{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:42:53Z","timestamp":1772905373487,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R & D Program of China","award":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076119"],"award-info":[{"award-number":["62076119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380119"],"award-info":[{"award-number":["020214380119"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Frontier Technology Research and Development Program","award":["BF2024076"],"award-info":[{"award-number":["BF2024076"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3518762","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:18:37Z","timestamp":1734376717000},"page":"2107-2124","source":"Crossref","is-referenced-by-count":2,"title":["PDPP: Projected Diffusion for Procedure Planning in Instructional Videos"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5431-1468","authenticated-orcid":false,"given":"Hanlin","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilu","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8959-2473","authenticated-orcid":false,"given":"Sheng","family":"Guo","sequence":"additional","affiliation":[{"name":"MYbank, Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"ref4","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref6","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01425"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref9","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref10","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Janner"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref12","article-title":"VDT: An empirical study on video diffusion with transformers","author":"Lu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00270"},{"key":"ref16","first-page":"159","article-title":"Long-term anticipation of activities with cycle consistency","volume-title":"Proc. 42nd DAGM German Conf. Pattern Recognit.","author":"Farha"},{"key":"ref17","first-page":"2664","article-title":"Uni-perceiver-MoE: Learning sparse generalist models with conditional MoEs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00599"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205207"},{"key":"ref20","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3005508"},{"key":"ref22","first-page":"1305","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref23","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Riquelme"},{"key":"ref24","first-page":"10 435","article-title":"Mesh-tensorflow: Deep learning for supercomputers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shazeer"},{"key":"ref25","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lepikhin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref27","first-page":"4739","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref29","first-page":"2928","article-title":"${\\rm{P}}^{\\text{3}} {\\rm{iv}}$P3 iv : Probabilistic procedure planning from instructional videos with weak supervision","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhao","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref32","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"issue":"8","key":"ref33","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref34","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref35","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref36","article-title":"Variational diffusion models","author":"Kingma","year":"2021"},{"key":"ref37","article-title":"Human motion diffusion model","author":"Tevet","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref39","article-title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","author":"Chen","year":"2015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852234"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191288"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref46","article-title":"ResMLP: Feedforward networks for image classification with data-efficient training","author":"Touvron","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00426"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00387"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref54","article-title":"Diffusion-LM improves controllable text generation","author":"Li","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref56","article-title":"Mish: A self regularized non-monotonic neural activation function","author":"Misra","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_19"},{"key":"ref58","first-page":"13\u2009782","article-title":"Drop-DTW: Aligning common signal between sequences while dropping outliers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dvornik"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref60","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10804102.pdf?arnumber=10804102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:48Z","timestamp":1738821648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":62,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3518762","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":[[2025,3]]}}}