{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T13:06:30Z","timestamp":1773320790627,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"Korean Government","doi-asserted-by":"publisher","award":["2023R1A2C1005744"],"award-info":[{"award-number":["2023R1A2C1005744"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3667939","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:57:49Z","timestamp":1772053069000},"page":"35485-35494","source":"Crossref","is-referenced-by-count":0,"title":["Mu-Mixer: A Hierarchical MLP-Based Framework for Cover Song Identification"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7977-2789","authenticated-orcid":false,"given":"Jungwoo","family":"Heo","sequence":"first","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6022-7674","authenticated-orcid":false,"given":"Hyun-Seo","family":"Shin","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6671-5004","authenticated-orcid":false,"given":"Chan-Yeong","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyo-Won","family":"Koo","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7036-072X","authenticated-orcid":false,"given":"Seung-Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2245-5945","authenticated-orcid":false,"given":"Jisoo","family":"Son","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3657-0665","authenticated-orcid":false,"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11674-2_14"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367348"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053839"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486531"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/673"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00297-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00189"},{"key":"ref10","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Luo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref12","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747172"},{"key":"ref14","article-title":"SV-mixer: Replacing the transformer encoder with lightweight MLPs for self-supervised model compression in speaker verification","volume-title":"Proc. IEEE Autom. Speech Recognit. Understand. Workshop (ASRU)","author":"Heo"},{"key":"ref15","first-page":"288","article-title":"Audio matching via chroma-based statistical features","volume-title":"Proc. ISMIR","author":"M\u00fcller"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/11\/9\/093017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref19","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref22","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref23","volume-title":"Music Similarity Data","author":"Hub","year":"2023"},{"key":"ref24","article-title":"Automatic musical genre classification of audio signals","volume-title":"Proc. 2nd Int. Symp. Music Inf. Retr.","author":"George"},{"key":"ref25","article-title":"FMA: A dataset for music analysis","author":"Defferrard","year":"2016","journal-title":"arXiv:1612.01840"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023314"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09643-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IC3S57698.2023.10169397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia57006.2022.9954732"},{"key":"ref32","article-title":"Da-TACOS: A dataset for cover song identification and understanding","author":"Yesiler","year":"2019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11411795.pdf?arnumber=11411795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:38:27Z","timestamp":1773257907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11411795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3667939","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}