{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T21:55:11Z","timestamp":1793051711395,"version":"4.5.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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","award":["62025101"],"award-info":[{"award-number":["62025101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072008"],"award-info":[{"award-number":["62072008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071449"],"award-info":[{"award-number":["62071449"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20184"],"award-info":[{"award-number":["U20A20184"]}],"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","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-performance Computing Platform of Peking University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3146721","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T22:31:14Z","timestamp":1643322674000},"page":"2354-2367","source":"Crossref","is-referenced-by-count":33,"title":["STAM: A SpatioTemporal Attention Based Memory for Video Prediction"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8986-6841","authenticated-orcid":false,"given":"Zheng","family":"Chang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 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 Laboratory for Video 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 Laboratory for Video 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 Laboratory for Video Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594264"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref12","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref56","article-title":"3DSRNet: Video super-resolution using 3D convolutional neural networks","author":"kim","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_44"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref14","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00190"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00803"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00441"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref17","first-page":"1174","article-title":"Stochastic video generation with a learned prior","author":"denton","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","first-page":"3233","article-title":"Stochastic latent residual video prediction","author":"franceschi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035281"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018618"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20876-9_39"},{"key":"ref46","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"ji","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5893"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref42","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"ref43","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"ranzato","year":"2014"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"2990","DOI":"10.1109\/TMM.2020.2965434","article-title":"Spatio-temporal attention networks for action recognition and detection","volume":"22","author":"li","year":"2020","journal-title":"IEEE Trans Multimedia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref7","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946475"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3104305"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2639379"},{"key":"ref5","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428231"},{"key":"ref35","article-title":"CMS-LSTM: Context-embedding and multi-scale spatiotemporal-expression LSTM for video prediction","author":"chai","year":"2021"},{"key":"ref34","article-title":"Efficient and information-preserving future frame prediction and beyond","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref31","first-page":"5123","article-title":"PredRNN: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"879","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMS","author":"wang","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2579505"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2323939"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428362"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref71","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref70","first-page":"13?714","article-title":"Convolutional tensor-train LSTM for spatio-temporal learning","volume":"33","author":"su","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00819"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref68","first-page":"667","article-title":"Dynamic filter networks","author":"jia","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045007"},{"key":"ref26","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref25","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMS","author":"srivastava","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref69","first-page":"5617","article-title":"Deep learning for precipitation nowcasting: A benchmark and a new model","volume":"30","author":"shi","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"10628","article-title":"Video prediction via example guidance","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","article-title":"MAU: A motion-aware unit for video prediction and beyond","volume":"34","author":"chang","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref63","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref22","article-title":"Stochastic adversarial video prediction","author":"lee","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref21","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"0"},{"key":"ref65","first-page":"716","article-title":"Folded recurrent neural networks for future video prediction","author":"oliu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"ref27","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"0","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00158"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","article-title":"Pedestrian detection: An evaluation of the state of the art","volume":"34","author":"dollar","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref62","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR (Poster)"},{"key":"ref61","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09695337.pdf?arnumber=9695337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:44:33Z","timestamp":1687805073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9695337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3146721","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}