{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:57:00Z","timestamp":1775570220532,"version":"3.50.1"},"reference-count":27,"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\/icassp48485.2024.10447276","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8135-8139","source":"Crossref","is-referenced-by-count":5,"title":["Emotion-Aligned Contrastive Learning Between Images and Music"],"prefix":"10.1109","author":[{"given":"Shanti","family":"Stewart","sequence":"first","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kleanthis","family":"Avramidis","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiantian","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413514"},{"key":"ref2","article-title":"Contrastive audio-language learning for music","volume-title":"Proc. of 23rd International Society for Music Information Retrieval Conference","author":"Manco"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"ref4","article-title":"Query by video: Cross-modal music retrieval","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference","author":"Li"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096514"},{"key":"ref7","article-title":"Emotion embedding spaces for matching music to stories","volume-title":"Proc. of the 22nd International Society for Music Information Retrieval Conference","author":"Won"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095926"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","article-title":"Mulan: A joint embedding of music audio and natural language","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference","author":"Huang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094915"},{"key":"ref16","article-title":"Evaluation of cnn-based automatic music tagging models","volume-title":"Proc. of 17th Sound and Music Computing","author":"Won"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"key":"ref18","article-title":"The million song dataset","volume-title":"Proceedings of the 12th International Society for Music Information Retrieval Conference","author":"Bertin-Mahieux"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref21","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Loshchilov"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980227"},{"key":"ref26","article-title":"Contrastive learning of musical representations","volume-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference","author":"Spijkervet"},{"key":"ref27","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. of the 10th International Society for Music Information Retrieval Conference","author":"Law"}],"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\/10447276.pdf?arnumber=10447276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:50:32Z","timestamp":1722574232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447276","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}