{"id":"https://openalex.org/W2104160358","doi":"https://doi.org/10.1109/cvpr.2005.105","title":"Computer Vision for Music Identification","display_name":"Computer Vision for Music Identification","publication_year":2005,"publication_date":"2005-07-27","ids":{"openalex":"https://openalex.org/W2104160358","doi":"https://doi.org/10.1109/cvpr.2005.105","mag":"2104160358"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2005.105","doi":"https://doi.org/10.1109/cvpr.2005.105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2005.105","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","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/A5039611523","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0002-1611-6636","observed_orcids":["https://orcid.org/0000-0002-1611-6636"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Ke","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009682734","display_name":"Derek Hoiem","orcid":"https://orcid.org/0000-0001-6260-5708","observed_orcids":["https://orcid.org/0000-0001-6260-5708"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Hoiem","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066107323","display_name":"Rahul Sukthankar","orcid":null,"observed_orcids":[]},"institutions":[{"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"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Sukthankar","raw_affiliation_strings":["Intel Research Pittsburgh, USA","School of Computer Science, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Research Pittsburgh, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.3566,"has_fulltext":false,"cited_by_count":154,"citation_normalized_percentile":{"value":0.99288678,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"1","issue":null,"first_page":"597","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/music-identification","display_name":"music identification","score":0.9300000071525574},{"id":"https://openalex.org/keywords/content-based-music-retrieval","display_name":"content-based music retrieval","score":0.7839999794960022},{"id":"https://openalex.org/keywords/noisy-audio","display_name":"noisy audio","score":0.6639999747276306},{"id":"https://openalex.org/keywords/local-descriptors","display_name":"local descriptors","score":0.9089999794960022},{"id":"https://openalex.org/keywords/geometric-verification","display_name":"geometric verification","score":0.8320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815189003944397},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6863119602203369},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6832141280174255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6343343257904053},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5946562886238098},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5530079007148743},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.518726646900177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4995763301849365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4948226809501648},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.46178773045539856},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44712433218955994},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44616076350212097},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43988150358200073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39704447984695435},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27766692638397217},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr.2005.105","doi":"https://doi.org/10.1109/cvpr.2005.105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2005.105","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.138.184","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yke/musicretrieval/cvpr2005-mr.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.581","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~dhoiem/publications/./cvpr2005-mr.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.2528","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.2528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lb.cs.cmu.edu/~rahuls/pub/cvpr2005-rahuls.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W1502916507","https://openalex.org/W1510532633","https://openalex.org/W2032210760","https://openalex.org/W2061044111","https://openalex.org/W2085261163","https://openalex.org/W2098381762","https://openalex.org/W2112076978","https://openalex.org/W2117052143","https://openalex.org/W2117853077","https://openalex.org/W2124386111","https://openalex.org/W2141417147","https://openalex.org/W2147717514","https://openalex.org/W2152926413","https://openalex.org/W2164598857","https://openalex.org/W4244952642"],"related_works":["https://openalex.org/W2131463062","https://openalex.org/W2627485755","https://openalex.org/W2953702648","https://openalex.org/W1999999865","https://openalex.org/W2133036393","https://openalex.org/W7099024714","https://openalex.org/W2735263010","https://openalex.org/W2105663656","https://openalex.org/W2155164976","https://openalex.org/W7100832359"],"abstract_inverted_index":{"We":[0,129],"describe":[1],"how":[2],"certain":[3],"tasks":[4],"in":[5,110,134,149,174],"the":[6,21,27,45,90,95,103,119,126,150,171],"audio":[7,147],"domain":[8],"can":[9,139],"be":[10],"effectively":[11],"addressed":[12],"using":[13],"computer":[14],"vision":[15],"approaches.":[16],"This":[17],"paper":[18],"focuses":[19],"on":[20,69],"problem":[22],"of":[23,39,47,73,97,152],"music":[24,49,57,144,176],"identification,":[25],"where":[26],"goal":[28],"is":[29,122],"to":[30,86,117],"reliably":[31],"identify":[32,118],"a":[33,36,52,60,70,135],"song":[34,98,120],"given":[35],"few":[37],"seconds":[38],"noisy":[40,104],"audio.":[41],"Our":[42,163],"approach":[43,168],"treats":[44],"spectrogram":[46],"each":[48],"clip":[50],"as":[51,155],"2D":[53],"image":[54],"and":[55,106,141,159],"transforms":[56],"identification":[58],"into":[59],"corrupted":[61],"sub-image":[62],"retrieval":[63],"problem.":[64],"By":[65],"employing":[66],"pairwise":[67],"boosting":[68],"large":[71],"set":[72,96],"Viola-Jones":[74],"features,":[75],"our":[76,132],"system":[77,137],"learns":[78],"compact,":[79],"discriminative,":[80],"local":[81],"descriptors":[82],"that":[83,100,121,138,166],"are":[84],"amenable":[85],"efficient":[87],"indexing.":[88],"During":[89],"query":[91],"phase,":[92],"we":[93],"retrieve":[94],"snippets":[99],"locally":[101],"match":[102],"sample":[105],"employ":[107],"geometric":[108],"verification":[109],"conjunction":[111],"with":[112,125],"an":[113],"EM-based":[114],"\"occlusion\"":[115],"model":[116],"most":[123],"consistent":[124],"observed":[127],"signal.":[128],"have":[130],"implemented":[131],"algorithm":[133],"practical":[136],"quickly":[140],"accurately":[142],"recognize":[143],"from":[145],"short":[146],"samples":[148],"presence":[151],"distortions":[153],"such":[154],"poor":[156],"recording":[157],"quality":[158],"significant":[160],"ambient":[161],"noise.":[162],"experiments":[164],"demonstrate":[165],"this":[167],"significantly":[169],"outperforms":[170],"current":[172],"state-of-the-art":[173],"content-based":[175],"identification.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}