{"id":"https://openalex.org/W3069400403","doi":"https://doi.org/10.1109/access.2020.3017661","title":"Multi-Level Local Feature Coding Fusion for Music Genre Recognition","display_name":"Multi-Level Local Feature Coding Fusion for Music Genre Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3069400403","doi":"https://doi.org/10.1109/access.2020.3017661","mag":"3069400403"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3017661","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017661","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09170628.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09170628.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105759393","display_name":"Wing W. Y. Ng","orcid":"https://orcid.org/0000-0003-0783-3585"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wing W. Y. Ng","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-3585","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014125308","display_name":"Wei-jie Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4692-1871","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100739453","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0001-5967-5940"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105759393"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.9502,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94546405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"152713","last_page":"152727"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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":0.9825999736785889,"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":0.8086732029914856},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6915199160575867},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5862792730331421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5845546722412109},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5186294913291931},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5128267407417297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49220505356788635},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47643929719924927},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4621677100658417},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4237784445285797},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.423475980758667},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.42308157682418823},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4209763705730438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4105483293533325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2529149055480957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086732029914856},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6915199160575867},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5862792730331421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845546722412109},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5186294913291931},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5128267407417297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49220505356788635},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47643929719924927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4621677100658417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4237784445285797},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.423475980758667},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.42308157682418823},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4209763705730438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4105483293533325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2529149055480957},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3017661","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017661","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09170628.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f88701b05d144df0a9e61038157e8473","is_oa":false,"landing_page_url":"https://doaj.org/article/f88701b05d144df0a9e61038157e8473","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 152713-152727 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3017661","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017661","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09170628.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3800154869","display_name":null,"funder_award_id":"2020B010166002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6185284941","display_name":null,"funder_award_id":"61876066","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6928099250","display_name":null,"funder_award_id":"2019A050510006","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3069400403.pdf","grobid_xml":"https://content.openalex.org/works/W3069400403.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1146734363","https://openalex.org/W1825426646","https://openalex.org/W1878565453","https://openalex.org/W1966385142","https://openalex.org/W1992855217","https://openalex.org/W2001709122","https://openalex.org/W2012592962","https://openalex.org/W2027035856","https://openalex.org/W2059341259","https://openalex.org/W2093231248","https://openalex.org/W2095147901","https://openalex.org/W2123745357","https://openalex.org/W2125271533","https://openalex.org/W2128196382","https://openalex.org/W2133824856","https://openalex.org/W2134789674","https://openalex.org/W2140065105","https://openalex.org/W2148748626","https://openalex.org/W2150279609","https://openalex.org/W2162915993","https://openalex.org/W2293255527","https://openalex.org/W2377006970","https://openalex.org/W2400549570","https://openalex.org/W2520774990","https://openalex.org/W2549961504","https://openalex.org/W2563031223","https://openalex.org/W2579586206","https://openalex.org/W2582368719","https://openalex.org/W2592168896","https://openalex.org/W2604959036","https://openalex.org/W2620629206","https://openalex.org/W2646300815","https://openalex.org/W2752306073","https://openalex.org/W2793881638","https://openalex.org/W2794150026","https://openalex.org/W2799604493","https://openalex.org/W2884013187","https://openalex.org/W2889391573","https://openalex.org/W2939753704","https://openalex.org/W2951111322","https://openalex.org/W2970737019","https://openalex.org/W2975625678","https://openalex.org/W2978099719","https://openalex.org/W3004064628","https://openalex.org/W3105202226","https://openalex.org/W4232730838","https://openalex.org/W4300957348","https://openalex.org/W4385245566","https://openalex.org/W6674642818","https://openalex.org/W6678853083","https://openalex.org/W6682080903","https://openalex.org/W6732863995","https://openalex.org/W6736327223","https://openalex.org/W6739901393","https://openalex.org/W6743574221","https://openalex.org/W6785932716"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2008961482","https://openalex.org/W2242773987"],"abstract_inverted_index":{"Music":[0],"genre":[1],"recognition":[2],"(MGR)":[3],"plays":[4],"a":[5,59],"fundamental":[6],"role":[7],"in":[8,30,49],"the":[9,50,70,87,107],"context":[10],"of":[11,21],"music":[12,18],"indexing":[13],"and":[14,44,66,75,120],"retrieval.":[15],"Unlike":[16],"images,":[17],"genres":[19],"consist":[20],"immediate":[22],"characteristics":[23],"that":[24,106],"are":[25],"highly":[26],"diversified":[27],"with":[28,64],"abstractions":[29],"different":[31,98],"levels.":[32],"However,":[33],"most":[34],"representation":[35],"learning":[36,92],"methods":[37],"for":[38],"MGR":[39,89],"focus":[40],"on":[41,117],"global":[42],"features":[43,48,96],"make":[45,86],"decisions":[46],"from":[47,93,97],"same":[51],"level.":[52],"To":[53],"remedy":[54],"such":[55],"defects,":[56],"we":[57],"intergrate":[58],"convolutional":[60],"neural":[61],"network":[62],"(CNN)":[63],"NetVLAD":[65],"self-attention":[67],"to":[68,85],"capture":[69],"local":[71,99],"information":[72],"across":[73],"levels":[74],"learn":[76],"their":[77],"long-term":[78],"dependencies.":[79],"A":[80],"meta":[81],"classifier":[82],"is":[83],"used":[84],"final":[88],"classification":[90],"by":[91],"aggregated":[94],"high-level":[95],"feature":[100],"coding":[101],"networks.":[102],"Experimental":[103],"results":[104],"show":[105],"proposed":[108],"approach":[109],"yields":[110],"higher":[111],"accuracies":[112],"than":[113],"other":[114],"state-of-the-art":[115],"models":[116],"GTZAN,":[118],"ISMIR2004,":[119],"Extended":[121],"Ballroom":[122],"dataset.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}