{"id":"https://openalex.org/W2120945552","doi":"https://doi.org/10.1109/icassp.2009.4959999","title":"Audiovisual celebrity recognition in unconstrained web videos","display_name":"Audiovisual celebrity recognition in unconstrained web videos","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2120945552","doi":"https://doi.org/10.1109/icassp.2009.4959999","mag":"2120945552"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5015357395","display_name":"Mehmet Emre Sargin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Emre Sargin","raw_affiliation_strings":["Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","Google, Inc., Mountain View, CA, USA","Department of Electrical and Computer Engineering, University of California,\uc2a0Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California,\uc2a0Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026953796","display_name":"Hrishikesh Aradhye","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hrishikesh Aradhye","raw_affiliation_strings":["Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":["Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101521257","display_name":"Ming Zhao","orcid":"https://orcid.org/0000-0002-1310-6766"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Zhao","raw_affiliation_strings":["Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1977","last_page":"1980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9980999827384949,"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":0.856234073638916},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6967981457710266},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.679872989654541},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6342108249664307},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5723320245742798},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.5317484140396118},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45481881499290466},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43422698974609375},{"id":"https://openalex.org/keywords/video-content-analysis","display_name":"Video content analysis","score":0.43153905868530273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38456088304519653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3762613534927368},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30595508217811584},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.299055814743042},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.26164841651916504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.856234073638916},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6967981457710266},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.679872989654541},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6342108249664307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5723320245742798},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.5317484140396118},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45481881499290466},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43422698974609375},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.43153905868530273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38456088304519653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3762613534927368},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30595508217811584},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.299055814743042},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.26164841651916504},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4959999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.4933","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.4933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/35286.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.991.2248","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.991.2248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0001977.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1555737547","https://openalex.org/W1989702938","https://openalex.org/W2041823554","https://openalex.org/W2042608483","https://openalex.org/W2083792893","https://openalex.org/W2096391593","https://openalex.org/W2102006361","https://openalex.org/W2111135419","https://openalex.org/W2119468495","https://openalex.org/W2171700247","https://openalex.org/W2544874028"],"related_works":["https://openalex.org/W2386723501","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2387879414","https://openalex.org/W2390304029","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2562733635"],"abstract_inverted_index":{"The":[0],"number":[1],"of":[2,21,27,34,42,72,137,142,163],"video":[3,23,43,50,91],"clips":[4],"available":[5],"online":[6],"is":[7,52,92,114],"growing":[8],"at":[9],"a":[10,25,53],"tremendous":[11],"pace.":[12],"Conventionally,":[13],"user-supplied":[14],"metadata":[15],"text,":[16],"such":[17],"as":[18],"the":[19,22,31,84,87,90,95,109,124,131,135,138,143,154,161,164],"title":[20],"and":[24,47,55,94,100,127,159],"set":[26],"keywords,":[28],"has":[29],"been":[30],"only":[32],"source":[33],"indexing":[35],"information":[36],"for":[37,45],"user-uploaded":[38],"videos.":[39,75,120],"Automated":[40],"extraction":[41],"content":[44],"unconstrained":[46,73,118],"large":[48],"scale":[49,136],"databases":[51],"challenging":[54],"yet":[56],"unsolved":[57],"problem.":[58],"In":[59],"this":[60,112],"paper,":[61],"we":[62],"present":[63,153],"an":[64],"audiovisual":[65,79,125],"celebrity":[66],"recognition":[67,81],"system":[68,144],"towards":[69],"automatic":[70],"tagging":[71],"Web":[74,119],"Prior":[76],"work":[77],"on":[78,83,117,156],"person":[80,88],"relied":[82],"fact":[85],"that":[86],"in":[89],"speaking":[93],"features":[96],"extracted":[97],"from":[98],"audio":[99],"visual":[101],"domain":[102],"are":[103,145],"associated":[104],"with":[105],"each":[106],"other":[107],"throughout":[108],"video.":[110],"However,":[111],"assumption":[113],"not":[115],"valid":[116],"Proposed":[121],"method":[122,165],"finds":[123],"mapping":[126],"hence":[128],"improve":[129],"upon":[130],"association":[132],"assumption.":[133],"Considering":[134],"application,":[139],"all":[140],"pieces":[141],"trained":[146],"automatically":[147],"without":[148],"any":[149],"human":[150],"supervision.":[151],"We":[152],"results":[155],"26,000":[157],"videos":[158],"show":[160],"effectiveness":[162],"per-celebrity":[166],"basis.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}
