{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:09:14Z","timestamp":1784203754675,"version":"3.55.0"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023RC26"],"award-info":[{"award-number":["2023RC26"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2241208"],"award-info":[{"award-number":["U2241208"]}],"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":["62006024"],"award-info":[{"award-number":["62006024"]}],"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":["62071057"],"award-info":[{"award-number":["62071057"]}],"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":["62376035"],"award-info":[{"award-number":["62376035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134072","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T23:35:44Z","timestamp":1779492944000},"page":"134072","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Generating diverse high-fidelity 3D human motion with hierarchical VQ-VAE"],"prefix":"10.1016","volume":"696","author":[{"given":"Yexuan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134072_bib0005","series-title":"2019 International Conference on 3D Vision (3DV)","article-title":"Language2Pose: natural language grounded pose forecasting","author":"Ahuja","year":"2019"},{"issue":"6","key":"10.1016\/j.neucom.2026.134072_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550454.3555435","article-title":"Rhythmic gesticulator: rhythm-aware co-speech gesture synthesis with hierarchical neural embeddings","volume":"41","author":"Ao","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.134072_bib0015","series-title":"wav2VEC 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0020","series-title":"3rd International Conference on Learning Representations (ICLR)","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015"},{"key":"10.1016\/j.neucom.2026.134072_bib0025","author":"Bao"},{"key":"10.1016\/j.neucom.2026.134072_bib0030","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","article-title":"HP-GAN: probabilistic 3D human motion prediction via GAN","author":"Barsoum","year":"2018"},{"key":"10.1016\/j.neucom.2026.134072_bib0035","author":"Brock"},{"key":"10.1016\/j.neucom.2026.134072_bib0040","author":"Brown"},{"key":"10.1016\/j.neucom.2026.134072_bib0045","series-title":"European Conference on Computer Vision (ECCV)","first-page":"356","article-title":"Implicit neural representations for variable length human motion generation","author":"Cervantes","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0050","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11315","article-title":"MaskGIT: masked generative image transformer","author":"Chang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0055","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18000","article-title":"Executing your commands via motion diffusion in latent space","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0060","series-title":"Human Motion Prediction Using Manifold-Aware Wasserstein GAN","author":"Chopin","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0065","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.134072_bib0070","series-title":"Jukebox: A Generative Model for Music","author":"Dhariwal","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0075","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134072_bib0080","author":"Dieleman"},{"key":"10.1016\/j.neucom.2026.134072_bib0085","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Taming transformers for high-resolution image synthesis","author":"Esser","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0090","series-title":"International Conference on Computer Vision","article-title":"Synthesis of compositional animations from textual descriptions","author":"Ghosh","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0095","author":"Gong"},{"key":"10.1016\/j.neucom.2026.134072_bib0100","author":"Guo"},{"key":"10.1016\/j.neucom.2026.134072_bib0105","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"580","article-title":"TM2T: stochastic and tokenized modeling for the reciprocal generation of 3D human motions and texts","volume":"vol. 13695","author":"Guo","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5152","article-title":"Generating diverse and natural 3D human motions from text","author":"Guo","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0115","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","article-title":"Action2motion: conditioned generation of 3D human motions","author":"Guo","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0120","series-title":"Proceedings of the British Machine Vision Conference 2017","article-title":"A recurrent variational autoencoder for human motion synthesis","author":"Habibe","year":"2017"},{"issue":"6","key":"10.1016\/j.neucom.2026.134072_bib0125","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417836","article-title":"Probabilistic and controllable motion synthesis using normalizing flows","volume":"39","author":"Henter","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.134072_bib0130","series-title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","author":"Huang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0135","article-title":"Motionflip: human motion as a foreign language","volume":"36","author":"Jiang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134072_bib0140","author":"Jin"},{"key":"10.1016\/j.neucom.2026.134072_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"key":"10.1016\/j.neucom.2026.134072_bib0150","series-title":"GMD: Controllable Human Motion Synthesis via Guided Diffusion Models","author":"Karunratanakul","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0155","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.134072_bib0160","series-title":"Learning to Generate Diverse Dance Motions with Transformer","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0165","series-title":"Masked Modeling for Self-Supervised Representation Learning on Vision and Beyond","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0170","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134072_bib0175","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.134072_bib0180","series-title":"Posegpt: Quantization-Based 3D Human Motion Generation and Forecasting","author":"Lucas","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0185","series-title":"International Conference on Computer Vision","first-page":"5442","article-title":"AMASS: archive of motion capture as surface shapes","author":"Mahmood","year":"2019"},{"key":"10.1016\/j.neucom.2026.134072_bib0190","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Learning trajectory dependencies for human motion prediction","author":"Mao","year":"2019"},{"key":"10.1016\/j.neucom.2026.134072_bib0195","series-title":"Massively Multimodal Masked Modeling","author":"Mirzahi","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0200","series-title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","author":"Ng","year":"2024"},{"key":"10.1016\/j.neucom.2026.134072_bib0205","series-title":"Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech Using Denoising Distillation","author":"Niizumi","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0210","series-title":"Advances in Neural Information Processing Systems","article-title":"Conditional image generation with PixelCNN decoders","volume":"vol. 29","author":"van den Oord","year":"2016"},{"key":"10.1016\/j.neucom.2026.134072_bib0215","series-title":"Advances in Neural Information Processing Systems","article-title":"Neural discrete representation learning","volume":"vol. 30","author":"van den Oord","year":"2017"},{"key":"10.1016\/j.neucom.2026.134072_bib0220","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Film: visual reasoning with a general conditioning layer","volume":"vol. 32","author":"Perez","year":"2018"},{"key":"10.1016\/j.neucom.2026.134072_bib0225","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Action-conditioned 3D human motion synthesis with transformer","author":"Petrovich","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0230","series-title":"European Conference on Computer Vision","first-page":"480","article-title":"Temos: generating diverse human motions from textual descriptions","author":"Petrovich","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0235","series-title":"Mmm: Generative Masked Motion Model","author":"Phinyomrattanapong","year":"2023"},{"issue":"4","key":"10.1016\/j.neucom.2026.134072_bib0240","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1089\/big.2016.0028","article-title":"The KIT motion-language dataset","volume":"4","author":"Plappert","year":"2016","journal-title":"Big Data"},{"issue":"13\u201326","key":"10.1016\/j.neucom.2026.134072_bib0245","article-title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","volume":"9","author":"Plappert","year":"2018","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.neucom.2026.134072_bib0250","series-title":"Transformer: Probabilistic Autoregressive Dance Generation with Multimodal Attention","author":"Perez","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0255","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0260","series-title":"International Conference on Machine Learning","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0265","author":"Razavi"},{"key":"10.1016\/j.neucom.2026.134072_bib0270","series-title":"2021 5th International Conference on Digital Signal Processing (ICDSP)","article-title":"Human motion generation using transformer learning","author":"Shiobara","year":"2021"},{"key":"10.1016\/j.neucom.2026.134072_bib0275","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11050","article-title":"Ballando: 3D dance generation by actor-critic GPT with choreographic memory","author":"Siyao","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0280","author":"Tevet"},{"key":"10.1016\/j.neucom.2026.134072_bib0285","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.134072_bib0290","series-title":"Advances in Neural Information Processing Systems","article-title":"Hierarchical quantized autoencoders","volume":"vol. 33","author":"Williams","year":"2020"},{"key":"10.1016\/j.neucom.2026.134072_bib0295","series-title":"The Twelfth International Conference on Learning Representations (ICLR)","article-title":"OmniControl: control any joint at any time for human motion generation","author":"Xie","year":"2024"},{"key":"10.1016\/j.neucom.2026.134072_bib0300","series-title":"Actformer: a GAN-based transformer towards general action-conditioned 3D human motion generation","author":"Xu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0305","article-title":"Speech gesture generation from the trimodal context of text, audio, and speaker identity","volume":"1-16","author":"Yoon","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.134072_bib0310","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"T2m-GPT: generating human motion from textual descriptions with discrete prompts","volume":"vol. 2, 4, 5, 6, 10","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0315","series-title":"Motiondiffuse: Text-Driven Human Motion Generation with Diffusion Model","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0320","series-title":"General-Diffuse: Retrieval-Augmented Motion Diffusion Model","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0325","series-title":"Tedi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0330","series-title":"A Unified Driving Engine for Human Motion Generation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134072_bib0335","series-title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","author":"Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134072_bib0340","series-title":"AttT2M:Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","author":"Zhong","year":"2023"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014700?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014700?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:44:14Z","timestamp":1784202254000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226014700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":68,"alternative-id":["S0925231226014700"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134072","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Generating diverse high-fidelity 3D human motion with hierarchical VQ-VAE","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134072","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134072"}}