{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:37:32Z","timestamp":1773416252835,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688193","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["SIAM: A Simple Alternating Mixer for Video Prediction"],"prefix":"10.1109","author":[{"given":"Xin","family":"Zheng","sequence":"first","affiliation":[{"name":"Fudan University,Shanghai Key Lab of Intelligent Information Processing,School of Computer Science,Shanghai,China,200433"}]},{"given":"Ziang","family":"Peng","sequence":"additional","affiliation":[{"name":"Fudan University,Department of Aeronautics and Astronautics,Shanghai,China,200433"}]},{"given":"Yuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai Key Lab of Intelligent Information Processing,School of Computer Science,Shanghai,China,200433"}]},{"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[{"name":"Fudan University,Institute of Science and Technology for Brain-Inspired Intelligence,Shanghai,China,200433"}]},{"given":"Junping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai Key Lab of Intelligent Information Processing,School of Computer Science,Shanghai,China,200433"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MCVD masked conditional video diffusion for prediction, generation, and interpolation","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Voleti"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095169"},{"key":"ref3","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Finn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01356"},{"key":"ref8","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Shi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-xlii-2-w16-3-2019"},{"key":"ref14","article-title":"Earthformer: Exploring space-time transformers for earth system forecasting","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Gao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25289"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00542"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01239"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Tolstikhin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref21","article-title":"Openstl: A comprehensive benchmark of spatio-temporal predictive learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Tan"},{"key":"ref22","article-title":"MAU: A Motion-Aware Unit for Video Prediction and Beyond","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Chang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688193.pdf?arnumber=10688193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:42:37Z","timestamp":1727764957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688193","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}