{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:35:32Z","timestamp":1790310932435,"version":"4.1.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076061"],"award-info":[{"award-number":["62076061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20220127"],"award-info":[{"award-number":["BK20220127"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3358978","type":"journal-article","created":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T19:10:59Z","timestamp":1706296259000},"page":"506-510","source":"Crossref","is-referenced-by-count":2,"title":["Music Conditioned Generation for Human-Centric Video"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6570-0620","authenticated-orcid":false,"given":"Zimeng","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automation, Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4975-8205","authenticated-orcid":false,"given":"Binghui","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Automation, Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1325-9252","authenticated-orcid":false,"given":"Yangang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3295756"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref7","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singer","year":"2023"},{"key":"ref8","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.73"},{"key":"ref10","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109419"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3077801"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3221350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3232277"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3304564"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref19","article-title":"DISCO: Disentangled control for referring human dance generation in real world","author":"Wang","year":"2023"},{"key":"ref20","article-title":"High fidelity neural audio compression","volume-title":"Trans. Mach. Learn. Res.","author":"Dfossez","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","first-page":"409","article-title":"LP-musiccaps: LLM-based pseudo music captioning","volume-title":"Proc. 24th Int. Soc. Music Inf. Retrieval Conf.","author":"Doh","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref27","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"ref33","first-page":"22113","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Mach. Learn. Res.","volume":"202","author":"Liu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10415104.pdf?arnumber=10415104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T22:32:39Z","timestamp":1707258759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10415104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3358978","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}