{"id":"https://openalex.org/W1992171448","doi":"https://doi.org/10.1109/icme.2003.1221656","title":"Audio-visual talking face detection","display_name":"Audio-visual talking face detection","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1992171448","doi":"https://doi.org/10.1109/icme.2003.1221656","mag":"1992171448"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-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/A5101753482","display_name":"Mingkun Li","orcid":"https://orcid.org/0000-0003-3332-7168"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingkun Li","raw_affiliation_strings":["Intelligent Information Engineering Laboratory, Oakland University, Rochester, MI, USA","Intelligent Inf. Eng. Lab, Oakland Univ., Rochester, MI, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Information Engineering Laboratory, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"Intelligent Inf. Eng. Lab, Oakland Univ., Rochester, MI, USA#TAB#","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010906479","display_name":"Dongge Li","orcid":"https://orcid.org/0000-0001-7205-353X"},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongge Li","raw_affiliation_strings":["Motorola Research Laboratories, Schaumburg, IL, USA","[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Research Laboratories, Schaumburg, IL, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017119312","display_name":"Nevenka Dimitrova","orcid":"https://orcid.org/0000-0003-4091-9233"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210131230","display_name":"Philips (United States)","ror":"https://ror.org/03kw6wr76","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122849","https://openalex.org/I4210131230"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Dimitrova","raw_affiliation_strings":["Philips Research, Briarcliff Manor, NY, USA","[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research, Briarcliff Manor, NY, USA","institution_ids":["https://openalex.org/I4210131230"]},{"raw_affiliation_string":"[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085622001","display_name":"Ishwar K. Sethi","orcid":"https://orcid.org/0000-0002-2578-111X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Sethi","raw_affiliation_strings":["Intelligent Information Engineering Laboratory, Oakland University, Rochester, MI, USA","[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Information Engineering Laboratory, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0764,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87669683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T10057","display_name":"Face and Expression Recognition","score":0.9973999857902527,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"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":0.8187618255615234},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.6923196315765381},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.612133264541626},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6025065779685974},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5961275696754456},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4623156189918518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4512183666229248},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4170064628124237},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4145134389400482},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4068067669868469},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4040338397026062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39819321036338806},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2538655400276184},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12564989924430847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187618255615234},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.6923196315765381},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.612133264541626},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6025065779685974},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5961275696754456},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4623156189918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4512183666229248},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4170064628124237},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4145134389400482},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4068067669868469},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4040338397026062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39819321036338806},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2538655400276184},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12564989924430847},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1221656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1969228515","https://openalex.org/W1993625798","https://openalex.org/W2024677982","https://openalex.org/W2032360374","https://openalex.org/W2034985742","https://openalex.org/W2078298881","https://openalex.org/W2100561338","https://openalex.org/W2138451337","https://openalex.org/W2147152072","https://openalex.org/W6669733040"],"related_works":["https://openalex.org/W1967587236","https://openalex.org/W2098693229","https://openalex.org/W2384651879","https://openalex.org/W2336272890","https://openalex.org/W4308999381","https://openalex.org/W3183843611","https://openalex.org/W4312238398","https://openalex.org/W3211418293","https://openalex.org/W4308999963","https://openalex.org/W2133653344"],"abstract_inverted_index":{"Talking":[0],"face":[1,13,46],"detection":[2,9,69],"is":[3,14],"important":[4],"for":[5,42],"videoconferencing.":[6],"However,":[7],"the":[8,11,18,22,25,31,44,75,88],"of":[10,17,21,28,60,96],"talking":[12,45],"difficult":[15],"because":[16],"low":[19],"resolution":[20],"capturing":[23],"devices,":[24],"informal":[26],"style":[27],"communication":[29],"and":[30],"background":[32],"sounds.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38],"a":[39,57,66,82],"novel":[40],"method":[41,55,77,90],"finding":[43],"using":[47],"latent":[48],"semantic":[49],"indexing":[50],"approach.":[51],"We":[52],"tested":[53],"our":[54],"on":[56],"comprehensive":[58],"set":[59],"home":[61],"video":[62],"conferencing":[63],"sessions":[64],"with":[65],"very":[67],"high":[68],"rate.":[70],"Our":[71],"experiments":[72],"show":[73],"that":[74],"LSI":[76],"accuracy":[78],"degrades":[79],"gracefully":[80],"in":[81,94],"noisy":[83],"environment":[84],"as":[85],"opposed":[86],"to":[87],"correlation":[89],"which":[91],"simply":[92],"fails":[93],"presence":[95],"noise.":[97]},"counts_by_year":[{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}