{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T20:02:00Z","timestamp":1785268920991,"version":"3.55.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62441201"],"award-info":[{"award-number":["62441201"]}],"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":["62102036"],"award-info":[{"award-number":["62102036"]}],"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":["62272021"],"award-info":[{"award-number":["62272021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L232102"],"award-info":[{"award-number":["L232102"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4222024"],"award-info":[{"award-number":["4222024"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"R&D Program of Beijing Municipal Education Commission","award":["KM202211232003"],"award-info":[{"award-number":["KM202211232003"]}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Plan Project","doi-asserted-by":"publisher","award":["Z231100005923039"],"award-info":[{"award-number":["Z231100005923039"]}],"id":[{"id":"10.13039\/501100012401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFF1203803"],"award-info":[{"award-number":["2023YFF1203803"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"USA NSF","doi-asserted-by":"publisher","award":["IIS-1715985"],"award-info":[{"award-number":["IIS-1715985"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"USA NSF","doi-asserted-by":"publisher","award":["IIS-1812606"],"award-info":[{"award-number":["IIS-1812606"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tvcg.2024.3456213","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:06:21Z","timestamp":1725995181000},"page":"7397-7407","source":"Crossref","is-referenced-by-count":99,"title":["Expressive 3D Facial Animation Generation Based on Local-to-Global Latent Diffusion"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5101-1071","authenticated-orcid":false,"given":"Wenfeng","family":"Song","sequence":"first","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2777-0179","authenticated-orcid":false,"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8071-2894","authenticated-orcid":false,"given":"Yiming","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-1588","authenticated-orcid":false,"given":"Shuai","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5774-6706","authenticated-orcid":false,"given":"Aimin","family":"Hao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6006-4215","authenticated-orcid":false,"given":"Xia","family":"Hou","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7699-1355","authenticated-orcid":false,"given":"Hong","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University (SUNY at Stony Brook), Stony Brook, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"636","article-title":"Hierarchical residual learning based vector quantized variational autoencoder for image reconstruction and generation","volume-title":"British Machine Vision Conference","author":"Adiban","year":"2022"},{"key":"ref2","article-title":"Segdiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct57072.2022.00048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref7","article-title":"Adamesh: Personalized facial expressions and head poses for speech-driven 3d facial animation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00537"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_59"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614157"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2016.0034"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3220511.3220518"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2019.00-47"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref32","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref35","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2021"},{"key":"ref36","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PCEMS58491.2023.10136091"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref40","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref41","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref42","first-page":"14866","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"14","key":"ref43","first-page":"71","article-title":"Dall-e: Creating images from text","volume":"8","author":"Reddy","year":"2021","journal-title":"UGC Care Group I Journal"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref47","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref49","first-page":"1","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"International Conference on Learning Representations","author":"Singer","year":"2023"},{"key":"ref50","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref51","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3320216"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct57072.2022.00092"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3409568"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00083"},{"key":"ref57","article-title":"Sdxs: Real-time one-step latent diffusion models with image conditions","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR50242.2020.00030"},{"key":"ref60","first-page":"1","article-title":"Human motion diffusion model","volume-title":"International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.241"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref64","first-page":"6309","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref65","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01020"},{"key":"ref69","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2023","journal-title":"Medical Imaging with Deep Learning"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00231"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901521"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/10713475\/10670569.pdf?arnumber=10670569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T04:27:39Z","timestamp":1728620859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":78,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2024.3456213","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":[[2024,11]]}}}