{"id":"https://openalex.org/W4415708768","doi":"https://doi.org/10.1109/icme59968.2025.11209392","title":"MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach","display_name":"MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708768","doi":"https://doi.org/10.1109/icme59968.2025.11209392"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5108313260","display_name":"Xin Zhang","orcid":"https://orcid.org/0009-0004-7590-8600"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089749731","display_name":"Siting Huang","orcid":"https://orcid.org/0000-0002-4230-7735"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siting Huang","raw_affiliation_strings":["Xi’an Jiaotong University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018721","display_name":"Xiangyang Luo","orcid":"https://orcid.org/0000-0001-6062-2950"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Luo","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056844117","display_name":"Yifan Xie","orcid":"https://orcid.org/0009-0002-3225-9220"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Xie","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055989750","display_name":"Weijiang Yu","orcid":"https://orcid.org/0000-0002-7449-3093"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijiang Yu","raw_affiliation_strings":["Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027050251","display_name":"Heng Chang","orcid":"https://orcid.org/0000-0002-4978-8041"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Chang","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031311274","display_name":"Fei Ma","orcid":"https://orcid.org/0009-0002-5388-9125"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34656318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5260999798774719,"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":0.5260999798774719,"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":0.39149999618530273,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7081000208854675},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7038000226020813},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6963000297546387},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5769000053405762},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4666999876499176},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40950000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7081000208854675},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7038000226020813},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C2777359053","wikidata":"https://www.wikidata.org/wiki/Q2463823","display_name":"Face-to-face","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C144501496","wikidata":"https://www.wikidata.org/wiki/Q5533489","display_name":"Genome editing","level":4,"score":0.28360000252723694},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2964325922","https://openalex.org/W3034521057","https://openalex.org/W3096831136","https://openalex.org/W3174194560","https://openalex.org/W3217030260","https://openalex.org/W4214622647","https://openalex.org/W4312933868","https://openalex.org/W4376851211","https://openalex.org/W4385271281","https://openalex.org/W4386075893","https://openalex.org/W4386076215","https://openalex.org/W4387968172","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4393148714","https://openalex.org/W4402727797","https://openalex.org/W4403780774","https://openalex.org/W4409366558"],"related_works":[],"abstract_inverted_index":{"Face":[0],"editing":[1,58,81,111,128,139],"modifies":[2],"the":[3,41,105,108,116,133],"appearance":[4],"of":[5,16,37,43,84,115,137],"face,":[6],"which":[7,60],"plays":[8],"a":[9,55,73,78],"key":[10],"role":[11],"in":[12,26],"customization":[13],"and":[14,46,77,92,102,130,135],"enhancement":[15],"personal":[17],"images.":[18],"Although":[19],"much":[20],"work":[21],"have":[22],"achieved":[23],"remarkable":[24],"success":[25],"text-driven":[27,56],"face":[28,32,57,68,80,94,110,127,138],"editing,":[29],"they":[30],"still":[31],"significant":[33],"challenges":[34],"as":[35],"none":[36],"them":[38],"simultaneously":[39],"fulfill":[40],"characteristics":[42],"diversity,":[44],"controllability":[45,114,134],"flexibility.":[47],"To":[48],"address":[49],"this":[50],"challenge,":[51],"we":[52],"propose":[53],"MuseFace,":[54],"framework,":[59,106],"relies":[61],"solely":[62],"on":[63],"text":[64,91],"prompt":[65],"to":[66,104],"enable":[67],"editing.":[69,95],"Specifically,":[70],"MuseFace":[71,145],"integrates":[72],"Text-to-Mask":[74,97],"diffusion":[75,98],"model":[76,99,112],"semantic-aware":[79,109],"model,":[82],"capable":[83],"directly":[85],"generating":[86],"fine-grained":[87,122],"semantic":[88,123],"masks":[89],"from":[90],"performing":[93],"The":[96],"provides":[100],"diversity":[101],"flexibility":[103,136],"while":[107],"ensures":[113],"framework.":[117],"Our":[118],"framework":[119],"can":[120],"create":[121],"masks,":[124],"making":[125],"precise":[126],"possible,":[129],"significantly":[131],"enhancing":[132],"models.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"that":[144],"achieves":[146],"superior":[147],"high-fidelity":[148],"performance.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}