{"id":"https://openalex.org/W4401210548","doi":"https://doi.org/10.1109/tcsvt.2024.3436900","title":"Toward Open-World Text-Driven Face Generation and Manipulation via StyleGAN3","display_name":"Toward Open-World Text-Driven Face Generation and Manipulation via StyleGAN3","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4401210548","doi":"https://doi.org/10.1109/tcsvt.2024.3436900"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3436900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3436900","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5100731668","display_name":"Zonglin Li","orcid":"https://orcid.org/0000-0002-4181-310X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zonglin Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111365315","display_name":"Zhaoxin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxin Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102842796","display_name":"Peiqiang Liu","orcid":"https://orcid.org/0000-0002-4774-7094"},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiqiang Liu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong Technology and Business University, Yantai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong Technology and Business University, Yantai, China","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957268","display_name":"Qinglin Liu","orcid":"https://orcid.org/0000-0002-2408-3344"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101501338","display_name":"Xin Sun","orcid":"https://orcid.org/0000-0002-2125-2595"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Sun","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100731668"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.98,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76375578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"34","issue":"12","first_page":"12862","last_page":"12872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"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/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"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":0.9656000137329102,"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/T12290","display_name":"Human Motion and Animation","score":0.9557999968528748,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6231153011322021},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5165916681289673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46352630853652954},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4209189713001251},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10321015119552612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6231153011322021},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5165916681289673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46352630853652954},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4209189713001251},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10321015119552612},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3436900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3436900","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5835972371","display_name":null,"funder_award_id":"62072141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2194775991","https://openalex.org/W2341528187","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963163163","https://openalex.org/W2963861381","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W2969985801","https://openalex.org/W2985068832","https://openalex.org/W3014852036","https://openalex.org/W3014859719","https://openalex.org/W3026885507","https://openalex.org/W3034521057","https://openalex.org/W3035316078","https://openalex.org/W3035574324","https://openalex.org/W3035693354","https://openalex.org/W3147954272","https://openalex.org/W3150608155","https://openalex.org/W3173102319","https://openalex.org/W3173241699","https://openalex.org/W3174194560","https://openalex.org/W3174807077","https://openalex.org/W3176913662","https://openalex.org/W3178406257","https://openalex.org/W3196587153","https://openalex.org/W3201739204","https://openalex.org/W3208722310","https://openalex.org/W3209830847","https://openalex.org/W3217427959","https://openalex.org/W4205219932","https://openalex.org/W4213186350","https://openalex.org/W4214926101","https://openalex.org/W4296079585","https://openalex.org/W4312477574","https://openalex.org/W4312984277","https://openalex.org/W4313172221","https://openalex.org/W4320900831","https://openalex.org/W4375928651","https://openalex.org/W4386066025","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6677618333","https://openalex.org/W6684191040","https://openalex.org/W6713645886","https://openalex.org/W6755102824","https://openalex.org/W6765779288","https://openalex.org/W6766196973","https://openalex.org/W6767164110","https://openalex.org/W6767384525","https://openalex.org/W6787060426","https://openalex.org/W6791353385","https://openalex.org/W6794739714","https://openalex.org/W6804649961","https://openalex.org/W6840753732"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Most":[0],"existing":[1],"text-driven":[2],"face":[3,31,86,95],"image":[4,47,96],"generation":[5],"and":[6,20,48,83,103,159],"manipulation":[7,214],"methods":[8,24,35],"are":[9],"based":[10],"on":[11],"StyleGAN2,":[12],"which":[13,50,139,216],"is":[14,97],"inherently":[15],"limited":[16],"to":[17,26,41,81,100,197,209,218,222],"aligned":[18,102],"faces":[19],"therefore":[21],"makes":[22],"these":[23,34,69],"fail":[25],"preserve":[27],"the":[28,43,46,58,73,77,85,93,104,124,132,152,162,182,199,228,237],"highly":[29],"variable":[30],"placement.":[32],"Additionally,":[33],"directly":[36],"leverage":[37],"a":[38,137,142,172,187,193,205,211],"pairwise":[39],"loss":[40],"learn":[42],"correspondence":[44],"between":[45],"text,":[49,184],"can":[51],"not":[52,98],"handle":[53],"complex":[54,178],"text":[55,59,105],"descriptions,":[56],"e.g.,":[57,92],"with":[60,145,192],"multiple":[61,64,108],"captions":[62],"describes":[63],"facial":[65],"attributes.":[66],"To":[67,110,176],"address":[68],"issues,":[70],"we":[71,113,185,203],"explore":[72],"feasibility":[74],"of":[75,154,231],"applying":[76],"more":[78,173],"advanced":[79],"StyleGAN3":[80,156],"generate":[82],"manipulate":[84],"images":[87],"in":[88],"an":[89,116],"Open-World":[90],"setup,":[91],"target":[94],"required":[99],"be":[101],"description":[106],"contains":[107],"captions.":[109],"this":[111],"end,":[112],"first":[114],"design":[115],"improved":[117],"iterative":[118],"refinement":[119],"strategy":[120,196],"that":[121,161],"adaptively":[122],"predicts":[123],"generator":[125,144],"weight":[126],"offsets":[127],"rather":[128],"than":[129],"residuals":[130],"for":[131],"inverted":[133],"latent":[134,157,213],"code":[135],"via":[136],"hypernetwork,":[138],"efficiently":[140],"finds":[141],"desired":[143],"no":[146],"image-specific":[147],"optimization.":[148],"We":[149],"further":[150],"analyze":[151],"disentanglement":[153],"different":[155,223],"spaces":[158],"demonstrate":[160,227],"<inline-formula":[163],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[165],"<tex-math":[166],"notation=\"LaTeX\">${\\mathcal":[167],"{S}}$":[168],"</tex-math></inline-formula>":[169],"space":[170],"learns":[171,217],"semantically-disentangled":[174],"representation.":[175],"enable":[177],"edits":[179],"mentioned":[180],"by":[181],"multi-caption":[183],"propose":[186],"cross-modal":[188],"feature":[189],"filtration":[190],"module":[191],"probability":[194],"adaptation":[195],"capture":[198],"image-text":[200],"correspondences.":[201],"Finally,":[202],"incorporate":[204],"channel-wise":[206],"attention":[207],"mechanism":[208],"obtain":[210],"global":[212],"direction,":[215],"assign":[219],"importance":[220],"weights":[221],"channels.":[224],"Extensive":[225],"experiments":[226],"superior":[229],"performance":[230],"our":[232],"proposed":[233],"method":[234],"compared":[235],"against":[236],"state-of-the-art":[238],"methods.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}