{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T22:31:04Z","timestamp":1782253864226,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Funds for International Cooperation and Exchange of the National Natural Science Foundation of China","award":["62461160310"],"award-info":[{"award-number":["62461160310"]}]},{"name":"Key Program of the National Natural Science Foundation of China","award":["62431011"],"award-info":[{"award-number":["62431011"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025101"],"award-info":[{"award-number":["62025101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PCL-CMCC Foundation for science and innovation","award":["2024ZY1C0040"],"award-info":[{"award-number":["2024ZY1C0040"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3572735","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T13:58:37Z","timestamp":1747922317000},"page":"7916-7929","source":"Crossref","is-referenced-by-count":2,"title":["STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8986-6841","authenticated-orcid":false,"given":"Zheng","family":"Chang","sequence":"first","affiliation":[{"name":"Huawei Technologies, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7517-3868","authenticated-orcid":false,"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7665-7434","authenticated-orcid":false,"given":"Shanshe","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2731-5403","authenticated-orcid":false,"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8070-802X","authenticated-orcid":false,"given":"Wen","family":"Gao","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104305"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_45"},{"key":"ref4","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Finn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045007"},{"key":"ref6","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"Ranzato","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref9","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xingjian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref12","article-title":"Delving deeper into convolutional networks for learning video representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ballas"},{"key":"ref13","first-page":"5617","article-title":"Deep learning for precipitation nowcasting: A benchmark and a new model","author":"Shi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506391"},{"key":"ref15","first-page":"879","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref16","first-page":"5123","article-title":"PredRNN: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","volume-title":"Proc. Int. Conf Mach. Learn.","author":"Wang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref18","article-title":"Efficient and information-preserving future frame prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref22","article-title":"Eidetic 3 D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428362"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428231"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859659"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref29","article-title":"Stochastic variational video prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Babaeizadeh"},{"key":"ref30","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denton"},{"key":"ref31","first-page":"3233","article-title":"Stochastic latent residual video prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref32","first-page":"10628","article-title":"Video prediction via example guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00235"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref35","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2998297"},{"key":"ref38","article-title":"Transformation-based adversarial video prediction on large-scale data","author":"Luc","year":"2020"},{"key":"ref39","article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mathieu"},{"key":"ref40","article-title":"MAU: A motion-aware unit for video prediction and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995667"},{"key":"ref44","first-page":"344","article-title":"Self-supervised visual planning with temporal skip connections","volume-title":"Proc. Conf. Robot Learn.","author":"Ebert"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref46","article-title":"On information and sufficiency","author":"Zhu","year":"1997","journal-title":"Ann. Statist."},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref48","first-page":"1771","article-title":"Video pixel networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"ref50","article-title":"The mnist database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref51","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref52","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lotter"},{"key":"ref53","article-title":"Decomposing motion and content for natural video sequence prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Villegas"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00819"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01729"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00593"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00374"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01827"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00691"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11010155.pdf?arnumber=11010155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:38Z","timestamp":1755546218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11010155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":61,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3572735","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":[[2025,9]]}}}