{"id":"https://openalex.org/W2146639878","doi":"https://doi.org/10.1109/icassp.2003.1199126","title":"The indexing of persons in news sequences using audio-visual data","display_name":"The indexing of persons in news sequences using audio-visual data","publication_year":2004,"publication_date":"2004-02-03","ids":{"openalex":"https://openalex.org/W2146639878","doi":"https://doi.org/10.1109/icassp.2003.1199126","mag":"2146639878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1199126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1199126","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5076064509","display_name":"Alberto Albiol","orcid":"https://orcid.org/0000-0002-1970-3289"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"A. Albiol","raw_affiliation_strings":["Polytechnic University of Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775939","display_name":"L. Torres","orcid":"https://orcid.org/0000-0001-9141-9875"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"L. Torres","raw_affiliation_strings":["Technical University of Catalonia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E.J. Delp","raw_affiliation_strings":["Purdue University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"III","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.9047502875328064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257762789726257},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6381042003631592},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.529466986656189},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5266361236572266},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4800078272819519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722796380519867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46545344591140747},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43368959426879883},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.418828547000885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3298378586769104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31130683422088623},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26365846395492554}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.9047502875328064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257762789726257},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6381042003631592},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.529466986656189},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5266361236572266},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4800078272819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722796380519867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46545344591140747},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43368959426879883},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.418828547000885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3298378586769104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31130683422088623},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26365846395492554},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1199126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1199126","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.906","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cerias.purdue.edu/ssl/techreports-ssl/01199126.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1546507953","https://openalex.org/W2044591814","https://openalex.org/W2069883713","https://openalex.org/W2094908632","https://openalex.org/W2098693229","https://openalex.org/W2112173139","https://openalex.org/W2114543139","https://openalex.org/W2115089255","https://openalex.org/W2120032316","https://openalex.org/W2126268115","https://openalex.org/W2164741953","https://openalex.org/W2799061466","https://openalex.org/W4230982142","https://openalex.org/W6674436933","https://openalex.org/W6678870529"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2271369634","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W2350550760"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,10,14,37],"video":[3,23],"indexing":[4],"system":[5,34,55],"that":[6,41],"automatically":[7],"searches":[8],"for":[9,43],"specific":[11],"person":[12,47],"in":[13],"news":[15,62],"sequence.":[16],"The":[17,33,54],"proposed":[18],"approach":[19],"combines":[20],"audio":[21],"and":[22,29],"confidence":[24],"values":[25],"extracted":[26],"from":[27],"speaker":[28],"face":[30],"recognition":[31,67],"analysis.":[32],"also":[35],"incorporates":[36],"shot":[38],"selection":[39],"module":[40],"seeks":[42],"anchors,":[44],"where":[45],"the":[46,49],"on":[48,60],"scene":[50],"is":[51],"likely":[52],"speaking.":[53],"has":[56],"been":[57],"extensively":[58],"tested":[59],"several":[61],"sequences":[63],"with":[64],"very":[65],"good":[66],"rates.":[68]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
