{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:56:19Z","timestamp":1767034579233,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428231","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":7,"title":["STAE: A Spatiotemporal Auto-Encoder for High-Resolution Video Prediction"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Chang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanshe","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,Institute of Digital Media,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Peking University,Institute of Digital Media,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Group,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University,Institute of Digital Media,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref11","article-title":"Eidetic 3d lstm: A model for video prediction and beyond","author":"wang","year":"2019","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"article-title":"Decomposing motion and content for natural video sequence prediction","year":"2017","author":"villegas","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"article-title":"Video (language) modeling: a baseline for generative models of natural videos","year":"2014","author":"ranzato","key":"ref4"},{"key":"ref3","article-title":"Efficient and information-preserving future frame prediction and beyond","author":"yu","year":"2019","journal-title":"ICLRE"},{"key":"ref6","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"ICLRE"},{"key":"ref5","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"ICML"},{"article-title":"Deep predictive coding networks for video prediction and unsupervised learning","year":"2016","author":"lotter","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"ref2","first-page":"802","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"NeurIPS"},{"key":"ref1","article-title":"Image and video compression with neural networks: A review","author":"ma","year":"2019","journal-title":"TCSVT"},{"key":"ref9","first-page":"879","article-title":"Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms","author":"wang","year":"2017","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref21","article-title":"A review on deep learning techniques for video prediction","author":"oprea","year":"2020","journal-title":"TPAMI"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428231.pdf?arnumber=9428231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T18:27:39Z","timestamp":1682965659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428231","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}