{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:30:00Z","timestamp":1770917400934,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62207029"],"award-info":[{"award-number":["62207029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271454"],"award-info":[{"award-number":["62271454"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1403903"],"award-info":[{"award-number":["2018YFB1403903"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900700"],"award-info":[{"award-number":["2021YFF0900700"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L223033"],"award-info":[{"award-number":["L223033"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tsmc.2025.3576988","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T13:34:55Z","timestamp":1750772095000},"page":"6000-6010","source":"Crossref","is-referenced-by-count":2,"title":["TVMTrailer: A Text-Video-Music AIGC Framework for Film Trailer Generation"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0464-9862","authenticated-orcid":false,"given":"Cong","family":"Jin","sequence":"first","affiliation":[{"name":"School of Data Science and Intelligent Media, Communication University Of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1079-7457","authenticated-orcid":false,"given":"Meixiu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengjuan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3481-7820","authenticated-orcid":false,"given":"Xiaoyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3224-0063","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Cyber-Physical Fusion Intelligent Computing, State Ethnic Affairs Commission, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6601-3515","authenticated-orcid":false,"given":"Jiacun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Monmouth University, West Long Branch, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3349567"},{"key":"ref2","article-title":"Movie2Trailer: Unsupervised trailer generation using anomaly detection","author":"Rehusevych","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00261-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282953"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12153"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IWDRL.2018.8358211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3532213.3532306"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874092"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2015.520"},{"key":"ref11","article-title":"Film trailer generation via task decomposition","author":"Papalampidi","year":"2021","journal-title":"arXiv:2111.08774"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref13","article-title":"Mood classification using listening data","author":"Korzeniowski","year":"2020","journal-title":"arXiv:2010.11512"},{"key":"ref14","first-page":"4364","article-title":"A hierarchical latent vector model for learning long-term structure in music","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Roberts"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2991\/ismss-19.2019.75"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3374915"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"ref21","article-title":"MMM: Exploring conditional multi-track music generation with the transformer","author":"Ens","year":"2020","journal-title":"arXiv:2008.06048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12065"},{"key":"ref23","article-title":"Music transformer","author":"Huang","year":"2018","journal-title":"arXiv:1809.04281"},{"key":"ref24","article-title":"Symbolic music generation with diffusion models","author":"Mittal","year":"2021","journal-title":"arXiv:2103.16091"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10241-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","article-title":"PIANOTREE VAE: Structured representation learning for polyphonic music","author":"Wang","year":"2020","journal-title":"arXiv:2008.07118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21074-8_4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00045"},{"key":"ref33","article-title":"MusPy: A toolkit for symbolic music generation","author":"Dong","year":"2020","journal-title":"arXiv:2008.01951"},{"key":"ref34","article-title":"The Jazz transformer on the front line: Exploring the shortcomings of AI-composed music through quantitative measures","author":"Wu","year":"2020","journal-title":"arXiv:2008.01307"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref36","article-title":"InverseMV: Composing piano scores with a convolutional video-music transformer","author":"Lin","year":"2021","journal-title":"arXiv:2112.15320"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11130413\/11048957.pdf?arnumber=11048957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:43:17Z","timestamp":1755715397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11048957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":36,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3576988","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}