{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T19:10:03Z","timestamp":1765480203308,"version":"3.48.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"24","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"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":["62476086"],"award-info":[{"award-number":["62476086"]}],"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":["52078212"],"award-info":[{"award-number":["52078212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1109\/jiot.2025.3617889","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:59Z","timestamp":1759772279000},"page":"52979-52989","source":"Crossref","is-referenced-by-count":0,"title":["Temporally Masked Diffusion: An Effective Behavioral Cloning Method in Robot Action Sequence Generation"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4871-9549","authenticated-orcid":false,"given":"Jiayi","family":"Sun","sequence":"first","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5336-5431","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control and Computer Engineering, North China Electric Power University, Beijing, China"}]},{"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7854-0766","authenticated-orcid":false,"given":"Shuangshuang","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"given":"Yingchun","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4601-4996","authenticated-orcid":false,"given":"Yanfeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Automation, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3228792"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3286398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3170149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2024.3406333"},{"key":"ref5","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3ICT.2018.8855753"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3002505"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS59377.2023.10316957"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610532"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3477450"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204708"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282704"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3100509"},{"key":"ref18","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref19","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Nichol","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","first-page":"1","article-title":"Imitating human behaviour with diffusion models","volume-title":"Int. Conf. Learn. Represent.","author":"Pearce"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref23","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"J\u00e4nner"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3057768"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref29","first-page":"25117","article-title":"Mask-based latent reconstruction for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref31","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Mandlekar","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111454"},{"issue":"1","key":"ref34","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3198678"},{"key":"ref36","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf.  Process. Syst.","volume":"34","author":"Chen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3342559"},{"key":"ref38","first-page":"22955","article-title":"Behavior transformers: Cloning k modes with one stone","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shafiullah"},{"key":"ref39","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref40","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol"},{"key":"ref41","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref42","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref43","first-page":"1","article-title":"DiffuSeq: Sequence to sequence text generation with diffusion models","volume-title":"Int. Conf. Learn. Represent.","author":"Gong"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref46","first-page":"1","article-title":"Copilot4D: Learning unsupervised world models for autonomous driving via discrete diffusion","volume-title":"Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3327501"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342382"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref53","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref54","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feichtenhofer"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3445991"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3322409"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00767"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref60","first-page":"1","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"Mar. 2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref62","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling"},{"key":"ref63","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Florence","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539396"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref66","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11293846\/11193794.pdf?arnumber=11193794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:49:01Z","timestamp":1765478941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":66,"journal-issue":{"issue":"24"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3617889","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2025,12,15]]}}}