{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:23Z","timestamp":1740169343433,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFC1523004"],"award-info":[{"award-number":["2020YFC1523004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3394209","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T18:01:58Z","timestamp":1714154518000},"page":"73258-73267","source":"Crossref","is-referenced-by-count":0,"title":["A Dual-Branch Spatial\u2013Temporal Learning Network for Video Prediction"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7231-6946","authenticated-orcid":false,"given":"Huilin","family":"Huang","sequence":"first","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yepeng","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3350643"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2954540"},{"key":"ref3","first-page":"1","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Finn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3352129"},{"key":"ref5","first-page":"152","article-title":"Learning to see physics via visual de-animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wu"},{"key":"ref6","first-page":"2688","article-title":"Neural relational inference for interacting systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kipf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00558"},{"key":"ref8","article-title":"Revisiting hierarchical approach for persistent long-term video prediction","author":"Lee","year":"2021","journal-title":"arXiv:2104.06697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00786"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00096"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref13","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"Lotter","year":"2016","journal-title":"arXiv:1605.08104"},{"key":"ref14","article-title":"Decomposing motion and content for natural video sequence prediction","author":"Villegas","year":"2017","journal-title":"arXiv:1706.08033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01356"},{"key":"ref16","first-page":"1","article-title":"Efficient and information-preserving future frame prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00394"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2992184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01729"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00910"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref26","first-page":"26950","article-title":"MAU: A motion-aware unit for video prediction and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref28","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Shi"},{"key":"ref29","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","volume":"37","author":"Srivastava"},{"key":"ref30","first-page":"1","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wang"},{"key":"ref31","first-page":"5123","article-title":"PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","volume-title":"Proc. PMLR Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref34","first-page":"1","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00461"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104612"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.031"},{"key":"ref40","article-title":"Stochastic variational video prediction","author":"Babaeizadeh","year":"2017","journal-title":"arXiv:1710.11252"},{"key":"ref41","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018","journal-title":"arXiv:1804.01523"},{"key":"ref42","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denton"},{"key":"ref43","first-page":"10628","article-title":"Video prediction via example guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref44","first-page":"3233","article-title":"Stochastic latent residual video prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref45","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","first-page":"110","article-title":"Ensemble learning","volume-title":"The Handbook Brain Theory Neural Networks","volume":"2","author":"Dietterich","year":"2002"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref56","article-title":"Deep multi-scale video prediction beyond mean square error","author":"Mathieu","year":"2015","journal-title":"arXiv:1511.05440"},{"key":"ref57","article-title":"STIP: A SpatioTemporal information-preserving and perception-augmented model for high-resolution video prediction","author":"Chang","year":"2022","journal-title":"arXiv:2206.04381"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00593"},{"key":"ref59","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Jia"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00048"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594264"},{"key":"ref63","article-title":"Mutual suppression network for video prediction using disentangled features","author":"Lee","year":"2018","journal-title":"arXiv:1804.04810"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10508954.pdf?arnumber=10508954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T04:35:17Z","timestamp":1717130117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3394209","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}