{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:44Z","timestamp":1774419644711,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890382","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Semi-Supervised Contrastive Learning for Controllable Video-to-Music Retrieval"],"prefix":"10.1109","author":[{"given":"Shanti","family":"Stewart","sequence":"first","affiliation":[{"name":"Dolby Laboratories"}]},{"given":"Gouthaman","family":"KV","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}]},{"given":"Lie","family":"Lu","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}]},{"given":"Andrea","family":"Fanelli","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533662"},{"key":"ref3","article-title":"Is there a \u201dlanguage of music-video clips\"? a qualitative and quantitative study","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Pr\u00e9tet"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01031"},{"key":"ref5","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01420"},{"key":"ref7","article-title":"Mulan: A joint embedding of music audio and natural language","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Huang"},{"key":"ref8","article-title":"Contrastive audio-language learning for music","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Manco"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095926"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248113"},{"key":"ref13","article-title":"Query by video: Cross-modal music retrieval","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Li"},{"key":"ref14","article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Li"},{"key":"ref15","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref17","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref20","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Loshchilov"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref23","article-title":"Emotion embedding spaces for matching music to stories","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Won"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890382.pdf?arnumber=10890382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:55Z","timestamp":1774416235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890382","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}