{"id":"https://openalex.org/W4236459808","doi":"https://doi.org/10.1109/icme.2003.1220921","title":"Audio-visual synchrony for detection of monologues in video archives","display_name":"Audio-visual synchrony for detection of monologues in video archives","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W4236459808","doi":"https://doi.org/10.1109/icme.2003.1220921"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220921","doi":"https://doi.org/10.1109/icme.2003.1220921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220921","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5022650481","display_name":"Giridharan Iyengar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Iyengar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291571","display_name":"Harriet J. Nock","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H.J. Nock","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111579153","display_name":"C. Neti","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Neti","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.4966,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.66067683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9711999893188477,"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":0.9711999893188477,"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":0.024000000208616257,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual-synchronization","display_name":"audio-video synchronization","score":0.9290000200271606},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.6370000243186951},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"video retrieval","score":0.7099999785423279},{"id":"https://openalex.org/keywords/lip-synchronization","display_name":"lip synchronization","score":0.5699999928474426},{"id":"https://openalex.org/keywords/speaker-localization","display_name":"speaker localization","score":0.7350000143051147},{"id":"https://openalex.org/keywords/video-archives","display_name":"video archives","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257378339767456},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6883730888366699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6352944374084473},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5205884575843811},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5204135179519653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4565531611442566},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4517199993133545},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.42982175946235657},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.42903149127960205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35045939683914185},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3057277202606201},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09381610155105591},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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.2003.1220921","doi":"https://doi.org/10.1109/icme.2003.1220921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220921","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W2021437674","https://openalex.org/W2106488367","https://openalex.org/W2111135419","https://openalex.org/W2132214951","https://openalex.org/W2137398355","https://openalex.org/W2154636774","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W2021437674","https://openalex.org/W1997535979","https://openalex.org/W1932997869","https://openalex.org/W2100366204","https://openalex.org/W1988910659","https://openalex.org/W1142123214","https://openalex.org/W7096550717","https://openalex.org/W2118847468","https://openalex.org/W1997231916","https://openalex.org/W1562651896"],"abstract_inverted_index":{"In":[0,99],"this":[1],"paper":[2],"we":[3,107,131],"present":[4],"our":[5],"approach":[6,49,79],"to":[7,156],"detect":[8,89],"monologues":[9],"in":[10,25,33,69,76,95],"video":[11,27,43,55,97],"shots.":[12],"A":[13],"monologue":[14,109,166],"shot":[15,20],"is":[16,80],"defined":[17],"as":[18,82,111],"a":[19,22,83,96,105,133],"containing":[21,101],"talking":[23],"person":[24],"the":[26,30,34,40,47,115,124,139,146,170],"channel":[28],"with":[29,138],"corresponding":[31],"speech":[32,92,103,116,127,160],"audio":[35,53],"channel.":[36],"Whilst":[37],"motivated":[38],"by":[39,150],"TREC":[41],"2002":[42],"retrieval":[44],"track":[45],"(VT02),":[46],"underlying":[48],"of":[50,66,91],"synchrony":[51,125,164],"between":[52,126],"and":[54,62,72,93,104,117,128,159],"signals":[56],"are":[57,120],"also":[58],"applicable":[59],"for":[60,73],"voice":[61],"face-based":[63],"biometrics,":[64],"assessing":[65],"lip-synchronization":[67],"quality":[68],"movie":[70],"editing,":[71],"speaker":[74],"localization":[75],"video.":[77],"Our":[78,163],"envisioned":[81],"two":[84],"part":[85],"scheme.":[86],"We":[87],"first":[88],"occurrence":[90],"face":[94,158],"shot.":[98],"shots":[100,110,113],"both":[102],"face,":[106],"distinguish":[108],"those":[112],"where":[114],"facial":[118,129],"movements":[119,130],"synchronized.":[121],"To":[122],"measure":[123],"use":[132],"mutual-information":[134],"based":[135,165],"measure.":[136],"Experiments":[137],"VT02":[140],"corpus":[141],"indicate":[142],"that":[143],"using":[144,157],"synchrony,":[145],"average":[147,172],"precision":[148,173],"improves":[149],"more":[151],"than":[152],"50%":[153],"relative":[154],"compared":[155],"information":[161],"alone.":[162],"detector":[167],"submission":[168],"had":[169],"best":[171],"performance":[174],"(in":[175],"VT02)":[176],"amongst":[177],"18":[178],"different":[179],"submissions.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-05-12T00:00:00"}