{"id":"https://openalex.org/W4415707836","doi":"https://doi.org/10.1109/icme59968.2025.11209446","title":"BeatFM: Improving Beat Tracking with Pre-trained Music Foundation Model","display_name":"BeatFM: Improving Beat Tracking with Pre-trained Music Foundation Model","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707836","doi":"https://doi.org/10.1109/icme59968.2025.11209446"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5060139314","display_name":"Ganghui Ru","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ganghui Ru","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731347","display_name":"Jieying Wang","orcid":"https://orcid.org/0000-0002-0085-3551"},"institutions":[{"id":"https://openalex.org/I1312537475","display_name":"Naval Medical Research Command","ror":"https://ror.org/05f421b09","country_code":"US","type":"facility","lineage":["https://openalex.org/I1312537475","https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I4391768141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieying Wang","raw_affiliation_strings":["PLA,Naval Medical Center,China"],"affiliations":[{"raw_affiliation_string":"PLA,Naval Medical Center,China","institution_ids":["https://openalex.org/I1312537475"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088562282","display_name":"Jiahao Zhao","orcid":"https://orcid.org/0000-0002-8312-7300"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiahao Zhao","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043561002","display_name":"Yulun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulun Wu","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060028296","display_name":"Nannan Jiang","orcid":"https://orcid.org/0000-0003-3375-4805"},"institutions":[{"id":"https://openalex.org/I1312537475","display_name":"Naval Medical Research Command","ror":"https://ror.org/05f421b09","country_code":"US","type":"facility","lineage":["https://openalex.org/I1312537475","https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I4391768141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nannan Jiang","raw_affiliation_strings":["PLA,Naval Medical Center,China"],"affiliations":[{"raw_affiliation_string":"PLA,Naval Medical Center,China","institution_ids":["https://openalex.org/I1312537475"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391700","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-6853-7785"},"institutions":[{"id":"https://openalex.org/I1312537475","display_name":"Naval Medical Research Command","ror":"https://ror.org/05f421b09","country_code":"US","type":"facility","lineage":["https://openalex.org/I1312537475","https://openalex.org/I1330347796","https://openalex.org/I3130687028","https://openalex.org/I4391768141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["PLA,Naval Medical Center,China"],"affiliations":[{"raw_affiliation_string":"PLA,Naval Medical Center,China","institution_ids":["https://openalex.org/I1312537475"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100318314","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-9235-9429"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5060139314"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42345038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.0005000000237487257,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.00039999998989515007,"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/beat","display_name":"Beat (acoustics)","score":0.6905999779701233},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.3785000145435333},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.31940001249313354},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.30399999022483826},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.29260000586509705},{"id":"https://openalex.org/keywords/music-theory","display_name":"Music theory","score":0.2759999930858612}],"concepts":[{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1999949665","https://openalex.org/W2016885049","https://openalex.org/W2051672531","https://openalex.org/W2066158380","https://openalex.org/W2114640443","https://openalex.org/W2117330939","https://openalex.org/W2133824856","https://openalex.org/W2156063659","https://openalex.org/W2172212034","https://openalex.org/W2404176928","https://openalex.org/W4224918587","https://openalex.org/W4280498166","https://openalex.org/W4310987263","https://openalex.org/W4372259908","https://openalex.org/W4372347373","https://openalex.org/W4385152046","https://openalex.org/W4392904213","https://openalex.org/W4392910303"],"related_works":[],"abstract_inverted_index":{"Beat":[0],"tracking":[1,14,50,69,139],"is":[2,107],"a":[3,47,55,81,100],"widely":[4],"researched":[5],"topic":[6],"in":[7,118,135],"music":[8,57,74,77],"information":[9],"retrieval.":[10],"However,":[11],"current":[12],"beat":[13,49,68,96,136],"methods":[15],"face":[16],"challenges":[17],"due":[18],"to":[19,29,66],"the":[20,119],"scarcity":[21],"of":[22,84,109],"labeled":[23],"data,":[24],"which":[25,53,106],"limits":[26],"their":[27],"ability":[28],"generalize":[30],"across":[31,140],"diverse":[32,73],"musical":[33],"styles":[34],"and":[35,60,122,137],"accurately":[36],"capture":[37],"complex":[38],"rhythmic":[39],"structures.":[40],"To":[41,91],"overcome":[42],"these":[43,89],"challenges,":[44],"we":[45,98],"propose":[46],"novel":[48],"paradigm":[51],"BeatFM,":[52],"introduces":[54],"pre-trained":[56],"foundation":[58,78],"model":[59],"leverages":[61],"its":[62],"rich":[63],"semantic":[64,103,116],"knowledge":[65],"improve":[67],"performance.":[70],"Pre-training":[71],"on":[72,115],"datasets":[75],"endows":[76],"models":[79],"with":[80],"robust":[82],"understanding":[83],"music,":[85],"thereby":[86],"effectively":[87],"addressing":[88],"challenges.":[90],"further":[92],"adapt":[93],"it":[94],"for":[95],"tracking,":[97],"design":[99],"plug-and-play":[101],"multi-dimensional":[102],"aggregation":[104,117],"module,":[105],"composed":[108],"three":[110],"parallel":[111],"sub-modules,":[112],"each":[113],"focusing":[114],"temporal,":[120],"frequency,":[121],"channel":[123],"domains,":[124],"respectively.":[125],"Extensive":[126],"experiments":[127],"demonstrate":[128],"that":[129],"our":[130],"method":[131],"achieves":[132],"state-of-the-art":[133],"performance":[134],"downbeat":[138],"multiple":[141],"benchmark":[142],"datasets.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}