{"id":"https://openalex.org/W4200541904","doi":"https://doi.org/10.1109/ictc52510.2021.9620826","title":"Multi-modal, Multi-task and Multi-label for Music Genre Classification and Emotion Regression","display_name":"Multi-modal, Multi-task and Multi-label for Music Genre Classification and Emotion Regression","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W4200541904","doi":"https://doi.org/10.1109/ictc52510.2021.9620826"},"language":"en","primary_location":{"id":"doi:10.1109/ictc52510.2021.9620826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc52510.2021.9620826","pdf_url":null,"source":{"id":"https://openalex.org/S4363607766","display_name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5064192572","display_name":"Yagya Raj Pandeya","orcid":"https://orcid.org/0000-0002-9842-8704"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yagya Raj Pandeya","raw_affiliation_strings":["Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea","institution_ids":["https://openalex.org/I80611190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021721815","display_name":"Jie You","orcid":"https://orcid.org/0000-0002-2595-7357"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jie You","raw_affiliation_strings":["Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea","institution_ids":["https://openalex.org/I80611190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030180662","display_name":"Bhuwan Bhattarai","orcid":"https://orcid.org/0000-0001-7014-4868"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bhuwan Bhattarai","raw_affiliation_strings":["Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea","institution_ids":["https://openalex.org/I80611190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044837622","display_name":"Joonwhoan Lee","orcid":"https://orcid.org/0000-0003-1854-9643"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonwhoan Lee","raw_affiliation_strings":["Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of computer science and engineering, Jeonbuk National University, Jeonju-City, South Korea","institution_ids":["https://openalex.org/I80611190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6885,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73382749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1042","last_page":"1045"},"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":0.9958000183105469,"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":0.9866999983787537,"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":0.7606909275054932},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.6893229484558105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5430499911308289},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.537570595741272},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5244507789611816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.502387285232544},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49378570914268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4887847602367401},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4780195951461792},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4598660469055176},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45719707012176514},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.45324766635894775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3787848949432373},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18926864862442017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14606380462646484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11895188689231873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606909275054932},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6893229484558105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5430499911308289},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.537570595741272},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5244507789611816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.502387285232544},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49378570914268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887847602367401},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4780195951461792},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4598660469055176},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45719707012176514},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.45324766635894775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3787848949432373},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18926864862442017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14606380462646484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11895188689231873},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc52510.2021.9620826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc52510.2021.9620826","pdf_url":null,"source":{"id":"https://openalex.org/S4363607766","display_name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7112868416","display_name":null,"funder_award_id":"NRF-2021R1A2C2006895","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1566337733","https://openalex.org/W1973746598","https://openalex.org/W2091096948","https://openalex.org/W2123459668","https://openalex.org/W2153719147","https://openalex.org/W2170120951","https://openalex.org/W2437181147","https://openalex.org/W2604959036","https://openalex.org/W2619383789","https://openalex.org/W2736887001","https://openalex.org/W2810371401","https://openalex.org/W2896082894","https://openalex.org/W2902922910","https://openalex.org/W2907176602","https://openalex.org/W2977423666","https://openalex.org/W2981571772","https://openalex.org/W3023001428","https://openalex.org/W3045349544","https://openalex.org/W3049459827","https://openalex.org/W3069400403","https://openalex.org/W3080689104","https://openalex.org/W3084086733","https://openalex.org/W3085812513","https://openalex.org/W3087549734","https://openalex.org/W3101923269","https://openalex.org/W3115225613","https://openalex.org/W3116444474","https://openalex.org/W3141797743","https://openalex.org/W3185593275","https://openalex.org/W3202295776","https://openalex.org/W6741185346","https://openalex.org/W6756669892","https://openalex.org/W6949711019"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W1532663766"],"abstract_inverted_index":{"A":[0],"smart":[1],"system":[2],"is":[3,50,60,97,116],"highly":[4],"desirable":[5],"with":[6],"the":[7,27,57,63,84,89,93],"capability":[8],"to":[9,99],"divide":[10],"music":[11,28,46],"into":[12,34,41,52],"coarse":[13],"and":[14,20,32,47,56,66,73,80,110,118,124,128,133],"fine":[15,43],"categories":[16,37],"based":[17,29],"on":[18,30,120],"emotion":[19,33],"genre.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"classify":[26],"genre":[31],"44":[35],"class":[36],"which":[38],"further":[39],"subdivided":[40],"255":[42],"categories.":[44],"The":[45,101,114],"lyrics":[48,134],"information":[49,59],"input":[51],"two":[53],"separate":[54],"networks":[55],"global":[58],"integrated":[61],"for":[62,126],"final":[64],"classification":[65],"regression":[67],"task.":[68],"We":[69],"proposed":[70,102],"a":[71,121],"channel":[72,90],"filter":[74],"convolution":[75],"network":[76,115],"by":[77],"factorizing":[78],"spatial":[79],"temporal":[81],"interactions":[82],"of":[83,92,131],"standard":[85],"2D/3D":[86],"convolutions.":[87],"Furthermore,":[88],"interaction":[91],"general":[94],"residual":[95],"block":[96],"factorized":[98],"one.":[100],"convolutional":[103],"method":[104],"yields":[105],"significant":[106],"gains":[107],"in":[108],"accuracy":[109],"lower":[111],"computational":[112],"cost.":[113],"trained":[117],"tested":[119],"public":[122],"dataset":[123],"evaluated":[125],"individual":[127],"joint":[129],"representation":[130],"audio":[132],"networks.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
