{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:40:58Z","timestamp":1779288058011,"version":"3.51.4"},"reference-count":53,"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":["62172101"],"award-info":[{"award-number":["62172101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3303690","type":"journal-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T17:29:47Z","timestamp":1691602187000},"page":"8454-8463","source":"Crossref","is-referenced-by-count":7,"title":["Learning Music-Dance Representations Through Explicit-Implicit Rhythm Synchronization"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-6687","authenticated-orcid":false,"given":"Jiashuo","family":"Yu","sequence":"first","affiliation":[{"name":"ARC Lab, PCG Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9915-5437","authenticated-orcid":false,"given":"Junfu","family":"Pu","sequence":"additional","affiliation":[{"name":"Applied Research Center, PCG, Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-3998","authenticated-orcid":false,"given":"Ying","family":"Cheng","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0574","authenticated-orcid":false,"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Applied Research Center, PCG, Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3485664"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086082"},{"key":"ref4","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093345"},{"key":"ref6","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Chung","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref9","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korbar","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref13","article-title":"Active contrastive learning of audio-visual video representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2021"},{"key":"ref14","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref17","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alwassel","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref21","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref24","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Morgado","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01032"},{"key":"ref26","article-title":"Exploring modality-agnostic representations for music classification","author":"Wu","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475576"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.70"},{"key":"ref30","article-title":"Dance generation with style embedding: Learning and transferring latent representations of dance styles","author":"Zhang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414005"},{"key":"ref32","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2019.8757943"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201371"},{"key":"ref35","first-page":"400","article-title":"Dance beat tracking from visual information alone","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf","author":"Pedersoli","year":"2020"},{"key":"ref36","first-page":"4","article-title":"Maximum filter vibrato suppression for onset detection","volume-title":"Proc. 16th Int. Conf. Digit. Audio Effects","author":"Bck","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206821"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"issue":"1","key":"ref42","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref48","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Panchendrarajan","year":"2018","journal-title":"Proc. 32nd Pacific Asia Conf. Lang., Inf. Comput."},{"key":"ref49","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty","year":"2001"},{"key":"ref50","article-title":"Lets dance: Learning from online dance videos","author":"Castro","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5220\/0009326005580565"},{"key":"ref52","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume-title":"Proc. 3rd Int. Conf. Knowl. Discov. Data Mining Workshop","author":"Berndt","year":"1994"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10214079.pdf?arnumber=10214079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T07:57:11Z","timestamp":1722585431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3303690","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}