{"id":"https://openalex.org/W6929340669","doi":"https://doi.org/10.48550/arxiv.2505.24214","title":"Benchmarking Foundation Models for Zero-Shot Biometric Tasks","display_name":"Benchmarking Foundation Models for Zero-Shot Biometric Tasks","publication_year":2025,"publication_date":"2025-05-30","ids":{"openalex":"https://openalex.org/W6929340669","doi":"https://doi.org/10.48550/arxiv.2505.24214"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.24214","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24214","pdf_url":"https://arxiv.org/pdf/2505.24214","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.24214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011798787","display_name":"Redwan Sony","orcid":"https://orcid.org/0000-0002-0155-1993","observed_orcids":["https://orcid.org/0000-0002-0155-1993"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sony, Redwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093917373","display_name":"Parisa Farmanifard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farmanifard, Parisa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alzwairy, Hamzeh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alzwairy, Hamzeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002382519","display_name":"Nitish Shukla","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shukla, Nitish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ross, Arun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ross, Arun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"primary_topic":{"id":"https://openalex.org/T10828","display_name":"Biometric Identification and Security","score":0.736299991607666,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10828","display_name":"Biometric Identification and Security","score":0.736299991607666,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.25589999556541443,"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":0.0012000000569969416,"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/foundation-models","display_name":"foundation models","score":0.8190000057220459},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9570000171661377},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.777999997138977},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.9150000214576721},{"id":"https://openalex.org/keywords/biometric-recognition","display_name":"biometric identification","score":0.9399999976158142},{"id":"https://openalex.org/keywords/face-verification","display_name":"face verification","score":0.9950000047683716},{"id":"https://openalex.org/keywords/iris-recognition","display_name":"iris recognition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/spoofing-detection","display_name":"anti-spoofing","score":0.9599999785423279},{"id":"https://openalex.org/keywords/deepfake-detection","display_name":"deepfake detection","score":0.890999972820282},{"id":"https://openalex.org/keywords/face-manipulation-detection","display_name":"face manipulation detection","score":0.9039999842643738},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.3440000116825104},{"id":"https://openalex.org/keywords/pre-trained-embeddings","display_name":"pre-trained embeddings","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.92330002784729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6495000123977661},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.45969998836517334},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C112356035","wikidata":"https://www.wikidata.org/wiki/Q1672722","display_name":"Iris recognition","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C79540074","wikidata":"https://www.wikidata.org/wiki/Q3269465","display_name":"Keystroke dynamics","level":4,"score":0.3059999942779541},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.24214","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24214","pdf_url":"https://arxiv.org/pdf/2505.24214","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.24214","doi":"https://doi.org/10.48550/arxiv.2505.24214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.24214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.24214","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24214","pdf_url":"https://arxiv.org/pdf/2505.24214","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Gender equality","score":0.6029874086380005,"id":"https://metadata.un.org/sdg/5"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,19,59,100,126,133,141,152,170,234,242],"foundation":[3,114],"models,":[4],"particularly":[5],"Vision-Language":[6],"Models":[7,13],"(VLMs)":[8],"and":[9,39,56,64,73,83,91,96,214,221],"Multi-modal":[10],"Large":[11],"Language":[12],"(MLLMs),":[14],"has":[15],"redefined":[16],"the":[17,54,71,131,156,160,168,173,180,232,239],"frontiers":[18],"artificial":[20],"intelligence,":[21],"enabling":[22],"remarkable":[23],"generalization":[24],"across":[25,66],"diverse":[26,120],"tasks":[27,69,122],"with":[28,123,225],"minimal":[29],"or":[30],"no":[31],"supervision.":[32],"Yet,":[33],"their":[34],"potential":[35,233],"in":[36,105,130,159,237],"biometric":[37,68,79,121,217],"recognition":[38],"analysis":[40],"remains":[41],"relatively":[42],"underexplored.":[43],"In":[44,167],"this":[45,106],"work,":[46],"we":[47,190],"introduce":[48],"a":[49,136,147,194],"comprehensive":[50],"benchmark":[51],"that":[52,110,192],"evaluates":[53],"zero-shot":[55],"few-shot":[57],"performance":[58],"state-of-the-art":[60],"publicly":[61],"available":[62],"VLMs":[63,102],"MLLMs":[65],"six":[67],"spanning":[70],"face":[72,76,92,134],"iris":[74,85,171],"modalities:":[75],"verification,":[77,135],"soft":[78,216],"attribute":[80],"prediction":[81],"(gender":[82],"race),":[84],"recognition,":[86,172],"presentation":[87],"attack":[88],"detection":[89,94,205],"(PAD),":[90],"manipulation":[93],"(morphs":[95],"deepfakes).":[97],"A":[98],"total":[99],"41":[101],"were":[103],"used":[104,118],"evaluation.":[107],"Experiments":[108],"show":[109,191],"embeddings":[111,200],"from":[112,223],"these":[113,199],"models":[115,236],"can":[116,201],"be":[117],"for":[119,206,212],"varying":[124],"degrees":[125],"success.":[127],"For":[128],"example,":[129],"case":[132,169],"True":[137],"Match":[138,149],"Rate":[139,150],"(TMR)":[140],"96.77":[142],"percent":[143,154,177,185],"was":[144,183],"obtained":[145],"at":[146,175],"False":[148],"(FMR)":[151],"1":[153,176],"on":[155,179],"Labeled":[157],"Face":[158],"Wild":[161],"(LFW)":[162],"dataset,":[163],"without":[164,186],"any":[165,187],"fine-tuning.":[166,188],"TMR":[174],"FMR":[178],"IITD-R-Full":[181],"dataset":[182],"97.55":[184],"Further,":[189],"applying":[193],"simple":[195],"classifier":[196],"head":[197],"to":[198],"help":[202],"perform":[203],"DeepFake":[204],"faces,":[207],"Presentation":[208],"Attack":[209],"Detection":[210],"(PAD)":[211],"irides,":[213],"extract":[215],"attributes":[218],"like":[219],"gender":[220],"ethnicity":[222],"faces":[224],"reasonably":[226],"high":[227],"accuracy.":[228],"This":[229],"work":[230],"reiterates":[231],"pretrained":[235],"achieving":[238],"long-term":[240],"vision":[241],"Artificial":[243],"General":[244],"Intelligence.":[245]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}