{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:21:11Z","timestamp":1776882071801,"version":"3.51.2"},"reference-count":125,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62072427"],"award-info":[{"award-number":["62072427"]}],"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":["12227901"],"award-info":[{"award-number":["12227901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Team in Basic Research Field, CAS","award":["YSBR-005"],"award-info":[{"award-number":["YSBR-005"]}]},{"name":"Academic Leaders Cultivation Program"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2024A03J0620"],"award-info":[{"award-number":["2024A03J0620"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tkde.2024.3363711","type":"journal-article","created":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T13:56:12Z","timestamp":1707400572000},"page":"4050-4062","source":"Crossref","is-referenced-by-count":10,"title":["Modeling Spatio-Temporal Dynamical Systems With Neural Discrete Learning and Levels-of-Experts"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0602-169X","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0795-3790","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6405-3289","authenticated-orcid":false,"given":"Guibin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3317-2103","authenticated-orcid":false,"given":"Junfeng","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-7337","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"additional","affiliation":[{"name":"INTR Thrust &#x0026; DSA Thrust, The Hong Kong University of Science and Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4435-9413","authenticated-orcid":false,"given":"Yuankai","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-7053","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/2025075"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0402_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1515\/9781937585730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/9781009023405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.177701"},{"key":"ref6","first-page":"9422","article-title":"Learning diverse and discriminative representations via the principle of maximal coding rate reduction","volume":"33","author":"Yu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"ref7","first-page":"4907","article-title":"ReduNet: A white-box deep network from the principle of maximizing rate reduction","volume":"23","author":"Chan","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.177.4047.393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/posc_a_00449"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/1352-2310(95)00442-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1972)011<0312:NMOAAD>2.0.CO;2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/S0022112005008153"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3219104.3229262"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-011-2388-4","volume-title":"Dynamical Systems: Differential Equations, Maps, and Chaotic Behaviour","volume":"5","author":"Arrowsmith","year":"1992"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1090\/S0273-0979-1984-15236-4"},{"key":"ref16","volume-title":"Differential Equations, Dynamical Systems, and an Introduction to Chaos","author":"Hirsch","year":"2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2991\/978-94-6239-021-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61453-8"},{"key":"ref19","volume-title":"Introduction to Applied Nonlinear Dynamical Systems and Chaos","volume":"2","author":"Wiggins","year":"2003"},{"key":"ref20","volume-title":"Dynamics and Bifurcations","volume":"3","author":"Hale","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/b11772"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2019.000565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2015.12.040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fluid.30.1.539"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fl.16.010184.000531"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.28.76"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0009-2509(99)00235-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fluid.40.111406.102130"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2011.01.012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0379-7112(02)00082-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2023.0422"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.114034"},{"key":"ref33","volume-title":"Dynamics of Physical Systems","author":"Cannon","year":"2003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12601-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00281-6"},{"issue":"3","key":"ref36","first-page":"271","article-title":"Finite difference method for numerical computation of discontinuous solutions of the equations of fluid dynamics","volume":"47","author":"Godunov","year":"1959","journal-title":"Matemati\u010deskij Sbornik"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.59.337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/50\/10\/103001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/10273669708833012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref41","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3195"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref48","article-title":"Physics-aware difference graph networks for sparsely-observed dynamics","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Seo"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref51","first-page":"25 390","article-title":"Earthformer: Exploring space-time transformers for earth system forecasting","volume":"35","author":"Gao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref53","article-title":"Learning mesh-based simulation with graph networks","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Pfaff"},{"key":"ref54","first-page":"6309","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref55","article-title":"SOM-VAE: Interpretable discrete representation learning on time series","author":"Fortuin","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10934"},{"key":"ref58","first-page":"4542","article-title":"Visual interaction networks: Learning a physics simulator from video","volume":"30","author":"Watters","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0093"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403198"},{"key":"ref61","first-page":"10 638","article-title":"Amortized finite element analysis for fast PDE-constrained optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xue"},{"key":"ref62","first-page":"4470","article-title":"Graph networks as learnable physics engines for inference and control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sanchez-Gonzalez"},{"key":"ref63","first-page":"152","article-title":"Learning to see physics via visual de-animation","volume":"30","author":"Wu","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64","article-title":"Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","author":"Lu","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.08.029"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1718942115"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113250"},{"key":"ref68","article-title":"Predicting parametric spatiotemporal dynamics by multi-resolution PDE structure-preserved deep learning","author":"Liu","year":"2022"},{"key":"ref69","article-title":"Hard encoding of physics for learning spatiotemporal dynamics","author":"Rao","year":"2021"},{"key":"ref70","article-title":"Discovering nonlinear PDEs from scarce data with physics-encoded learning","author":"Rao","year":"2022"},{"key":"ref71","first-page":"23 426","article-title":"Meta-auto-decoder for solving parametric partial differential equations","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.143"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_2"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.509"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"ref79","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref80","article-title":"Predicting video with VQVAE","author":"Walker","year":"2021"},{"key":"ref81","article-title":"Streamlining multimodal data fusion in wireless communication and sensor networks","author":"Bocus","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1101"},{"key":"ref84","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","volume":"28","author":"Oh","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref85","article-title":"Deep multi-scale video prediction beyond mean square error","author":"Mathieu","year":"2015"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref87","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"Ranzato","year":"2014"},{"key":"ref88","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref89","first-page":"3560","article-title":"Learning to generate long-term future via hierarchical prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Villegas"},{"key":"ref90","first-page":"6038","article-title":"Hierarchical long-term video prediction without supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Villegas"},{"key":"ref91","first-page":"11570","article-title":"Variational temporal abstraction","volume":"32","author":"Kim","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref92","article-title":"Scaling autoregressive video models","author":"Weissenborn","year":"2019"},{"key":"ref93","article-title":"Videoflow: A flow-based generative model for video","author":"Kumar","year":"2019"},{"key":"ref94","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3162882"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3008774"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482000"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/369"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3176650"},{"key":"ref101","first-page":"879","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume":"30","author":"Wang","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref102","first-page":"8832","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref104","first-page":"17 157","article-title":"Learning physics constrained dynamics using autoencoders","volume":"35","author":"Yang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref105","article-title":"Physics-as-inverse-graphics: Unsupervised physical parameter estimation from video","author":"Jaques","year":"2019"},{"key":"ref106","article-title":"Efficient and information-preserving future frame prediction and beyond","author":"Yu","year":"2020","journal-title":"Proc. 8th Int. Conf. Learn. Representations"},{"key":"ref107","article-title":"Stability regularization for discrete representation learning","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Pervez"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.215"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref110","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref111","article-title":"Efficient and information-preserving future frame prediction and beyond","author":"Wu","journal-title":"Proc. 8th Int. Conf. Learn. Representations"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3033"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3195"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000045324.43199.43"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref118","article-title":"FlowNet: Learning optical flow with convolutional networks","author":"Fischer","year":"2015"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref121","first-page":"22 009","article-title":"SEVIR: A storm event imagery dataset for deep learning applications in radar and satellite meteorology","volume":"33","author":"Veillette","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref122","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2020"},{"key":"ref123","article-title":"Adaptive fourier neural operators: Efficient token mixers for transformers","author":"Guibas","year":"2021"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref125","article-title":"PastNet: Introducing physical inductive biases for spatio-temporal video prediction","author":"Wu","year":"2023"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10589999\/10428110.pdf?arnumber=10428110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T18:28:04Z","timestamp":1766687284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10428110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":125,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3363711","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}