{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T06:53:08Z","timestamp":1775803988339,"version":"3.50.1"},"reference-count":23,"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\/icassp48485.2024.10447760","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1126-1130","source":"Crossref","is-referenced-by-count":6,"title":["Joint Music and Language Attention Models for Zero-Shot Music Tagging"],"prefix":"10.1109","author":[{"given":"Xingjian","family":"Du","sequence":"first","affiliation":[{"name":"Bytedance"}]},{"given":"Zhesong","family":"Yu","sequence":"additional","affiliation":[{"name":"Bytedance"}]},{"given":"Jiaju","family":"Lin","sequence":"additional","affiliation":[{"name":"Bytedance"}]},{"given":"Bilei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Bytedance"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hongkong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref3","article-title":"Automatic tagging using deep convolutional neural networks","author":"Choi","year":"2016","journal-title":"International Society of Music Information Retrieval (ISMIR)"},{"key":"ref4","article-title":"Evaluation of CNN-based automatic music tagging models","volume-title":"Sound and Music Computing Conference (SMC)","author":"Won"},{"key":"ref5","article-title":"Semi-supervised music tagging transformer","author":"Won","year":"2021","journal-title":"International Society for Music Information Retrieval (ISMIR)"},{"key":"ref6","article-title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","author":"Li","year":"2023"},{"key":"ref7","article-title":"Open set recognition for music genre classification","author":"Liu","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_9081"},{"key":"ref9","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref10","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511571169.014"},{"key":"ref12","article-title":"MuLan: A joint embedding of music audio and natural language","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Huang"},{"key":"ref13","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref14","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"Proceedings of Machine Learning Research","author":"Niizumi"},{"key":"ref15","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International Conference on Machine Learning (ICML)","author":"Jaegle"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref19","article-title":"Falcon-40B: an open large language model with state-of-the-art performance","author":"Almazrouei","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-79948-3_5050"},{"key":"ref22","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Law"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10447760.pdf?arnumber=10447760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:54:52Z","timestamp":1722574492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447760","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}