{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:29:39Z","timestamp":1770226179725,"version":"3.49.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031222153","type":"print"},{"value":"9783031222160","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-22216-0_35","type":"book-chapter","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T04:39:26Z","timestamp":1673930366000},"page":"511-528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning Sequential Latent Variable Models from\u00a0Multimodal Time Series Data"],"prefix":"10.1007","author":[{"given":"Oliver","family":"Limoyo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Ablett","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,18]]},"reference":[{"key":"35_CR1","unstructured":"Hafner, D., Lillicrap, T., Fischer, I., Villegas, R., Ha, D., Lee, H., Davidson, J.: Learning latent dynamics for planning from pixels. Int. Conf. Machine Learn. (ICML) 2555\u20132565 (2019)"},{"key":"35_CR2","unstructured":"Watter, M., Springenberg, J.T., Boedecker, J., Riedmiller, M.: Embed to control: a locally linear latent dynamics model for control from raw images. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 2746\u20132754 (2015)"},{"key":"35_CR3","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: Bengio, Y., LeCun, Y. (eds.) International Conference on Learning Representations (ICLR) (2014)"},{"key":"35_CR4","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning (ICML), pp. 1278\u20131286 (2014)"},{"key":"35_CR5","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering atari with discrete world models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"35_CR6","unstructured":"Rafailov, R., Yu, T., Rajeswaran, A., Finn, C.: Offline reinforcement learning from images with latent space models. In: Learning for Dynamics and Control (L4DC), pp. 1154\u20131168. PMLR (2021)"},{"issue":"3","key":"35_CR7","doi-asserted-by":"publisher","first-page":"2407","DOI":"10.1109\/LRA.2019.2901898","volume":"4","author":"B Ichter","year":"2019","unstructured":"Ichter, B., Pavone, M.: Robot motion planning in learned latent spaces. IEEE Robot. Autom. Lett. 4(3), 2407\u20132414 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Lippi, M., Poklukar, P., Welle, M.C., Varava, A., Yin, H., Marino, A., Kragic, D.: Latent space roadmap for visual action planning of deformable and rigid object manipulation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9340764"},{"key":"35_CR9","unstructured":"Zhang, M., Vikram, S., Smith, L., Abbeel, P., Johnson, M., Levine, S.: Solar: deep structured representations for model-based reinforcement learning. In: International Conference on Machine Learning (ICML), PMLR, pp. 7444\u20137453 (2019)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Wahlstr\u00f6m, N., Sch\u00f6n, T.B., Desienroth, M.P.: From pixels to torques: policy learning with deep dynamical models. In: ICML\u201915 Deep Learning Workshop (2015)","DOI":"10.1016\/j.ifacol.2015.12.271"},{"key":"35_CR11","unstructured":"Karl, M., S\u00f6lch, M., Bayer, J., van der Smagt, P.: Deep variational Bayes filters: unsupervised learning of state space models from raw data. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"35_CR12","unstructured":"Fraccaro, M., Kamronn, S., Paquet, U., Winther, O.: A disentangled recognition and nonlinear dynamics model for unsupervised learning. In Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 3601\u20133610 (2017)"},{"key":"35_CR13","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: International Conference on Machine Learning (ICML) (2011)"},{"issue":"2","key":"35_CR14","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Machine Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"35_CR15","unstructured":"Hristov, Y., Ramamoorthy, S.: Learning from demonstration with weakly supervised disentanglement. In: International Conference on Learning Representations (ICLR). (2021)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, K., Chen, C., Wang, B., Saputra, M.R.U., Trigoni, N., Markham, A.: VMLoc: Variational fusion for learning-based multimodal camera localization. In: Association for the Advancement of Artificial Intelligence Conference (AAAI) (2021), vol. 35, pp. 6165\u20136173","DOI":"10.1609\/aaai.v35i7.16767"},{"key":"35_CR17","unstructured":"Sergeant, J., Suenderhauf, N., Milford, M., Upcroft, B.: Multimodal deep autoencoders for control of a mobile robot. In: Li, H., Kim, J. (eds.) Proceedings of Australasian Conference on Robotics and Automation, Australia, pp. 1\u201310 (2015)"},{"key":"35_CR18","unstructured":"Wu, M., Goodman, N.: Multimodal generative models for scalable weakly-supervised learning. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 31 (2018)"},{"issue":"8","key":"35_CR19","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771\u20131800 (2002)","journal-title":"Neural Comput."},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: SSST-8 Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103\u2013111 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Kiela, D., Bottou, L.: Learning image embeddings using convolutional neural networks for improved multi-modal semantics. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 36\u201345 (2014)","DOI":"10.3115\/v1\/D14-1005"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"D\u2019mello, S.K., Kory, J.: A review and meta-analysis of multimodal affect detection systems. ACM Comput. Surv. (CSUR) 47(3) (2015) 1\u201336","DOI":"10.1145\/2682899"},{"key":"35_CR23","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Wetzel, D., Thater, S., Schiele, B., Pinkal, M.: Grounding action descriptions in videos. Trans. Assoc. Comput. Linguist. 1, 25\u201336 (2013)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Gandhi, D., Gupta, A., Pinto, L.: Swoosh! Rattle! Thump!-actions that sound. In: Robotics: Science and Systems (RSS) (2020)","DOI":"10.15607\/RSS.2020.XVI.002"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Lee, M., Yi, B., Martin-Martin, R., Savarese, S., Bohg, J.: Multimodal sensor fusion with differentiable filters. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9341579"},{"key":"35_CR26","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"35_CR27","unstructured":"Banijamali, E., Shu, R., Ghavamzadeh, M., Bui, H.H., Ghodsi, A.: Robust locally-linear controllable embedding. In: International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 84, pp. 1751\u20131759 (2018)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Krishnan, R.G., Shalit, U., Sontag, D.: Structured inference networks for nonlinear state space models. In: Association for the Advancement of Artificial Intelligence Conference (AAAI), pp. 2101\u20132109 (2017)","DOI":"10.1609\/aaai.v31i1.10779"},{"key":"35_CR29","unstructured":"Haarnoja, T., Ajay, A., Levine, S., Abbeel, P.: Backprop KF: Learning discriminative deterministic state estimators. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems (NeurIPS), vol. 29, pp. 4376\u20134384. Curran Associates, Inc. (2016)"},{"key":"35_CR30","first-page":"2946","volume":"29","author":"MJ Johnson","year":"2016","unstructured":"Johnson, M.J., Duvenaud, D., Wiltschko, A.B., Adams, R.P., Datta, S.R.: Composing graphical models with neural networks for structured representations and fast inference. Adv. Neural Inform. Proces. Syst. (NeurIPS) 29, 2946\u20132954 (2016)","journal-title":"Adv. Neural Inform. Proces. Syst. (NeurIPS)"},{"issue":"4","key":"35_CR31","doi-asserted-by":"publisher","first-page":"6654","DOI":"10.1109\/LRA.2020.3015449","volume":"5","author":"O Limoyo","year":"2020","unstructured":"Limoyo, O., Chan, B., Maric, F., Wagstaff, B., Mahmood, R., Kelly, J.: Heteroscedastic uncertainty for robust generative latent dynamics. IEEE Robot. Autom. Lett. 5(4), 6654\u20136661 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"35_CR32","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. Adv. Neural Inform. Proces. Syst. (NeurIPS) 2450\u20132462 (2018)"},{"issue":"1","key":"35_CR33","first-page":"2949","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep boltzmann machines. J. Machine Learn. Res. 15(1), 2949\u20132980 (2014)","journal-title":"J. Machine Learn. Res."},{"key":"35_CR34","unstructured":"Suzuki, M., Nakayama, K., Matsuo, Y.: Joint multimodal learning with deep generative models. arXiv preprint arXiv:1611.01891 (2016)"},{"key":"35_CR35","unstructured":"Vedantam, R., Fischer, I., Huang, J., Murphy, K.: Generative models of visually grounded imagination. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Rezaei-Shoshtari, S., Hogan, F.R., Jenkin, M., Meger, D., Dudek, G.: Learning intuitive physics with multimodal generative models. In: Association for the Advancement of Artificial Intelligence Conference (AAAI) (2021)","DOI":"10.1609\/aaai.v35i7.16761"},{"key":"35_CR37","unstructured":"Cao, Y., Fleet., D.J.: Generalized product of experts for automatic and principled fusion of Gaussian process predictions. In: NIPS\u201914 Modern Nonparametrics 3: Automating the Learning Pipeline Workshop (2014)"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Yu, K., Bauz\u00e1, M., Fazeli, N., Rodriguez, A.: More than a million ways to be pushed. A high-fidelity experimental dataset of planar pushing. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 30\u201337. IEEE (2016)","DOI":"10.1109\/IROS.2016.7758091"},{"key":"35_CR39","unstructured":"Coumans, E., Bai, Y.: Pybullet, A Python Module for Physics Simulation for Games, Robotics and Machine Learning (2016\u20132019). www.pybullet.org"},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Kloss, A., Schaal, S., Bohg, J.: Combining learned and analytical models for predicting action effects from sensory data. Int. J. Robot. Res. (2020)","DOI":"10.1177\/0278364920954896"},{"key":"35_CR41","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"35_CR42","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In Bengio, Y., LeCun, Y. (eds.) International Conference on Learning Representations (ICLR) (2015)"},{"key":"35_CR43","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., Piot, B., kavukcuoglu, k., Munos, R., Valko, M.: Bootstrap your own latent\u2013a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 21271\u201321284 (2020)"},{"key":"35_CR44","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2661\u20132671 (2019)","DOI":"10.1109\/CVPR.2019.00277"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Autonomous Systems 17"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22216-0_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T04:47:56Z","timestamp":1673930876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22216-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031222153","9783031222160"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22216-0_35","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Autonomous Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zagreb","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Croatia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ias2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ias-17.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}