{"id":"https://openalex.org/W2165421528","doi":"https://doi.org/10.1109/tcsvt.2009.2022694","title":"Audio-Guided Video-Based Face Recognition","display_name":"Audio-Guided Video-Based Face Recognition","publication_year":2009,"publication_date":"2009-07-01","ids":{"openalex":"https://openalex.org/W2165421528","doi":"https://doi.org/10.1109/tcsvt.2009.2022694","mag":"2165421528"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2009.2022694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2009.2022694","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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/A5089058945","display_name":"Xiaoou Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoou Tang","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634431","display_name":"Zhifeng Li","orcid":"https://orcid.org/0000-0002-9653-7907"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Li","raw_affiliation_strings":["Human-Computer Communications Laboratory, Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089058945"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.9842,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.80217708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"7","first_page":"955","last_page":"964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9991000294685364,"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/T10057","display_name":"Face and Expression Recognition","score":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9901000261306763,"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/T13579","display_name":"Image and Video Stabilization","score":0.9890000224113464,"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/computer-science","display_name":"Computer science","score":0.7934162616729736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6835616230964661},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5987377166748047},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5776996612548828},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.565386176109314},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5172577500343323},{"id":"https://openalex.org/keywords/video-post-processing","display_name":"Video post-processing","score":0.5052588582038879},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5014784336090088},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49262624979019165},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.49252447485923767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4899729788303375},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.44223278760910034},{"id":"https://openalex.org/keywords/block-matching-algorithm","display_name":"Block-matching algorithm","score":0.4409349262714386},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07443413138389587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934162616729736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6835616230964661},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5987377166748047},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5776996612548828},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.565386176109314},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5172577500343323},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.5052588582038879},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5014784336090088},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49262624979019165},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.49252447485923767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4899729788303375},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.44223278760910034},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.4409349262714386},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07443413138389587},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2009.2022694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2009.2022694","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.9057","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.9057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.se.cuhk.edu.hk/~hccl/publications/pub/Audio-Guided Video-Based Face Recognition.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1527240141","https://openalex.org/W1820849028","https://openalex.org/W2062104878","https://openalex.org/W2088900896","https://openalex.org/W2098693229","https://openalex.org/W2100846437","https://openalex.org/W2102734279","https://openalex.org/W2104442254","https://openalex.org/W2104462292","https://openalex.org/W2115758897","https://openalex.org/W2117553576","https://openalex.org/W2120954940","https://openalex.org/W2121199413","https://openalex.org/W2121647436","https://openalex.org/W2126344677","https://openalex.org/W2127587936","https://openalex.org/W2130418330","https://openalex.org/W2134849720","https://openalex.org/W2135962003","https://openalex.org/W2141425367","https://openalex.org/W2143103810","https://openalex.org/W2143162151","https://openalex.org/W2144002622","https://openalex.org/W2144119003","https://openalex.org/W2144854846","https://openalex.org/W2148191008","https://openalex.org/W2152826865","https://openalex.org/W2155797925","https://openalex.org/W2162581194","https://openalex.org/W2164568552","https://openalex.org/W2164617909","https://openalex.org/W2167144347","https://openalex.org/W2180187800","https://openalex.org/W6631618440","https://openalex.org/W6675479722","https://openalex.org/W6680266532","https://openalex.org/W6680911227","https://openalex.org/W6684271745"],"related_works":["https://openalex.org/W1574724839","https://openalex.org/W1623638113","https://openalex.org/W2032827369","https://openalex.org/W2213155192","https://openalex.org/W2187171999","https://openalex.org/W181787362","https://openalex.org/W2140582509","https://openalex.org/W3034776505","https://openalex.org/W2406608628","https://openalex.org/W2096476311"],"abstract_inverted_index":{"In":[0,33],"this":[1],"paper,":[2],"we":[3,61],"develop":[4,62],"a":[5,25,30,139],"new":[6,64,154],"video-to-video":[7],"face":[8,103],"recognition":[9],"algorithm.":[10],"The":[11,129],"major":[12],"advantage":[13,37],"of":[14,38,42,133,152],"the":[15,39,45,50,54,102,126,134,145,150],"video-based":[16],"method":[17,130],"is":[18,22,90,119],"that":[19],"more":[20],"information":[21,43,136],"available":[23],"in":[24,29,44,138],"video":[26,46,80,85,109,140],"sequence":[27,47,81,86],"than":[28],"single":[31],"image.":[32],"order":[34],"to":[35],"take":[36],"large":[40],"amount":[41],"and":[48,57,68,76,96,108],"at":[49],"same":[51],"time":[52],"overcome":[53],"processing":[55],"speed":[56],"data":[58],"size":[59],"problems,":[60],"several":[63],"techniques":[65],"including":[66],"temporal":[67,95],"spatial":[69,97],"frame":[70],"synchronization,":[71,98],"multilevel":[72,112],"discriminant":[73,113],"subspace":[74,114],"analysis,":[75],"multiclassifier":[77,117],"integration":[78,118],"for":[79,87,121],"processing.":[82],"An":[83],"aligned":[84],"each":[88],"person":[89],"first":[91],"obtained":[92],"by":[93],"applying":[94],"which":[99],"effectively":[100],"establishes":[101],"correspondence":[104],"using":[105],"both":[106],"audio":[107],"information;":[110],"then":[111],"analysis":[115,123],"or":[116],"employed":[120],"further":[122],"based":[124],"on":[125,144],"synchronized":[127],"sequence.":[128,141],"preserves":[131],"most":[132],"temporal-spatial":[135],"contained":[137],"Extensive":[142],"experiments":[143],"XM2VTS":[146],"database":[147],"clearly":[148],"show":[149],"superiority":[151],"our":[153],"algorithms":[155],"with":[156],"near-perfect":[157],"classification":[158],"results":[159],"(99.3%)":[160],"obtained.":[161]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}