{"id":"https://openalex.org/W1604419323","doi":"https://doi.org/10.1109/icpr.2002.1044776","title":"Video clip recognition using joint audio-visual processing model","display_name":"Video clip recognition using joint audio-visual processing model","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W1604419323","doi":"https://doi.org/10.1109/icpr.2002.1044776","mag":"1604419323"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2002.1044776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1044776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","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/A5003539810","display_name":"Victor Kulesh","orcid":null},"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/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"V. Kulesh","raw_affiliation_strings":["Intelligent Information Engineering Laboratory, Department of Computer Science and Engineering, Oakland University, Rochester, MI, USA"],"affiliations":[{"raw_affiliation_string":"Intelligent Information Engineering Laboratory, Department of Computer Science and Engineering, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651","https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075623067","display_name":"Valery A. Petrushin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099672","display_name":"Accenture (United States)","ror":"https://ror.org/013g16z83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093804","https://openalex.org/I4210099672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V.A. Petrushin","raw_affiliation_strings":["Accenture Technology Laboratories, Accenture, IL, USA"],"affiliations":[{"raw_affiliation_string":"Accenture Technology Laboratories, Accenture, IL, USA","institution_ids":["https://openalex.org/I4210099672"]}]},{"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/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I.K. Sethi","raw_affiliation_strings":["Intelligent Information Engineering Laboratory, Department of Computer Science and Engineering, Oakland University, Rochester, MI, USA"],"affiliations":[{"raw_affiliation_string":"Intelligent Information Engineering Laboratory, Department of Computer Science and Engineering, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651","https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003539810"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I177721651"],"apc_list":null,"apc_paid":null,"fwci":1.0676,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77193753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"500","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.995199978351593,"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":0.8452139496803284},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7273763418197632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6124624609947205},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5716717839241028},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.5579655170440674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5399861335754395},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4674592614173889},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.45802247524261475},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3889915347099304},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35415881872177124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06763893365859985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452139496803284},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7273763418197632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6124624609947205},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5716717839241028},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.5579655170440674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5399861335754395},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4674592614173889},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45802247524261475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3889915347099304},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35415881872177124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06763893365859985},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2002.1044776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1044776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1586405805","https://openalex.org/W1990517717","https://openalex.org/W1993625798","https://openalex.org/W2041823554","https://openalex.org/W2124851827","https://openalex.org/W6635268374"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2150890698","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"The":[0,45,53,65],"automatic":[1],"recognition":[2,30,54],"of":[3,56,68],"video":[4,28,40],"clips":[5],"is":[6,47,70,78],"an":[7,25],"important":[8],"capability":[9],"with":[10],"applications":[11],"in":[12],"broadcast":[13],"monitoring":[14],"for":[15,27,38],"content":[16],"theft":[17],"and":[18,34,41,60],"adherence":[19],"to":[20,49],"advertisement":[21],"campaign.":[22],"We":[23],"present":[24],"approach":[26,46],"clip":[29],"based":[31],"on":[32],"HMM":[33],"Gaussian":[35],"mixture":[36],"modeling":[37,39],"audio":[42],"streams":[43],"respectively.":[44],"used":[48],"model":[50,77],"TV":[51],"commercials.":[52],"results":[55],"using":[57],"single":[58],"stream":[59],"joint":[61,74],"models":[62],"are":[63],"compared":[64],"error":[66],"rate":[67],"0.01%":[69],"achieved":[71],"when":[72],"the":[73],"audiovisual":[75],"processing":[76],"employed.":[79]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
