{"id":"https://openalex.org/W1971114800","doi":"https://doi.org/10.1109/icassp.2010.5496233","title":"On-the-fly video genre classification by combination of audio features","display_name":"On-the-fly video genre classification by combination of audio features","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W1971114800","doi":"https://doi.org/10.1109/icassp.2010.5496233","mag":"1971114800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5496233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5071001941","display_name":"Micka\u00ebl Rouvier","orcid":"https://orcid.org/0000-0003-3541-3385"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mickael Rouvier","raw_affiliation_strings":["LIA-CERI, University of Avignon, France","LIA/CERI University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA-CERI, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA/CERI University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georges Linares","raw_affiliation_strings":["LIA-CERI, University of Avignon, France","LIA/CERI University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA-CERI, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA/CERI University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017334281","display_name":"Driss Matrouf","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Driss Matrouf","raw_affiliation_strings":["LIA-CERI, University of Avignon, France","LIA/CERI University of Avignon, France"],"affiliations":[{"raw_affiliation_string":"LIA-CERI, University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA/CERI University of Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071001941"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":1.7112,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83348226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"48"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9962000250816345,"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":0.8403584361076355},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.6035361886024475},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5916016101837158},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.588228166103363},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5747411847114563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5706822872161865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5424138307571411},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.506170928478241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5010991096496582},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4841483235359192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.389516144990921},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3222709894180298},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3200344443321228},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1356360912322998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403584361076355},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.6035361886024475},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5916016101837158},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.588228166103363},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5747411847114563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5706822872161865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424138307571411},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.506170928478241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5010991096496582},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4841483235359192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.389516144990921},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3222709894180298},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3200344443321228},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1356360912322998},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":2,"locations":[{"id":"doi:10.1109/icassp.2010.5496233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01320222v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01320222","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2010, Dallas, United States. &#x27E8;10.1109/ICASSP.2010.5496233&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W92751526","https://openalex.org/W158670877","https://openalex.org/W1515103638","https://openalex.org/W1558985830","https://openalex.org/W1563750459","https://openalex.org/W1966903391","https://openalex.org/W2071507457","https://openalex.org/W2109788830","https://openalex.org/W2113144451","https://openalex.org/W2119288237","https://openalex.org/W2137075158","https://openalex.org/W2142526407","https://openalex.org/W2151920764","https://openalex.org/W2411442511","https://openalex.org/W2904424563","https://openalex.org/W4301158409","https://openalex.org/W6606012490","https://openalex.org/W6606388411","https://openalex.org/W6630779002","https://openalex.org/W6633735077","https://openalex.org/W6676408509","https://openalex.org/W6681096189","https://openalex.org/W6999362176"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2003977768","https://openalex.org/W2910935116","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W4316036082"],"abstract_inverted_index":{"Video":[0],"genre":[1],"identification":[2,26],"methods":[3,39],"are":[4,13,20,67],"frequently":[5],"based":[6,82],"on":[7,83,90,100],"image":[8],"or":[9,61],"motion":[10],"analysis,":[11],"which":[12],"relatively":[14],"time-consuming":[15],"processes.":[16],"Since":[17],"such":[18],"approaches":[19],"tractable":[21],"by":[22,72],"batch":[23],"processing,":[24],"as-soon-as-possible":[25],"requires":[27],"faster":[28],"methods.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,53],"investigate":[34],"the":[35,59,63,76,80,88],"use":[36,47],"of":[37],"audio-only":[38],"for":[40],"on-the-fly":[41],"video":[42],"classification.":[43],"We":[44],"propose":[45],"to":[46,69,75],"several":[48],"acoustic":[49],"feature":[50],"streams":[51],"and":[52],"evaluate":[54],"various":[55],"combination":[56,85],"schemes":[57],"at":[58,62],"frame":[60],"score":[64],"level.":[65],"Results":[66],"compared":[68],"those":[70],"obtained":[71],"humans,":[73],"according":[74],"listening":[77],"duration.":[78],"Although":[79],"system":[81],"model":[84],"slightly":[86],"outperforms":[87],"humans":[89],"very":[91],"soon":[92],"detection.":[93],"The":[94],"latter":[95],"remain":[96],"significantly":[97],"more":[98],"accurate":[99],"long":[101],"sessions.":[102]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
