{"id":"https://openalex.org/W7131119065","doi":"https://doi.org/10.1109/iccvw69036.2025.00390","title":"FaceLLM: A Multimodal Large Language Model for Face Understanding","display_name":"FaceLLM: A Multimodal Large Language Model for Face Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131119065","doi":"https://doi.org/10.1109/iccvw69036.2025.00390"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5042428131","display_name":"Hatef Otroshi Shahreza","orcid":"https://orcid.org/0000-0002-8199-0098"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hatef Otroshi Shahreza","raw_affiliation_strings":["Idiap Research Institute,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126628353","display_name":"S\u00e9bastien Marcel","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Marcel","raw_affiliation_strings":["Idiap Research Institute,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3736","last_page":"3746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9682000279426575,"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":0.9682000279426575,"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/T10057","display_name":"Face and Expression Recognition","score":0.015699999406933784,"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/T11094","display_name":"Face Recognition and Perception","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5913000106811523},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5478000044822693},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.48179998993873596},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4325000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032999753952026},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27140000462532043}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5635796189308167,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F2824300450","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694"},{"id":"https://openalex.org/F4320321942","display_name":"Hasler Stiftung","ror":"https://ror.org/04m3t9183"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1643185111","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W1982209341","https://openalex.org/W2003092530","https://openalex.org/W2404498690","https://openalex.org/W2463631526","https://openalex.org/W2510725918","https://openalex.org/W2592232824","https://openalex.org/W2663800299","https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2946566846","https://openalex.org/W2963100452","https://openalex.org/W2963314072","https://openalex.org/W2982058372","https://openalex.org/W2998428583","https://openalex.org/W3015469128","https://openalex.org/W3034521057","https://openalex.org/W3034713808","https://openalex.org/W3120485916","https://openalex.org/W3138516171","https://openalex.org/W4313130906","https://openalex.org/W4385820037","https://openalex.org/W4386076045","https://openalex.org/W4386076638","https://openalex.org/W4392158419","https://openalex.org/W4394593171","https://openalex.org/W4400527853","https://openalex.org/W4402716216","https://openalex.org/W4402716330","https://openalex.org/W4402727885","https://openalex.org/W4402916438","https://openalex.org/W4402917263","https://openalex.org/W4402979749","https://openalex.org/W4403420692","https://openalex.org/W4403792097","https://openalex.org/W4403889519","https://openalex.org/W4405595839","https://openalex.org/W4409262674","https://openalex.org/W4409917679","https://openalex.org/W4410974031","https://openalex.org/W4413147355","https://openalex.org/W4413555882","https://openalex.org/W4415796627","https://openalex.org/W7125212912"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1,73],"language":[2,74,158],"models":[3,159,179],"(MLLMs)":[4],"have":[5],"shown":[6],"remarkable":[7],"performance":[8,138],"in":[9,33,183],"vision-language":[10],"tasks.":[11],"However,":[12],"existing":[13],"MLLMs":[14,54,140],"are":[15,180],"primarily":[16],"trained":[17,76],"on":[18,26,106,141],"generic":[19],"datasets,":[20],"limiting":[21],"their":[22],"ability":[23],"to":[24,56,100],"reason":[25],"domain-specific":[27],"visual":[28],"cues":[29],"such":[30],"as":[31],"those":[32],"facial":[34,44,79],"images.":[35],"In":[36,65],"particular,":[37],"tasks":[38,144],"that":[39,94,134],"require":[40],"detailed":[41],"understanding":[42],"of":[43,59,121,139,154],"structure,":[45],"expression,":[46,124],"emotion,":[47],"and":[48,128,145,164,176],"demographic":[49],"features":[50],"remain":[51],"underexplored":[52],"by":[53],"due":[55],"the":[57,84,109,137,152,184],"lack":[58],"large-scale":[60],"an-notated":[61],"face":[62],"image-text":[63],"datasets.":[64],"this":[66],"work,":[67],"we":[68,87],"introduce":[69],"FaceLLM,":[70],"a":[71,89,118,166],"multimodal":[72,171],"model":[75],"specifically":[77],"for":[78,160,168],"image":[80],"understanding.":[81],"To":[82],"construct":[83],"training":[85],"data,":[86],"propose":[88],"novel":[90],"weakly":[91],"supervised":[92],"pipeline":[93],"uses":[95],"ChatGPT":[96],"with":[97],"attribute-aware":[98],"prompts":[99],"generate":[101],"high-quality":[102],"question-answer":[103],"pairs":[104],"based":[105],"images":[107],"from":[108],"FairFace":[110],"dataset.":[111],"The":[112],"resulting":[113],"corpus,":[114],"called":[115],"FairFaceGPT,":[116],"covers":[117],"diverse":[119],"set":[120],"attributes":[122],"including":[123],"pose,":[125],"skin":[126],"texture,":[127],"forensic":[129],"information.":[130],"Our":[131],"experiments":[132],"demonstrate":[133],"FaceLLM":[135,178],"improves":[136],"various":[142],"face-centric":[143],"achieves":[146],"state-of-the-art":[147],"performance.":[148],"This":[149],"work":[150],"high-lights":[151],"potential":[153],"synthetic":[155],"supervision":[156],"via":[157],"building":[161],"domain-specialized":[162],"MLLMs,":[163],"sets":[165],"precedent":[167],"trustworthy,":[169],"human-centric":[170],"AI":[172],"systems.":[173],"FairFaceGPT":[174],"dataset":[175],"pretrained":[177],"publicly":[181],"available":[182],"project":[185],"page.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}