{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:27:41Z","timestamp":1743049661026,"version":"3.40.3"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703515"},{"type":"electronic","value":"9783031703522"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70352-2_1","type":"book-chapter","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T00:01:55Z","timestamp":1724976115000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable and\u00a0Generalizable Spatiotemporal Predictive Learning with\u00a0Disentangled Consistency"],"prefix":"10.1007","author":[{"given":"Jingxuan","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangyang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linzhuang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bihui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"1_CR1","unstructured":"Acharya, D., Huang, Z., Paudel, D.P., Van\u00a0Gool, L.: Towards high resolution video generation with progressive growing of sliced wasserstein gans. arXiv preprint arXiv:1810.02419 (2018)"},{"key":"1_CR2","unstructured":"Babaeizadeh, M., et\u00a0al.: Stochastic variational video prediction. In: ICLR (2018)"},{"key":"1_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-030-58592-1_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Bhagat","year":"2020","unstructured":"Bhagat, S., Uppal, S., Yin, Z., Lim, N.: Disentangling multiple features in video sequences using Gaussian processes in variational autoencoders. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 102\u2013117. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_7"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: A survey on generative diffusion models. IEEE Trans. Knowl. Data Eng. (2024)","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chai, Z., et\u00a0al.: CMS-LSTM: context embedding and multi-scale spatiotemporal expression LSTM for predictive learning. In: ICME, pp. 01\u201306 (2022)","DOI":"10.1109\/ICME52920.2022.9859659"},{"key":"1_CR6","unstructured":"Chang, Z., et\u00a0al.: Mau: a motion-aware unit for video prediction and beyond. Adv. NIPS 34 (2021)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Cho, K., et\u00a0al.: On the properties of neural machine translation: encoder\u2013decoder approaches. In: Proceedings of SSST-8, pp. 103\u2013111 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"1_CR8","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. arXiv preprint arXiv:1907.06571 (2019)"},{"key":"1_CR9","unstructured":"Cover, T.M., Thomas, J.A.: Elements of information theory second edition solutions to problems. Internet Access, 19\u201320 (2006)"},{"key":"1_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-194-6","volume-title":"Essential Topology","author":"MD Crossley","year":"2006","unstructured":"Crossley, M.D.: Essential Topology. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/1-84628-194-6"},{"key":"1_CR11","unstructured":"Denton, E.L., et\u00a0al.: Unsupervised learning of disentangled representations from video. Adv. NIPS 30 (2017)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Gao, Z., Tan, C., Li, S.Z.: Simvp: simpler yet better video prediction. In: Proceedings of CVPR, pp. 3170\u20133180 (2022)","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"1_CR13","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: International Conference on Machine Learning, pp. 1243\u20131252. PMLR (2017)"},{"key":"1_CR14","unstructured":"Guen, V.L., Thome, N.: Disentangling physical dynamics from unknown factors for unsupervised video prediction. In: Proceedings of CVPR, pp. 11474\u201311484 (2020)"},{"key":"1_CR15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511524646","volume-title":"The Large Scale Structure of Space-Time","author":"SW Hawking","year":"1973","unstructured":"Hawking, S.W., Ellis, G.F.R.: The Large Scale Structure of Space-Time, vol. 1. Cambridge University Press, Cambridge (1973)"},{"issue":"8","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR17","unstructured":"Hsieh, J.T., et\u00a0al.: Learning to decompose and disentangle representations for video prediction. Adv. NIPS 31 (2018)"},{"key":"1_CR18","unstructured":". Jia, X., et\u00a0al.: Dynamic filter networks. Adv. NIPS 29 (2016)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Jin, B., et\u00a0al.: Varnet: exploring variations for unsupervised video prediction. In: IROS, pp. 5801\u20135806 (2018)","DOI":"10.1109\/IROS.2018.8594264"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Jin, B., et\u00a0al.: Exploring spatial-temporal multi-frequency analysis for high-fidelity and temporal-consistency video prediction. In: Proceedings of CVPR, pp. 4554\u20134563 (2020)","DOI":"10.1109\/CVPR42600.2020.00461"},{"issue":"6","key":"1_CR21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138","volume":"69","author":"A Kraskov","year":"2004","unstructured":"Kraskov, A., St\u00f6gbauer, H., Grassberger, P.: Estimating mutual information. Phys. Rev. E 69(6), 066138 (2004)","journal-title":"Phys. Rev. E"},{"key":"1_CR22","unstructured":"Lee, A.X., et\u00a0al.: Stochastic adversarial video prediction. arXiv preprint arXiv:1804.01523 (2018)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Lee, S., et\u00a0al.: Video prediction recalling long-term motion context via memory alignment learning. In: Proceedings of CVPR, pp. 3054\u20133063 (2021)","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"1_CR24","unstructured":"Li, S., et al.: Semireward: a general reward model for semi-supervised learning. arXiv preprint arXiv:2310.03013 (2023)"},{"key":"1_CR25","unstructured":"Li, S., et al.: Moganet: multi-order gated aggregation network. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"1_CR26","unstructured":"Li, S., et\u00a0al.: Masked modeling for self-supervised representation learning on vision and beyond. arXiv preprint arXiv:2401.00897 (2023)"},{"issue":"5","key":"1_CR27","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TPAMI.2007.70735","volume":"30","author":"T Lin","year":"2008","unstructured":"Lin, T., Zha, H.: Riemannian manifold learning. IEEE Trans. Pattern Anal. Mach. Intell. 30(5), 796\u2013809 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"1_CR28","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1109\/TCSVT.2020.3021409","volume":"31","author":"X Liu","year":"2020","unstructured":"Liu, X., Yin, J., Liu, J., Ding, P., Liu, J., Liu, H.: Trajectorycnn: a new spatio-temporal feature learning network for human motion prediction. IEEE Trans. Circuits Syst. Video Technol. 31(6), 2133\u20132146 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1_CR29","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. In: ICLR (2017)"},{"key":"1_CR30","series-title":"Studies in Big Data","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-3-030-59338-4_19","volume-title":"Machine Learning and Big Data Analytics Paradigms: Analysis, Applications and Challenges","author":"A Mahmoud","year":"2021","unstructured":"Mahmoud, A., Mohammed, A.: A survey on deep learning for time-series forecasting. In: Hassanien, A.E., Darwish, A. (eds.) Machine Learning and Big Data Analytics Paradigms: Analysis, Applications and Challenges. SBD, vol. 77, pp. 365\u2013392. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-59338-4_19"},{"key":"1_CR31","unstructured":"Marc\u2019Aurelio\u00a0Ranzato, A.S., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. CoRR arxiv:1412.66042 (2014)"},{"key":"1_CR32","volume-title":"Introduction to Topology","author":"B Mendelson","year":"1990","unstructured":"Mendelson, B.: Introduction to Topology. Courier Corporation, North Chelmsford (1990)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Oliu, M., Selva, J., Escalera, S.: Folded recurrent neural networks for future video prediction. In: Proceedings of ECCV, pp. 716\u2013731 (2018)","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"1_CR34","unstructured":"Oprea, S., et\u00a0al.: A review on deep learning techniques for video prediction. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"1_CR35","unstructured":"Patraucean, V., Handa, A., Cipolla, R.: Spatio-temporal video autoencoder with differentiable memory. arXiv preprint arXiv:1511.06309 (2015)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Schuldt, C., et\u00a0al.: Recognizing human actions: a local SVM approach. In: ICPR, vol.\u00a03, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"1_CR37","unstructured":"Shi, X., et\u00a0al.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv. NIPS 28 (2015)"},{"key":"1_CR38","unstructured":"Simmons, G.F.: Introduction to topology and modern analysis, vol.\u00a044. Tokyo (1963)"},{"key":"1_CR39","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML, pp. 843\u2013852 (2015)"},{"key":"1_CR40","first-page":"13714","volume":"33","author":"J Su","year":"2020","unstructured":"Su, J., et al.: Convolutional tensor-train LSTM for spatio-temporal learning. Adv. NIPS 33, 13714\u201313726 (2020)","journal-title":"Adv. NIPS"},{"key":"1_CR41","unstructured":"Tan, C., Gao, Z., Li, S., Li, S.Z.: Simvp: towards simple yet powerful spatiotemporal predictive learning. arXiv preprint arXiv:2211.12509 (2022)"},{"key":"1_CR42","first-page":"69819","volume":"36","author":"C Tan","year":"2023","unstructured":"Tan, C., et al.: Openstl: a comprehensive benchmark of spatio-temporal predictive learning. Adv. Neural. Inf. Process. Syst. 36, 69819\u201369831 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Tan, C., et al.: Boosting the power of small multimodal reasoning models to match larger models with self-consistency training. arXiv preprint arXiv:2311.14109 (2023)","DOI":"10.1007\/978-3-031-73661-2_17"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Tan, C., Xia, J., Wu, L., Li, S.Z.: Co-learning: learning from noisy labels with self-supervision. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1405\u20131413 (2021)","DOI":"10.1145\/3474085.3475622"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Tan, C., et\u00a0al.: Temporal attention unit: towards efficient spatiotemporal predictive learning. arXiv preprint arXiv:2206.12126 (2022)","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"1_CR46","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. In: International Conference on Learning Representations (2019)"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Tulyakov, et\u00a0al.: Mocogan: decomposing motion and content for video generation. In: Proceedings of CVPR, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"1_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 5998\u20136008 (2017)"},{"key":"1_CR49","unstructured":"Villegas, R., et\u00a0al.: Decomposing motion and content for natural video sequence prediction. In: ICLR (2017)"},{"key":"1_CR50","unstructured":"Wang, Y., et\u00a0al.: Predrnn: recurrent neural networks for predictive learning using spatiotemporal LSTMs. Adv. NIPS 30 (2017)"},{"key":"1_CR51","unstructured":"Wang, Y., et\u00a0al.: Eidetic 3D LSTM: a model for video prediction and beyond. In: ICLR (2018)"},{"key":"1_CR52","unstructured":"Wang, Y., et\u00a0al.: Predrnn++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: ICML, pp. 5123\u20135132 (2018)"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Memory in memory: a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In: Proceedings of CVPR, pp. 9154\u20139162 (2019)","DOI":"10.1109\/CVPR.2019.00937"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Enhancing human-like multi-modal reasoning: a new challenging dataset and comprehensive framework. arXiv preprint arXiv:2307.12626 (2023)","DOI":"10.1007\/s00521-024-10310-2"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Wu, H., et\u00a0al.: Motionrnn: a flexible model for video prediction with spacetime-varying motions. In: Proceedings of CVPR, pp. 15435\u201315444 (2021)","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"1_CR56","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wang, Y., Long, M., Wang, J., KLiss, M.: Predcnn: predictive learning with cascade convolutions. In: IJCAI, pp. 2940\u20132947 (2018)","DOI":"10.24963\/ijcai.2018\/408"},{"key":"1_CR58","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"1_CR59","unstructured":"Yu, W., et\u00a0al.: Efficient and information-preserving future frame prediction and beyond. In: ICLR (2019)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70352-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T13:51:05Z","timestamp":1732715465000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70352-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703515","9783031703522"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70352-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Our submission does not involve any ethical issues, including but not limited to privacy, security, etc.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}