{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:28:16Z","timestamp":1783823296423,"version":"3.55.0"},"reference-count":59,"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":[{"name":"Guandong Basic and Applied Basic Research Foundation","award":["2022A1515011425"],"award-info":[{"award-number":["2022A1515011425"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3405734","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T17:22:23Z","timestamp":1716830543000},"page":"10237-10250","source":"Crossref","is-referenced-by-count":8,"title":["DanceComposer: Dance-to-Music Generation Using a Progressive Conditional Music Generator"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1584-6267","authenticated-orcid":false,"given":"Xiao","family":"Liang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6639-3156","authenticated-orcid":false,"given":"Wensheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5162-9894","authenticated-orcid":false,"given":"Lifeng","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1160-0717","authenticated-orcid":false,"given":"Chengying","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Dance2music: Automatic dance-driven music generation","author":"Aggarwal","year":"2021"},{"key":"ref2","first-page":"29258","article-title":"How does it sound?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_11"},{"key":"ref4","first-page":"1","article-title":"Discrete contrastive diffusion for cross-modal music and image generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhu","year":"2023"},{"key":"ref5","article-title":"Long-term rhythmic video soundtracker","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2023"},{"key":"ref6","article-title":"Dancing to music","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459940"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2981989"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626164"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00940"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref15","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2172401"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201371"},{"key":"ref20","first-page":"400","article-title":"Dance beat tracking from visual information alone","volume-title":"Proc. 21th Int. Soc. Music Inf. Retrieval Conf.","author":"Pedersoli","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475180"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3303690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152598"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3128254"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref27","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref28","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref29","article-title":"ArchiSound: Audio generation with diffusion","author":"Schneider","year":"2023"},{"key":"ref30","first-page":"492","article-title":"Music transformer: Generating music with long-term structure","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Huang","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161851"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321495"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301962"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3286826"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638091"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref43","first-page":"559","article-title":"MuLan: A joint embedding of music audio and natural language","volume-title":"Proc. 23rd Int. Soc. Music Inf. Retrieval Conf.","author":"Huang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref45","volume-title":"Theory and Applications of Digital Speech Processing","author":"Rabiner","year":"2010"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547797"},{"key":"ref47","first-page":"1899","article-title":"Encoding musical style with transformer autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Choi","year":"2020"},{"key":"ref48","first-page":"3679","article-title":"The curious case of neural text degeneration","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Holtzman","year":"2020"},{"key":"ref49","first-page":"501","article-title":"AIST dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","volume-title":"Proc. 20th Int. Soc. Music Inf. Retrieval Conf.","author":"Tsuchida","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref51","first-page":"2269","article-title":"Learning to groove with inverse sequence transformations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gillick","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref53","article-title":"Learning-based methods for comparing sequences, with applications to audio-to-midi alignment and matching","author":"Raffel","year":"2016"},{"key":"ref54","first-page":"142","article-title":"The jazz transformer on the front line: Exploring the shortcomings of AI-composed music through quantitative measures","volume-title":"Proc. 21th Int. Soc. Music Inf. Retrieval Conf.","author":"Wu","year":"2020"},{"key":"ref55","first-page":"101","article-title":"MusPy: A toolkit for symbolic music generation","volume-title":"Proc. 21th Int. Soc. Music Inf. Retrieval Conf.","author":"Dong","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1080\/09298210701653344"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref58","article-title":"Evaluation methods for musical audio beat tracking algorithms","author":"Davies","year":"2009"},{"key":"ref59","first-page":"367","article-title":"MIR_EVAL: A transparent implementation of common MIR metrics","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Raffel","year":"2014"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10539267.pdf?arnumber=10539267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:43:44Z","timestamp":1729187024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10539267\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3405734","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}