex.org\/W4298312966","https:\/\/openalex.org\/W2325697621"],"abstract_inverted_index":{"We":[0],"introduced":[1],"StyleEntity,":[2],"a":[3,34,79],"zero-shot":[4,80],"image":[5],"manipulation":[6,53],"model":[7,22,88],"that":[8],"utilizes":[9],"named":[10,58],"entities":[11,59],"as":[12],"proxies":[13],"during":[14,30,60],"its":[15],"training":[16,36],"phase.":[17,37],"This":[18],"strategy":[19],"enables":[20],"our":[21,72],"to":[23,83],"manipulate":[24],"images":[25],"using":[26],"unseen":[27],"textual":[28],"descriptions":[29],"inference,":[31,61],"all":[32],"within":[33],"single":[35],"Additionally,":[38],"we":[39],"proposed":[40],"an":[41],"inference":[42],"technique":[43],"termed":[44],"Prompt":[45],"Ensemble":[46],"Latent":[47],"Averaging":[48],"(PELA).":[49],"PELA":[50],"averages":[51],"the":[52,64],"directions":[54],"derived":[55],"from":[56],"various":[57],"effectively":[62],"eliminating":[63],"noise":[65],"directions,":[66],"thus":[67],"achieving":[68],"stable":[69],"manipulation.":[70],"In":[71],"experiments,":[73],"StyleEntity":[74],"exhibited":[75],"superior":[76],"performance":[77],"in":[78],"setting":[81],"compared":[82],"other":[84],"methods.":[85],"The":[86],"code,":[87],"weights,":[89],"and":[90],"datasets":[91],"are":[92],"available":[93],"at":[94],"https:\/\/github.com\/feng-zhida\/StyleEntity.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}