{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:10:26Z","timestamp":1758042626600,"version":"3.44.0"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icmew68306.2025.11152178","type":"proceedings-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:41:25Z","timestamp":1757526085000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Video-driven cross-modal controlled music generation"],"prefix":"10.1109","author":[{"given":"Jingge","family":"Zhao","sequence":"first","affiliation":[{"name":"ZhengZhou University,School of Electrical and Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Li","sequence":"additional","affiliation":[{"name":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"ZhengZhou University,School of Electrical and Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Central Conservatory of Music,Department of AI Music and Music Information Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Tie","sequence":"additional","affiliation":[{"name":"ZhengZhou University,School of Electrical and Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Symbolic music generation with non-differentiable rule guided diffusion","year":"2024","author":"Huang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09418-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123640"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01433"},{"article-title":"Vis2mus: Exploring multimodal representation mapping for controllable music generation","year":"2022","author":"Zhang","key":"ref6"},{"article-title":"Inversemv: Composing piano scores with a convolutional video-music transformer","year":"2021","author":"Lin","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_11"},{"article-title":"Multi-instrumentalist net: Unsupervised generation of music from body movements","year":"2020","author":"Su","key":"ref9"},{"key":"ref10","first-page":"54","article-title":"Butter: A representation learning framework for bi-directional music-sentence retrieval and generation","volume-title":"Proceedings of the 1st workshop on nlp for music and audio (nlp4musa)","author":"Zhang"},{"article-title":"Musiclm: Generating music from text","year":"2023","author":"Agostinelli","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"article-title":"music21: A toolkit for computer-aided musicology and symbolic music data","year":"2010","author":"Cuthbert","key":"ref13"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11152022\/11152034\/11152178.pdf?arnumber=11152178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:29:37Z","timestamp":1757611777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11152178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icmew68306.2025.11152178","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}