{"id":"https://openalex.org/W3000682400","doi":"https://doi.org/10.1109/icb45273.2019.8987249","title":"Likelihood Ratio based Loss to finetune CNNs for Very Low Resolution Face Verification","display_name":"Likelihood Ratio based Loss to finetune CNNs for Very Low Resolution Face Verification","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W3000682400","doi":"https://doi.org/10.1109/icb45273.2019.8987249","mag":"3000682400"},"language":"en","primary_location":{"id":"doi:10.1109/icb45273.2019.8987249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icb45273.2019.8987249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Biometrics (ICB)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.utwente.nl/en/publications/6c85de98-5ff4-4ae7-abba-91895776fa67","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456047","display_name":"Dan Zeng","orcid":"https://orcid.org/0000-0002-9036-7791"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dan Zeng","raw_affiliation_strings":["University of Twente,Faculty of EEMCS,Enschede,the Netherlands","Faculty of EEMCS, University of Twente, Enschede, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente,Faculty of EEMCS,Enschede,the Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Faculty of EEMCS, University of Twente, Enschede, the Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031138348","display_name":"Raymond Veldhuis","orcid":"https://orcid.org/0000-0002-0381-5235"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Raymond Veldhuis","raw_affiliation_strings":["University of Twente,Faculty of EEMCS,Enschede,the Netherlands","Faculty of EEMCS, University of Twente, Enschede, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente,Faculty of EEMCS,Enschede,the Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Faculty of EEMCS, University of Twente, Enschede, the Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108021253","display_name":"Luuk Spreeuwers","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Luuk Spreeuwers","raw_affiliation_strings":["University of Twente,Faculty of EEMCS,Enschede,the Netherlands","Faculty of EEMCS, University of Twente, Enschede, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente,Faculty of EEMCS,Enschede,the Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"Faculty of EEMCS, University of Twente, Enschede, the Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085914001","display_name":"Qijun Zhao","orcid":"https://orcid.org/0000-0003-4651-7163"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Zhao","raw_affiliation_strings":["Sichuan University,College of Computer Science,China","College of Computer Science, Sichuan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,China","institution_ids":["https://openalex.org/I24185976"]},{"raw_affiliation_string":"College of Computer Science, Sichuan University, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1984,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55840057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":1.0,"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":1.0,"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":0.9988999962806702,"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/T10828","display_name":"Biometric Identification and Security","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9586232900619507},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.7398957014083862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.704707145690918},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6724951267242432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6570644974708557},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.6334007382392883},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6132383346557617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6028084754943848},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5146694779396057},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.45574498176574707},{"id":"https://openalex.org/keywords/low-resolution","display_name":"Low resolution","score":0.449226975440979},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4180898368358612},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.3050873875617981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29617929458618164},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.21654626727104187}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9586232900619507},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.7398957014083862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704707145690918},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6724951267242432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6570644974708557},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.6334007382392883},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6132383346557617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6028084754943848},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5146694779396057},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.45574498176574707},{"id":"https://openalex.org/C3019883945","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Low resolution","level":3,"score":0.449226975440979},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4180898368358612},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.3050873875617981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29617929458618164},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.21654626727104187},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icb45273.2019.8987249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icb45273.2019.8987249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Biometrics (ICB)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/6c85de98-5ff4-4ae7-abba-91895776fa67","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/6c85de98-5ff4-4ae7-abba-91895776fa67","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zeng, D, Veldhuis, R, Spreeuwers, L & Zhao, Q 2019, Likelihood Ratio based Loss to finetune CNNs for Very Low Resolution Face Verification. in 2019 International Conference on Biometrics, ICB 2019., 8987249, International Conference on Biometrics, ICB, vol. 2019, IEEE, Piscataway, NJ, 12th IAPR International Conference on Biometrics, ICB 2019, Hersonissos, Crete, Greece, 4/06/19. https://doi.org/10.1109/ICB45273.2019.8987249","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/fd13f50a-4432-4e6b-8207-a3b623032c45","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/fd13f50a-4432-4e6b-8207-a3b623032c45","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zeng, D, Veldhuis, R N J, Spreeuwers, L & Zhao, Q 2019, Likelihood Ratio based Loss to fine tune CNNs for Very Low Resolution Face Verification. in M Nixon & P J Flynn (eds), The 12th IAPR International Conference on Biometrics (ICB 2019). pp. 1, 12th IAPR International Conference on Biometrics, ICB 2019, Hersonissos, Crete, Greece, 4/06/19.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:ris.utwente.nl:publications/6c85de98-5ff4-4ae7-abba-91895776fa67","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85081054029&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:ut:oai:ris.utwente.nl:publications/fd13f50a-4432-4e6b-8207-a3b623032c45","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/likelihood-ratio-based-loss-to-fine-tune-cnns-for-very-low-resolution-face-verification(fd13f50a-4432-4e6b-8207-a3b623032c45).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 12th IAPR International Conference on Biometrics (ICB 2019)","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/6c85de98-5ff4-4ae7-abba-91895776fa67","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/6c85de98-5ff4-4ae7-abba-91895776fa67","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zeng, D, Veldhuis, R, Spreeuwers, L & Zhao, Q 2019, Likelihood Ratio based Loss to finetune CNNs for Very Low Resolution Face Verification. in 2019 International Conference on Biometrics, ICB 2019., 8987249, International Conference on Biometrics, ICB, vol. 2019, IEEE, Piscataway, NJ, 12th IAPR International Conference on Biometrics, ICB 2019, Hersonissos, Crete, Greece, 4/06/19. https://doi.org/10.1109/ICB45273.2019.8987249","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1509966554","https://openalex.org/W1686810756","https://openalex.org/W1976948919","https://openalex.org/W1983781364","https://openalex.org/W2033419168","https://openalex.org/W2054515210","https://openalex.org/W2055492845","https://openalex.org/W2067023690","https://openalex.org/W2096027770","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2112724657","https://openalex.org/W2137659841","https://openalex.org/W2139340143","https://openalex.org/W2144172034","https://openalex.org/W2155759509","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2510798689","https://openalex.org/W2520774990","https://openalex.org/W2602265372","https://openalex.org/W2752042386","https://openalex.org/W2784163702","https://openalex.org/W2784874046","https://openalex.org/W2786817236","https://openalex.org/W2792481260","https://openalex.org/W2899282387","https://openalex.org/W2912990735","https://openalex.org/W2962898354","https://openalex.org/W2963102887","https://openalex.org/W2963466847","https://openalex.org/W2963656735","https://openalex.org/W2964350391","https://openalex.org/W2969985801","https://openalex.org/W2994340921","https://openalex.org/W3099206234","https://openalex.org/W3103152812","https://openalex.org/W6630649318","https://openalex.org/W6635552349","https://openalex.org/W6637373629","https://openalex.org/W6681239517","https://openalex.org/W6684191040","https://openalex.org/W6694260854","https://openalex.org/W6725456406","https://openalex.org/W6726946684","https://openalex.org/W6735013348","https://openalex.org/W6748010250"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W2211301776","https://openalex.org/W1995418324","https://openalex.org/W2275475525","https://openalex.org/W2060905804","https://openalex.org/W3009759344"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,55,98],"propose":[4,56],"a":[5,57,78],"likelihood":[6,62],"ratio":[7,63],"based":[8,60],"loss":[9,16,22,58,96],"for":[10,86],"very":[11,104],"low-resolution":[12,105],"face":[13,106],"verification.":[14,88],"Existing":[15],"functions":[17],"either":[18],"improve":[19],"the":[20,50,73,91,94,103,114,119,122,135],"softmax":[21],"to":[23,40,48,71,101,124],"learn":[24],"large-margin":[25],"facial":[26],"features":[27],"or":[28],"impose":[29],"Euclidean":[30],"margin":[31],"constraints":[32],"between":[33],"image":[34],"pairs.":[35],"These":[36],"methods":[37],"are":[38],"proved":[39],"be":[41,125],"better":[42],"than":[43],"traditional":[44],"softmax,":[45],"but":[46],"fail":[47],"guarantee":[49],"best":[51],"discrimination":[52],"features.":[53],"Therefore,":[54],"function":[59],"on":[61,113],"classifier,":[64],"an":[65],"optimal":[66],"classifier":[67],"in":[68],"Neyman-Pearson":[69],"sense,":[70],"give":[72],"highest":[74],"verification":[75],"rate":[76],"at":[77],"given":[79],"false":[80],"accept":[81],"rate,":[82],"which":[83],"is":[84],"suitable":[85],"biometrics":[87],"To":[89],"verify":[90],"efficacy":[92],"of":[93,121],"proposed":[95,136],"function,":[97],"apply":[99],"it":[100],"address":[102],"recognition":[107],"problem.":[108],"We":[109],"conduct":[110],"extensive":[111],"experiments":[112],"challenging":[115],"SCface":[116],"dataset":[117],"with":[118],"resolution":[120],"faces":[123],"recognized":[126],"below":[127],"16":[128],"\u00d7":[129],"16.":[130],"The":[131],"results":[132],"show":[133],"that":[134],"approach":[137],"outperforms":[138],"state-of-the-art":[139],"methods.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}