{"id":"https://openalex.org/W2799617355","doi":"https://doi.org/10.1117/12.2309852","title":"Hierarchical vs non-hierarchical audio indexation and classification for video genres","display_name":"Hierarchical vs non-hierarchical audio indexation and classification for video genres","publication_year":2018,"publication_date":"2018-04-13","ids":{"openalex":"https://openalex.org/W2799617355","doi":"https://doi.org/10.1117/12.2309852","mag":"2799617355"},"language":"en","primary_location":{"id":"doi:10.1117/12.2309852","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2309852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tenth International Conference on Machine Vision (ICMV 2017)","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/A5056816332","display_name":"Nouha Dammak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Nouha Dammak","raw_affiliation_strings":["Higher Institute of Computer Sciences and Communication Techniques (Tunisia)","MIRACL (Tunisia)"],"affiliations":[{"raw_affiliation_string":"Higher Institute of Computer Sciences and Communication Techniques (Tunisia)","institution_ids":[]},{"raw_affiliation_string":"MIRACL (Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772397","display_name":"Yassine BenAyed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119561","display_name":"Digital Research Centre of Sfax","ror":"https://ror.org/02s48dm85","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210119561"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Yassine BENAYED","raw_affiliation_strings":["MIRACL (Tunisia)"],"affiliations":[{"raw_affiliation_string":"MIRACL (Tunisia)","institution_ids":["https://openalex.org/I4210119561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056816332"],"corresponding_institution_ids":["https://openalex.org/I4210119561"],"apc_list":null,"apc_paid":null,"fwci":0.1651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4137108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"62","issue":null,"first_page":"51","last_page":"51"},"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":0.9975000023841858,"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":0.967199981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8031203746795654},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6947977542877197},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6669144630432129},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6666809320449829},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6201935410499573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565483570098877},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4756750166416168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4452449679374695},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44367364048957825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43633517622947693},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3779881000518799},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.34186527132987976},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2302665114402771},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21799492835998535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031203746795654},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6947977542877197},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6669144630432129},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6666809320449829},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6201935410499573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565483570098877},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4756750166416168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4452449679374695},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44367364048957825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43633517622947693},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3779881000518799},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.34186527132987976},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2302665114402771},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21799492835998535},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2309852","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2309852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tenth International Conference on Machine Vision (ICMV 2017)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1545046063","https://openalex.org/W1737761412","https://openalex.org/W1845249827","https://openalex.org/W1916562039","https://openalex.org/W1972482772","https://openalex.org/W1983991261","https://openalex.org/W1993521836","https://openalex.org/W2021167307","https://openalex.org/W2051580196","https://openalex.org/W2072792684","https://openalex.org/W2076029968","https://openalex.org/W2100454127","https://openalex.org/W2109077321","https://openalex.org/W2118020653","https://openalex.org/W2133824856","https://openalex.org/W2135322151","https://openalex.org/W2142526407","https://openalex.org/W3120421331","https://openalex.org/W6639914280","https://openalex.org/W6668718045","https://openalex.org/W6676161413","https://openalex.org/W6680130795"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2523968781","https://openalex.org/W2378862766","https://openalex.org/W1479881079","https://openalex.org/W3135871143","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186","https://openalex.org/W296599067"],"abstract_inverted_index":{"In":[0,65],"this":[1,97],"paper,":[2],"Support":[3],"Vector":[4],"Machines":[5],"(SVMs)":[6],"are":[7],"used":[8],"for":[9],"segmenting":[10],"and":[11,79,91],"indexing":[12],"video":[13,73,107],"genres":[14],"based":[15,56],"on":[16,46,57,102],"only":[17],"audio":[18,63],"features":[19],"extracted":[20],"at":[21],"block":[22],"level,":[23],"which":[24],"has":[25],"a":[26,110],"prominent":[27],"asset":[28],"by":[29],"capturing":[30],"local":[31],"temporal":[32],"information.":[33],"The":[34,82,94],"main":[35],"contribution":[36],"of":[37,96,106,113],"our":[38],"study":[39],"is":[40],"to":[41],"show":[42],"the":[43,47,67],"wide":[44],"effect":[45],"classification":[48,68,111],"accuracies":[49],"while":[50],"using":[51],"an":[52],"hierarchical":[53],"categorization":[54],"structure":[55],"Mel":[58],"Frequency":[59],"Cepstral":[60],"Coefficients":[61],"(MFCC)":[62],"descriptor.":[64],"fact,":[66],"consists":[69],"in":[70],"three":[71],"common":[72],"genres:":[74],"sports":[75],"videos,":[76],"music":[77],"clips":[78],"news":[80],"scenes.":[81],"sub-classification":[83],"may":[84],"divide":[85],"each":[86],"genre":[87],"into":[88],"several":[89],"multi-speaker":[90],"multi-dialect":[92],"sub-genres.":[93],"validation":[95],"approach":[98],"was":[99],"carried":[100],"out":[101],"over":[103,114],"360":[104],"minutes":[105],"span":[108],"yielding":[109],"accuracy":[112],"99%.":[115]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
