{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:58:36Z","timestamp":1767034716955,"version":"3.37.3"},"reference-count":24,"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\/icme51207.2021.9428362","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":6,"title":["ASTM: An Attention based Spatiotemporal Model for Video Prediction Using 3D Convolutional Neural Networks"],"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref11","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"ICML"},{"key":"ref12","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NeurIPS"},{"key":"ref13","first-page":"802","article-title":"Convolutional lstm network: a machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"NeurIPS"},{"key":"ref14","first-page":"879","article-title":"Predrnn: recurrent neural networks for predictive learning using spatiotemporal lstms","author":"wang","year":"2017","journal-title":"NeurIPS"},{"key":"ref15","first-page":"5123","article-title":"Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref16","article-title":"Eidetic 3d lstm: A model for video prediction and beyond","author":"wang","year":"2019","journal-title":"ICLRE"},{"key":"ref17","article-title":"Efficient and information-preserving future frame prediction and beyond","author":"yu","year":"2019","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref4","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"ICLRE"},{"key":"ref3","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"NeurIPS"},{"article-title":"Stochastic adversarial video prediction","year":"2018","author":"lee","key":"ref6"},{"key":"ref5","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2018","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2579505"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref1","article-title":"Image and video compression with neural networks: A review","author":"ma","year":"2019","journal-title":"TCSVT"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref24","article-title":"A review on deep learning techniques for video prediction","author":"oprea","year":"2020","journal-title":"TPAMI"},{"key":"ref23","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"2017","journal-title":"ICML"}],"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\/09428362.pdf?arnumber=9428362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T18:27:46Z","timestamp":1682965666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428362","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}