{"id":"https://openalex.org/W4309344457","doi":"https://doi.org/10.1109/smc53654.2022.9945477","title":"MATT. A Multiple-instance Attention Mechanism for Long-tail Music Genre Classification","display_name":"MATT. A Multiple-instance Attention Mechanism for Long-tail Music Genre Classification","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309344457","doi":"https://doi.org/10.1109/smc53654.2022.9945477"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945477","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5086178628","display_name":"Xiaokai Liu","orcid":"https://orcid.org/0000-0001-8509-5624"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokai Liu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102213401","display_name":"Shihui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihui Song","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041180540","display_name":"Menghua Zhang","orcid":"https://orcid.org/0000-0001-8588-3612"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghua Zhang","raw_affiliation_strings":["School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074539156","display_name":"Yafan Huang","orcid":"https://orcid.org/0000-0001-7370-6766"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafan Huang","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10072395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"782","last_page":"787"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9704999923706055,"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":0.9679999947547913,"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":0.750080943107605},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7358446717262268},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5865001678466797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.548888623714447},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.483762264251709},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4642311930656433},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4478397071361542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44004225730895996},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4305129945278168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3901277184486389},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08264529705047607},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07279890775680542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750080943107605},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7358446717262268},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5865001678466797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548888623714447},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.483762264251709},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4642311930656433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4478397071361542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44004225730895996},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4305129945278168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3901277184486389},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08264529705047607},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07279890775680542},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945477","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1583001605","https://openalex.org/W2071103260","https://openalex.org/W2088252378","https://openalex.org/W2099760476","https://openalex.org/W2101234009","https://openalex.org/W2107726111","https://openalex.org/W2107789863","https://openalex.org/W2125324924","https://openalex.org/W2167969117","https://openalex.org/W2242592536","https://openalex.org/W2377006970","https://openalex.org/W2395579298","https://openalex.org/W2747932385","https://openalex.org/W2768149277","https://openalex.org/W2806470391","https://openalex.org/W2892316911","https://openalex.org/W2919115771","https://openalex.org/W2954224973","https://openalex.org/W2963451564","https://openalex.org/W2978506400","https://openalex.org/W3000748319","https://openalex.org/W3030742524","https://openalex.org/W3097525302","https://openalex.org/W3163842339","https://openalex.org/W4225508588","https://openalex.org/W6675354045","https://openalex.org/W6676071220","https://openalex.org/W6678788828","https://openalex.org/W6752307336","https://openalex.org/W6765174816","https://openalex.org/W6778241845"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2378211422","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2130974462"],"abstract_inverted_index":{"Imbalanced":[0],"music":[1,25,44,57,119,145,153],"genre":[2,20,140,154],"classification":[3,76],"is":[4,29],"a":[5,80,127,151],"crucial":[6],"task":[7],"in":[8,32,47,50,74],"the":[9,17,23,37,56,60,63,67,92,102,107,118,124,131,137,143],"Music":[10],"Information":[11],"Retrieval":[12],"(MIR)":[13],"field":[14],"for":[15,42,94],"identifying":[16,55,95],"long-tail,":[18],"data-poor":[19],"based":[21],"on":[22,150],"related":[24],"audio":[26,120],"segments,":[27],"which":[28],"very":[30],"prevalent":[31],"real-world":[33],"scenarios.":[34],"Most":[35],"of":[36,62,69,126],"existing":[38],"models":[39,134],"are":[40],"designed":[41],"class-balanced":[43],"datasets,":[45],"resulting":[46],"poor":[48],"performance":[49,93],"accuracy":[51],"and":[52],"generalization":[53],"when":[54],"genres":[58],"at":[59],"tail":[61,96],"distribution.":[64],"Inspired":[65],"by":[66,105],"success":[68],"introducing":[70],"Multi-instance":[71,84],"Learning":[72],"(MIL)":[73],"various":[75],"tasks,":[77],"we":[78,99,112],"propose":[79],"novel":[81],"mechanism":[82],"named":[83],"Attention":[85],"(MATT)":[86],"<sup":[87,167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[88,168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[89,169],"to":[90,116,141],"boost":[91],"classes.":[97],"Specifically,":[98],"first":[100],"construct":[101],"bag-level":[103],"datasets":[104],"generating":[106],"album-artist":[108],"pair":[109],"bags.":[110],"Second,":[111],"leverage":[113],"neural":[114,132],"networks":[115],"encode":[117],"segments.":[121],"Finally,":[122],"under":[123],"guidance":[125],"multi-instance":[128],"attention":[129],"mechanism,":[130],"network-based":[133],"could":[135],"select":[136],"most":[138],"informative":[139],"match":[142],"given":[144],"segment.":[146],"Comprehensive":[147],"experimental":[148],"results":[149],"large-scale":[152],"benchmark":[155],"dataset":[156],"with":[157],"long-tail":[158],"distribution":[159],"demonstrate":[160],"MATT":[161],"significantly":[162],"outperforms":[163],"other":[164],"state-of-the-art":[165],"baselines.":[166],"Github:":[170],"https://github.com/JohannesLiu/Music-Genre-Classification":[171]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}