{"id":"https://openalex.org/W2116750654","doi":"https://doi.org/10.1109/tmm.2011.2129498","title":"Cost-Sensitive Multi-Label Learning for Audio Tag Annotation and Retrieval","display_name":"Cost-Sensitive Multi-Label Learning for Audio Tag Annotation and Retrieval","publication_year":2011,"publication_date":"2011-03-17","ids":{"openalex":"https://openalex.org/W2116750654","doi":"https://doi.org/10.1109/tmm.2011.2129498","mag":"2116750654"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2011.2129498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2011.2129498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5102235147","display_name":"Hung-Yi Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lo","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087480257","display_name":"Shou-De Lin","orcid":"https://orcid.org/0000-0001-9970-1250"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shou-De Lin","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.069,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.97725766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"518","last_page":"529"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9088714122772217},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5340657830238342},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5299333930015564},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5176994800567627},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.4948217272758484},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48372676968574524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44863221049308777},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.42956024408340454},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4184597134590149},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.411998450756073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.31148761510849},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.19167038798332214},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13964560627937317},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.13220110535621643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9088714122772217},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5340657830238342},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5299333930015564},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5176994800567627},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.4948217272758484},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48372676968574524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44863221049308777},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.42956024408340454},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4184597134590149},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.411998450756073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31148761510849},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.19167038798332214},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13964560627937317},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.13220110535621643},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2011.2129498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2011.2129498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.1934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.1934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/papers/asriver/1029-F.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W55768394","https://openalex.org/W168039245","https://openalex.org/W1549656520","https://openalex.org/W1618905105","https://openalex.org/W1953606363","https://openalex.org/W1979955134","https://openalex.org/W1988790447","https://openalex.org/W2035055162","https://openalex.org/W2056983531","https://openalex.org/W2071913706","https://openalex.org/W2083383166","https://openalex.org/W2083978868","https://openalex.org/W2103614420","https://openalex.org/W2108672713","https://openalex.org/W2113229563","https://openalex.org/W2116373735","https://openalex.org/W2119821739","https://openalex.org/W2140013053","https://openalex.org/W2142261479","https://openalex.org/W2161258050","https://openalex.org/W2162124943","https://openalex.org/W2163966202","https://openalex.org/W2167969117","https://openalex.org/W2169375076","https://openalex.org/W2295268182","https://openalex.org/W3217467030","https://openalex.org/W4239510810","https://openalex.org/W6606829919","https://openalex.org/W6676823600","https://openalex.org/W6680873201","https://openalex.org/W6683737379","https://openalex.org/W6697340004","https://openalex.org/W6805302155"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W1892467659","https://openalex.org/W2331043530","https://openalex.org/W2370554703","https://openalex.org/W4386245233","https://openalex.org/W1519384422","https://openalex.org/W627539891","https://openalex.org/W1552522012","https://openalex.org/W1569407470","https://openalex.org/W2116750654"],"abstract_inverted_index":{"Audio":[0],"tags":[1,84,133],"correspond":[2],"to":[3,8,34,181],"keywords":[4],"that":[5,66,188],"people":[6,89],"use":[7],"describe":[9],"different":[10,91],"aspects":[11],"of":[12,20,76,79,93,140],"a":[13,52,116,150,170],"music":[14,22,37,62],"clip.":[15],"With":[16],"the":[17,25,60,68,103,111,138,145,156,165,189],"explosive":[18],"growth":[19],"digital":[21],"available":[23],"on":[24,59],"Web,":[26],"automatic":[27,128],"audio":[28,71,112,129,146,166],"tagging,":[29],"which":[30],"can":[31,47,109,143],"be":[32,48],"used":[33],"annotate":[35],"unknown":[36],"or":[38],"retrieve":[39],"desirable":[40],"music,":[41],"is":[42,74,125],"becoming":[43],"increasingly":[44],"important.":[45],"This":[46],"achieved":[49],"by":[50,88],"training":[51],"binary":[53],"classifier":[54],"for":[55,127],"each":[56],"tag":[57,104,122,157],"based":[58],"labeled":[61],"data.":[63],"Our":[64],"method":[65],"won":[67],"MIREX":[69,194],"2009":[70,195],"tagging":[72,113,130,147,167],"competition":[73],"one":[75],"this":[77],"kind":[78],"methods.":[80],"However,":[81],"since":[82,131],"social":[83],"are":[85],"usually":[86],"assigned":[87],"with":[90],"levels":[92],"musical":[94],"knowledge,":[95],"they":[96],"inevitably":[97],"contain":[98],"noisy":[99],"information.":[100],"By":[101,136],"treating":[102],"counts":[105],"as":[106,115,149,169],"costs,":[107],"we":[108,142,163],"model":[110,144],"problem":[114,148,176],"cost-sensitive":[117,172],"classification":[118,152],"problem.":[119,153],"In":[120],"addition,":[121],"correlation":[123,160],"information":[124,161],"useful":[126],"some":[132],"often":[134],"co-occur.":[135],"considering":[137],"co-occurrences":[139],"tags,":[141],"multi-label":[151,173],"To":[154],"exploit":[155],"count":[158],"and":[159,177],"jointly,":[162],"formulate":[164],"task":[168],"novel":[171],"(CSML)":[174],"learning":[175],"propose":[178],"two":[179],"solutions":[180],"solve":[182],"it.":[183],"The":[184],"experimental":[185],"results":[186],"demonstrate":[187],"new":[190],"approach":[191],"outperforms":[192],"our":[193],"winning":[196],"method.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
