{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:29:41Z","timestamp":1773170981917,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MTC Programmatic Funds","award":["M23L7b0021"],"award-info":[{"award-number":["M23L7b0021"]}]},{"name":"EDB Space Technology Development Programme","award":["S22-19016-STDP"],"award-info":[{"award-number":["S22-19016-STDP"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571412"],"award-info":[{"award-number":["62571412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3641798","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:32:53Z","timestamp":1765305173000},"page":"4033-4050","source":"Crossref","is-referenced-by-count":0,"title":["Toward Accurate Procedure Planning in Instructional Videos: Visual State Generation Helps Task-Selective Diffusion"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3834-4795","authenticated-orcid":false,"given":"Fen","family":"Fang","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5959-2931","authenticated-orcid":false,"given":"Muli","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7916-3683","authenticated-orcid":false,"given":"Yanhua","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0105-5903","authenticated-orcid":false,"given":"Qianli","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4103-3824","authenticated-orcid":false,"given":"Joo-Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7002-4564","authenticated-orcid":false,"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A&#x002A;STAR), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref3","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387326"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00295"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01425"},{"key":"ref16","first-page":"1","article-title":"SCHEMA: State CHangEs MAtter for procedure planning in instructional videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Niu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref18","first-page":"17321","article-title":"Long-horizon visual planning with goal-conditioned hierarchical predictors","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Pertsch","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_45"},{"key":"ref20","first-page":"1","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nair","year":"2019"},{"key":"ref21","first-page":"8747","article-title":"Learning plannable representations with causal InfoGAN","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kurutach","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3518762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00945"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01780"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00366"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01341"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218596"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_31"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1641"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.399"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.326"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref48","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Oh","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.230"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00095"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1409-1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02213"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00952"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01357"},{"key":"ref57","first-page":"38863","article-title":"Ego4D goal-step: Toward hierarchical understanding of procedural activities","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Song","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2188"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00245"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00241"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_19"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00623"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"ref66","first-page":"14476","article-title":"Look at what i\u2019m doing: Self-supervised spatial grounding of narrations in instructional videos","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Tan","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeo.2021.100059"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.116"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref76","first-page":"67833","article-title":"Video-mined task graphs for keystep recognition in instructional videos","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ashutosh","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01817"},{"key":"ref78","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref80","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref85","first-page":"203","article-title":"Adaptive $\\varepsilon$\u025b-greedy exploration in reinforcement learning based on value differences","volume-title":"Proc. Annu. Conf. Artif. Intell.","author":"Tokic","year":"2010"},{"key":"ref86","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref87","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Int. Conf. Learn. Representations","author":"Song"},{"key":"ref88","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2017"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11288085.pdf?arnumber=11288085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:49Z","timestamp":1773106489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11288085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":88,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3641798","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}