{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:28:33Z","timestamp":1780608513980,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["957337"],"award-info":[{"award-number":["957337"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2021.3071082","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T20:34:56Z","timestamp":1617654896000},"page":"733-737","source":"Crossref","is-referenced-by-count":20,"title":["Enriched Music Representations With Multiple Cross-Modal Contrastive Learning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1236-2503","authenticated-orcid":false,"given":"Andres","family":"Ferraro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Favory","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3605-7127","authenticated-orcid":false,"given":"Konstantinos","family":"Drossos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Bogdanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1374376.1374452"},{"key":"ref32","article-title":"The MTG-Jamendo dataset for automatic music tagging","author":"bogdanov","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref30","article-title":"Musicnn: Pre-trained convolutional neural networks for music audio tagging","author":"pons","year":"2019","journal-title":"20th Late-Breaking\/Demo Session Int Soc Music Inf Retrieval Conf"},{"key":"ref34","author":"ricci","year":"2010","journal-title":"Recommender Systems Handbook"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref11","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"weinberger","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref12","article-title":"Zero-shot learning for audio-based music classification and tagging","author":"choi","year":"2019"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref14","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref15","article-title":"Unsupervised contrastive learning of sound event representations","author":"fonseca","year":"2020"},{"key":"ref16","article-title":"Contrastive learning of general-purpose audio representations","author":"saeed","year":"2020"},{"key":"ref17","article-title":"Coala: Co-aligned autoencoders for learning semantically enriched audio representations","author":"favory","year":"2020"},{"key":"ref18","article-title":"Supervised contrastive learning","author":"khosla","year":"2020"},{"key":"ref19","article-title":"Learning contextual tag embeddings for cross-modal alignment of audio and tags","author":"favory","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.10"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref3","article-title":"Mood classification using listening data","author":"korzeniowski","year":"2020"},{"key":"ref6","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_62"},{"key":"ref8","article-title":"Classification is a strong baseline for deep metric learning","author":"zhai","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054688"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454038"},{"key":"ref9","article-title":"Metric learning vs classification for disentangled music representation learning","author":"lee","year":"0","journal-title":"Proc 21st Int Soc Music Inf Retrieval Conf"},{"key":"ref1","article-title":"Multimodal metric learning for tag-based music retrieval","author":"won","year":"2020"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Wsabie: Scaling up to large vocabulary image annotation","author":"weston","year":"2011"},{"key":"ref21","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23808-6_10"},{"key":"ref23","article-title":"Melon playlist dataset: A public dataset for audio-based playlist generation and music tagging","author":"ferraro","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref26","article-title":"Evaluation of CNN-based automatic music tagging models","author":"won","year":"0","journal-title":"Proc SMC2020-17th Sound Music Comput Conf"},{"key":"ref25","first-page":"131","article-title":"How low can you go? Reducing frequency and time resolution in current CNN architectures for music auto-tagging","author":"ferraro","year":"0","journal-title":"Proc 28th Eur Signal Process Conf"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09395210.pdf?arnumber=9395210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T04:06:05Z","timestamp":1633493165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9395210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3071082","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}