{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:22:14Z","timestamp":1780593734804,"version":"3.54.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62320106007"],"award-info":[{"award-number":["62320106007"]}],"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":["62032022"],"award-info":[{"award-number":["62032022"]}],"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":["62236006"],"award-info":[{"award-number":["62236006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Program of Beijing Municipal Education Commission","award":["KZ201911417048"],"award-info":[{"award-number":["KZ201911417048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651041","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"2325-2336","source":"Crossref","is-referenced-by-count":1,"title":["MotionFlow: Efficient Motion Generation With Latent Flow Matching"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3714-1650","authenticated-orcid":false,"given":"Kun","family":"Dong","sequence":"first","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3624-5926","authenticated-orcid":false,"given":"Xing","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5877-2126","authenticated-orcid":false,"given":"Qingyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407529"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144958"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref16","first-page":"32939","article-title":"HumanTOMATO: Text-aligned whole-body motion generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu","year":"2024"},{"key":"ref17","article-title":"Human motion diffusion model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Tevet","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref21","article-title":"Human motion diffusion as a generative prior","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shafir","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref23","article-title":"OmniControl: Control any joint at any time for human motion generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xie","year":"2024"},{"key":"ref24","article-title":"Flow matching for generative modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref25","article-title":"Flow matching in latent space","author":"Dao","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27998"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref28","first-page":"22277","article-title":"Alphafold meets flow matching for generating protein ensembles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jing","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28483"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00089"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref34","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2013"},{"key":"ref35","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Ho"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref37","article-title":"HumanTOMATO: Text-aligned whole-body motion generation","author":"Lu","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref41","first-page":"20662","article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2024"},{"key":"ref42","first-page":"56998","article-title":"Latent diffusion for language generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lovelace","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref44","first-page":"1623","article-title":"MedSegDiff: Medical image segmentation with diffusion probabilistic model","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Wu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3359769"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref49","article-title":"Motion flow matching for human motion synthesis and editing","author":"Hu","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref51","first-page":"12171","article-title":"Point cloud completion with pretrained text-to-image diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kasten","year":"2024"},{"key":"ref52","first-page":"12489","article-title":"Protein design with guided discrete diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gruver","year":"2024"},{"key":"ref53","first-page":"68061","article-title":"SEEDS: Exponential SDE solvers for fast high-quality sampling from diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gonzalez","year":"2024"},{"key":"ref54","first-page":"77632","article-title":"SA-Solver: Stochastic adams solver for fast sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xue","year":"2024"},{"key":"ref55","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen","year":"2018"},{"key":"ref56","article-title":"FFJORD: Free-form continuous dynamics for scalable reversible generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grathwohl","year":"2018"},{"key":"ref57","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i9.37685"},{"key":"ref59","first-page":"982","article-title":"Learning robotic manipulation policies from point clouds with conditional flow matching","volume-title":"Proc. Conf. Robot Learn.","author":"Chisari","year":"2025"},{"key":"ref60","first-page":"12 606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1848"},{"key":"ref62","first-page":"14 699","article-title":"FLOAT: Generative motion latent flow matching for audio-driven talking portrait","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Ki","year":"2025"},{"key":"ref63","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS2021 Workshop Deep Generat. Models Downstream Appl.","author":"Ho","year":"2022"},{"key":"ref64","article-title":"OmniControl: Control any joint at any time for human motion generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xie","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Diederik","year":"2014"},{"key":"ref69","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inform. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.006"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"ref72","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329478.pdf?arnumber=11329478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:51:14Z","timestamp":1775537474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651041","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}