{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:20:57Z","timestamp":1772644857827,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62172126"],"award-info":[{"award-number":["62172126"]}],"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":["U2013210"],"award-info":[{"award-number":["U2013210"]}],"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":["62006060"],"award-info":[{"award-number":["62006060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Research Council","award":["JCYJ20210324120202006"],"award-info":[{"award-number":["JCYJ20210324120202006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tvcg.2023.3276973","type":"journal-article","created":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T17:25:08Z","timestamp":1684344308000},"page":"4752-4766","source":"Crossref","is-referenced-by-count":8,"title":["Audio2Gestures: Generating Diverse Gestures From Audio"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2162-1004","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-0897","authenticated-orcid":false,"given":"Di","family":"Kang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8117-2696","authenticated-orcid":false,"given":"Wenjie","family":"Pei","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5005-7166","authenticated-orcid":false,"given":"Xuefei","family":"Zhe","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6005-4989","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-3754","authenticated-orcid":false,"given":"Linchao","family":"Bao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2546-8721","authenticated-orcid":false,"given":"Zhenyu","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"93","article-title":"Investigating the use of recurrent motion modelling for speech gesture generation","volume-title":"Proc. 18th Int. Conf. Intell. Virtual Agents","author":"Ferstl"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618518"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778861"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981117"},{"key":"ref10","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_17"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00723"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392422"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref17","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3359566.3360053"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450692"},{"key":"ref21","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27077-2_18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref29","first-page":"299","article-title":"QuaterNet: A quaternion-based recurrent model for human motion","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Pavllo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref34","first-page":"465","article-title":"Toward multimodal image-to-image translation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"key":"ref37","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Larsen"},{"key":"ref38","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref39","article-title":"Adversarial feature learning","author":"Donahue","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref49","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref56","first-page":"7113","article-title":"Predicting 3D human dynamics from video","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Zhang"},{"key":"ref57","first-page":"2252","article-title":"Learning to reconstruct 3D human pose and shape via model-fitting in the loop","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Kolotouros"},{"key":"ref58","article-title":"Deep learning using rectified linear units (RELU)","author":"Agarap","year":"2018"},{"key":"ref59","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref60","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref62","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"CoRR"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00053","article-title":"Generating holistic 3D human motion from speech","volume-title":"CoRR","author":"Yi"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00338"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/10579898\/10128738.pdf?arnumber=10128738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:06:17Z","timestamp":1725995177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10128738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":67,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2023.3276973","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}