{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:33:45Z","timestamp":1763202825867},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447473","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1141-1145","source":"Crossref","is-referenced-by-count":6,"title":["An Experimental Comparison of Multi-View Self-Supervised Methods for Music Tagging"],"prefix":"10.1109","author":[{"given":"Gabriel","family":"Meseguer-Brocal","sequence":"first","affiliation":[{"name":"Deezer Research,Paris,France"}]},{"given":"Dorian","family":"Desblancs","sequence":"additional","affiliation":[{"name":"Deezer Research,Paris,France"}]},{"given":"Romain","family":"Hennequin","sequence":"additional","affiliation":[{"name":"Deezer Research,Paris,France"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Ming-Wei Chang Kenton","year":"2019","journal-title":"NAACL"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"article-title":"Vision models are more robust and fair when pretrained on uncurated images without supervision","year":"2022","author":"Goyal","key":"ref3"},{"key":"ref4","article-title":"Using self-supervised learning can improve model robustness and uncertainty","author":"Hendrycks","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref7","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"article-title":"A cookbook of self-supervised learning","year":"2023","author":"Balestriero","key":"ref9"},{"key":"ref10","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref12","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","author":"Jing","year":"2022","journal-title":"ICLR"},{"key":"ref13","article-title":"Supervised and unsupervised learning of audio representations for music understanding","author":"McCallum","year":"2022","journal-title":"ISMIR"},{"key":"ref14","article-title":"Contrastive learning of musical representations","author":"Spijkervet","year":"2021","journal-title":"ISMIR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3297963"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3169627"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref20","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref23","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021","journal-title":"ICML"},{"key":"ref24","article-title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2022","journal-title":"ICLR"},{"article-title":"Vicregl: Self-supervised learning of local visual features","year":"2022","author":"Bardes","key":"ref25"},{"article-title":"The million song dataset","year":"2011","author":"Bertin-Mahieux","key":"ref26"},{"key":"ref27","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"Law","year":"2009","journal-title":"ISMIR"},{"key":"ref28","article-title":"The mtg-jamendo dataset for automatic music tagging","author":"Bogdanov","year":"2019","journal-title":"ICML"},{"key":"ref29","article-title":"Music representation learning based on editorial metadata from discogs","author":"Alonso-Jim\u00e9nez","year":"2022","journal-title":"ISMIR"},{"key":"ref30","article-title":"Contrastive audio-language learning for music","author":"Manco","year":"2022","journal-title":"ISMIR"},{"key":"ref31","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"Sohn","year":"2016","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","year":"2023","author":"Li","key":"ref33"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447473.pdf?arnumber=10447473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:33:53Z","timestamp":1722573233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447473","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}