{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T09:32:07Z","timestamp":1774517527202,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859799","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Towards Proper Contrastive Self-Supervised Learning Strategies for Music Audio Representation"],"prefix":"10.1109","author":[{"given":"Jeong","family":"Choi","sequence":"first","affiliation":[{"name":"NAVER Corp."}]},{"given":"Seongwon","family":"Jang","sequence":"additional","affiliation":[{"name":"NCSOFT,Knowledge AI Lab."}]},{"given":"Hyunsouk","family":"Cho","sequence":"additional","affiliation":[{"name":"Ajou University"}]},{"given":"Sehee","family":"Chung","sequence":"additional","affiliation":[{"name":"NCSOFT,Knowledge AI Lab."}]}],"member":"263","reference":[{"key":"ref39","article-title":"Hypergraph models of playlist dialects","author":"mcfee","year":"0","journal-title":"ISMIR"},{"key":"ref38","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"0","journal-title":"ISMIR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053257"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2713830"},{"key":"ref31","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"0","journal-title":"ICLRE"},{"key":"ref30","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"0","journal-title":"JMLR"},{"key":"ref37","article-title":"Semi-supervised music tagging transformer","author":"won","year":"0","journal-title":"ISMIR"},{"key":"ref36","article-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","author":"pons","year":"0","journal-title":"ISMIR late-breaking news and demos"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref34","article-title":"The million song dataset","author":"bertin-mahieux","year":"0","journal-title":"ISMIR"},{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref12","article-title":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","author":"santiago","year":"0","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"0","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref18","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref28","article-title":"Contrastive learning of musical representations","author":"spijkervet","year":"0","journal-title":"ISMIR"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"NAACL"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053442"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref6","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"ArXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref7","article-title":"Generative pretraining from pixels","author":"chen","year":"0","journal-title":"ICML"},{"key":"ref2","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref20","article-title":"Clar: Contrastive learning of auditory representations","author":"haider","year":"0","journal-title":"AISTATS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"ref42","article-title":"Are we really making much progress? a worrying analysis of recent neural recommendation approaches","author":"dacrema","year":"0","journal-title":"RecSys"},{"key":"ref24","article-title":"Learning a metric for music similarity","author":"slaney","year":"0","journal-title":"ISMIR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04076-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053135"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2199109"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859799.pdf?arnumber=9859799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:25:01Z","timestamp":1663619101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859799\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859799","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}