{"id":"https://openalex.org/W4416872463","doi":"https://doi.org/10.48550/arxiv.2504.15624","title":"FaceInsight: A Multimodal Large Language Model for Face Perception","display_name":"FaceInsight: A Multimodal Large Language Model for Face Perception","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4416872463","doi":"https://doi.org/10.48550/arxiv.2504.15624"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.15624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15624","pdf_url":"https://arxiv.org/pdf/2504.15624","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.15624","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065742678","display_name":"Jingzhi Li","orcid":"https://orcid.org/0000-0003-1816-9464"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Jingzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luo, Changjiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Changjiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017131366","display_name":"Ruoyu Chen","orcid":"https://orcid.org/0000-0001-7630-7154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ruoyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408716","display_name":"Hua Zhang","orcid":"https://orcid.org/0000-0002-7627-4142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057999649","display_name":"Wenqi Ren","orcid":"https://orcid.org/0000-0001-5481-653X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Wenqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084677085","display_name":"Jianhou Gan","orcid":"https://orcid.org/0000-0002-1287-857X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Jianhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xiaochun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5065742678"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5670999884605408,"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":0.5670999884605408,"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":0.11089999973773956,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10890000313520432,"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/perception","display_name":"Perception","score":0.717199981212616},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6474000215530396},{"id":"https://openalex.org/keywords/face-perception","display_name":"Face perception","score":0.5260999798774719},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.45179998874664307},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.39910000562667847},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3693000078201294},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35190001130104065}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.717199981212616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071999907493591},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6474000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122999787330627},{"id":"https://openalex.org/C161657702","wikidata":"https://www.wikidata.org/wiki/Q529895","display_name":"Face perception","level":3,"score":0.5260999798774719},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.39910000562667847},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35190001130104065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C33640556","wikidata":"https://www.wikidata.org/wiki/Q2459671","display_name":"Categorical perception","level":4,"score":0.3278000056743622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30079999566078186},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2648000121116638}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.15624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15624","pdf_url":"https://arxiv.org/pdf/2504.15624","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.15624","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.15624","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.15624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15624","pdf_url":"https://arxiv.org/pdf/2504.15624","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416872463.pdf","grobid_xml":"https://content.openalex.org/works/W4416872463.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,23],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"demonstrated":[9],"strong":[10],"capabilities":[11],"understanding":[13],"general":[14],"visual":[15,91],"content.":[16],"However,":[17],"these":[18],"general-domain":[19],"MLLMs":[20,117],"perform":[21],"poorly":[22],"face":[24,45,81,107],"perception":[25,46,108],"tasks,":[26],"often":[27],"producing":[28],"inaccurate":[29],"or":[30],"misleading":[31],"responses":[32],"to":[33,61,97],"face-specific":[34],"queries.":[35],"To":[36],"address":[37],"this":[38],"gap,":[39],"we":[40,79],"propose":[41],"FaceInsight,":[42],"the":[43,73,90],"versatile":[44],"MLLM":[47],"that":[48,111],"provides":[49],"fine-grained":[50],"facial":[51,59,70],"information.":[52],"Our":[53],"approach":[54],"introduces":[55],"visual-textual":[56],"alignment":[57],"of":[58,75],"knowledge":[60],"model":[62],"both":[63,119],"uncertain":[64],"dependencies":[65],"and":[66,103,121],"deterministic":[67],"relationships":[68],"among":[69],"information,":[71],"mitigating":[72],"limitations":[74],"language-driven":[76],"reasoning.":[77],"Additionally,":[78],"incorporate":[80],"segmentation":[82],"maps":[83],"as":[84],"an":[85],"auxiliary":[86],"perceptual":[87],"modality,":[88],"enriching":[89],"input":[92],"with":[93],"localized":[94],"structural":[95],"cues":[96],"enhance":[98],"semantic":[99],"understanding.":[100],"Comprehensive":[101],"experiments":[102],"analyses":[104],"across":[105],"three":[106],"tasks":[109],"demonstrate":[110],"FaceInsight":[112],"consistently":[113],"outperforms":[114],"nine":[115],"compared":[116],"under":[118],"training-free":[120],"fine-tuned":[122],"settings.":[123]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}