{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:53:16Z","timestamp":1792515196307,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681489","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"2917-2926","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4084-1409","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5152-4014","authenticated-orcid":false,"given":"Fan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0213-9957","authenticated-orcid":false,"given":"Chong","family":"Chen","sequence":"additional","affiliation":[{"name":"Terminus Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8232-5049","authenticated-orcid":false,"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[{"name":"Terminus Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7987-3714","authenticated-orcid":false,"given":"Xiao","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5714-0149","authenticated-orcid":false,"given":"Haixin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Babaeizadeh Mohammad","year":"2017","unstructured":"Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy H Campbell, and Sergey Levine. 2017. Stochastic variational video prediction. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00096"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01356"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00281-6"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946475"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351054"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1321--1330","author":"Cohen Taco","year":"2019","unstructured":"Taco Cohen, Maurice Weiler, Berkay Kicanaoglu, and Max Welling. 2019. Gauge equivariant convolutional networks and the icosahedral CNN. In Proceedings of the International Conference on Machine Learning. 1321--1330."},{"key":"e_1_3_2_1_10_1","volume-title":"Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge. In International Conference on Learning Representations.","author":"de Bezenac Emmanuel","unstructured":"Emmanuel de Bezenac, Arthur Pajot, and Patrick Gallinari. [n.,d.]. Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285","author":"Dumoulin Vincent","year":"2016","unstructured":"Vincent Dumoulin and Francesco Visin. 2016. A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285 (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the International Conference on Machine Learning. 3233--3246","author":"Franceschi Jean-Yves","year":"2020","unstructured":"Jean-Yves Franceschi, Edouard Delasalles, Micka\u00ebl Chen, Sylvain Lamprier, and Patrick Gallinari. 2020. Stochastic latent residual video prediction. In Proceedings of the International Conference on Machine Learning. 3233--3246."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.109056"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11474--11484","author":"Guen Vincent Le","year":"2020","unstructured":"Vincent Le Guen and Nicolas Thome. 2020. Disentangling physical dynamics from unknown factors for unsupervised video prediction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11474--11484."},{"key":"e_1_3_2_1_17_1","volume-title":"Adaptive fourier neural operators: Efficient token mixers for transformers. arXiv preprint arXiv:2111.13587","author":"Guibas John","year":"2021","unstructured":"John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao, Anima Anandkumar, and Bryan Catanzaro. 2021. Adaptive fourier neural operators: Efficient token mixers for transformers. arXiv preprint arXiv:2111.13587 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Guibas John","year":"2021","unstructured":"John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao, Anima Anandkumar, and Bryan Catanzaro. 2021. Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3265201"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00593"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Lee Wonkwang","year":"2021","unstructured":"Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, and Seunghoon Hong. 2021. Revisiting hierarchical approach for persistent long-term video prediction. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems.","author":"Levina Elizaveta","year":"2004","unstructured":"Elizaveta Levina and Peter Bickel. 2004. Maximum likelihood estimation of intrinsic dimension. In Proceedings of the Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Li Zongyi","year":"2020","unstructured":"Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, and Anima Anandkumar. 2020. Fourier neural operator for parametric partial differential equations. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539397"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the International Conference on Machine Learning. 3208--3216","author":"Long Zichao","year":"2018","unstructured":"Zichao Long, Yiping Lu, Xianzhong Ma, and Bin Dong. 2018. Pde-net: Learning pdes from data. In Proceedings of the International Conference on Machine Learning. 3208--3216."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Lotter William","year":"2017","unstructured":"William Lotter, Gabriel Kreiman, and David Cox. 2017. Deep predictive coding networks for video prediction and unsupervised learning. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00302-5"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00313"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00385"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291125.3291150"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_37_1","volume-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification.","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. Dynamicvit: Efficient vision transformers with dynamic token sparsification. (2021), 13937--13949."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems.","author":"Shi Xingjian","year":"2015","unstructured":"Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-Kin Wong, and Wang-chun Woo. 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Proceedings of the Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Srivastava Nitish","year":"2015","unstructured":"Nitish Srivastava, Elman Mansimov, and Ruslan Salakhutdinov. 2015. Unsupervised Learning of Video Representations Using LSTMs. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML'15). JMLR.org, 843--852."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems.","author":"Den Oord Aaron Van","year":"2017","unstructured":"Aaron Van Den Oord, Oriol Vinyals, et al. 2017. Neural discrete representation learning. In Proceedings of the Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_42_1","first-page":"22009","article-title":"Sevir: A storm event imagery dataset for deep learning applications in radar and satellite meteorology","volume":"33","author":"Veillette Mark","year":"2020","unstructured":"Mark Veillette, Siddharth Samsi, and Chris Mattioli. 2020. Sevir: A storm event imagery dataset for deep learning applications in radar and satellite meteorology. Advances in Neural Information Processing Systems, Vol. 33 (2020), 22009--22019.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems.","author":"Villegas Ruben","year":"2019","unstructured":"Ruben Villegas, Arkanath Pathak, Harini Kannan, Dumitru Erhan, Quoc V Le, and Honglak Lee. 2019. High fidelity video prediction with large stochastic recurrent neural networks. In Proceedings of the Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Villegas Ruben","year":"2017","unstructured":"Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, and Honglak Lee. 2017. Decomposing motion and content for natural video sequence prediction. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems.","author":"Wang Ting-Chun","year":"2018","unstructured":"Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Guilin Liu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018. Video-to-video synthesis. In Proceedings of the Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_46_1","volume-title":"International conference on learning representations.","author":"Wang Yunbo","year":"2019","unstructured":"Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, and Li Fei-Fei. 2019. Eidetic 3d lstm: A model for video prediction and beyond. In International conference on learning representations."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00558"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01729"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the International Conference on Machine Learning. 10628--10637","author":"Xu Jingwei","year":"2020","unstructured":"Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, and Trevor Darrell. 2020. Video prediction via example guidance. In Proceedings of the International Conference on Machine Learning. 10628--10637."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547770"},{"key":"e_1_3_2_1_54_1","volume-title":"Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157","author":"Yan Wilson","year":"2021","unstructured":"Wilson Yan, Yunzhi Zhang, Pieter Abbeel, and Aravind Srinivas. 2021. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157 (2021)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00466-019-01718-y"},{"key":"e_1_3_2_1_56_1","volume-title":"VPTR: Efficient Transformers for Video Prediction. In International Conference on Pattern Recognition. 3492--3499","author":"Ye Xi","year":"2022","unstructured":"Xi Ye and Guillaume-Alexandre Bilodeau. 2022. VPTR: Efficient Transformers for Video Prediction. In International Conference on Pattern Recognition. 3492--3499."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"e_1_3_2_1_58_1","volume-title":"Efficient VVC Intra Prediction Based on Deep Feature Fusion and Probability Estimation","author":"Zhao Tiesong","year":"2022","unstructured":"Tiesong Zhao, Yuhang Huang, Weize Feng, Yiwen Xu, and Sam Kwong. 2022. Efficient VVC Intra Prediction Based on Deep Feature Fusion and Probability Estimation. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261755"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681489","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681489"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":59,"alternative-id":["10.1145\/3664647.3681489","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681489","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}