{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:02:36Z","timestamp":1777654956493,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095203","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":14,"title":["GTN-Bailando: Genre Consistent long-Term 3D Dance Generation Based on Pre-Trained Genre Token Network"],"prefix":"10.1109","author":[{"given":"Haolin","family":"Zhuang","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shun","family":"Lei","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqin","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sicheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[{"name":"XVerse Inc,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-012-1288-5"},{"key":"ref12","first-page":"501","article-title":"Example-based automatic music-driven conventional dance motion synthesis","volume":"18","author":"fan","year":"2011","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459932"},{"key":"ref14","article-title":"Dancing to music","volume":"32","author":"lee","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"key":"ref2","first-page":"26","article-title":"Groovenet: Real-time music-driven dance movement generation using artificial neural networks","volume":"8","author":"alemi","year":"2017","journal-title":"Networks"},{"key":"ref1","first-page":"501","article-title":"Aist dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","author":"tsuchida","year":"2019","journal-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference ISMIR 2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2181492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414005"},{"key":"ref19","article-title":"Neural discrete representation learning","author":"den oord","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref24","article-title":"Style tokens: Unsupervised style modeling, con-trol and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref25","article-title":"End-to-end emotional speech synthesis using style tokens and semi-supervised training","author":"pengfei","year":"2019","journal-title":"IEEE Conference Proceedings"},{"key":"ref20","article-title":"Actor-critic algorithms","author":"konda","year":"2002","journal-title":"Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747838"},{"key":"ref21","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref28","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"2017","journal-title":"Asian Journal of Applied Science and Engineering"},{"key":"ref27","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","author":"huang","year":"2020","journal-title":"Learning"},{"key":"ref7","article-title":"Learning to generate diverse dance motions with transformer","author":"li","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977333"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413848"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095203.pdf?arnumber=10095203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:39Z","timestamp":1700506959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095203","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}