{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:55:10Z","timestamp":1726055710985},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030336752"},{"type":"electronic","value":"9783030336769"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-33676-9_42","type":"book-chapter","created":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T17:20:30Z","timestamp":1572024030000},"page":"595-608","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning to Disentangle Latent Physical Factors for Video Prediction"],"prefix":"10.1007","author":[{"given":"Deyao","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Marco","family":"Munderloh","sequence":"additional","affiliation":[]},{"given":"Bodo","family":"Rosenhahn","sequence":"additional","affiliation":[]},{"given":"J\u00f6rg","family":"St\u00fcckler","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,25]]},"reference":[{"unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R., Levine, S.: Stochastic variational video prediction. In: ICLR (2018)","key":"42_CR1"},{"unstructured":"Battaglia, P., Pascanu, R., Lai, M., Rezende, D., Kavukcuoglu, K.: Interaction networks for learning about objects, relations and physics. In: NIPS (2016)","key":"42_CR2"},{"unstructured":"Burgess, C., Higgins, I., Pal, A., Matthey, L., Watters, N., Desjardins, G., Lerchner, A.: Understanding disentangling in beta -VAE. In: Learning Disentangle Representations: From Perception to Control workshop (2017)","key":"42_CR3"},{"unstructured":"Chen, T., Li, X., Grosse, R., Duvenaud, D.: Isolating sources of disentanglement in VAEs. In: NIPS (2018)","key":"42_CR4"},{"unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: NIPS (2016)","key":"42_CR5"},{"unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS Workshop (2014)","key":"42_CR6"},{"unstructured":"Ebert, F., Finn, C., Lee, X., Levine, S.: Self-supervised visual planning with temporal skip connections. In: CoRL (2017)","key":"42_CR7"},{"unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: NIPS (2016)","key":"42_CR8"},{"unstructured":"Fraccaro, M., Kamronn, S., Paquet, U., Winther, O.: A disentangled recognition and nonlinear dynamics model for unsupervised learning (2017)","key":"42_CR9"},{"unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)","key":"42_CR10"},{"unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 2555\u20132565. PMLR (2019)","key":"42_CR11"},{"unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)","key":"42_CR12"},{"unstructured":"Hochreiter, S., Schmidhuber, J.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Neural Computation (1997)","key":"42_CR13"},{"unstructured":"Johnson, M., Duvenaud, D.K., Wiltschko, A., Adams, R.P., Datta, S.R.: Composing graphical models with neural networks for structured representations and fast inference. In: Advances in Neural Information Processing Systems 29 (NIPS), pp. 2946\u20132954 (2016)","key":"42_CR14"},{"unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: CoRR (2018)","key":"42_CR15"},{"unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)","key":"42_CR16"},{"unstructured":"Kingma, D., Welling, M.: Auto-encoding variational Bayes. In: CoRR (2013)","key":"42_CR17"},{"key":"42_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-33765-9_15","volume-title":"Computer Vision \u2013 ECCV 2012","author":"KM Kitani","year":"2012","unstructured":"Kitani, K.M., Ziebart, B.D., Bagnell, J.A., Hebert, M.: Activity forecasting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 201\u2013214. Springer, Heidelberg (2012). \n                      https:\/\/doi.org\/10.1007\/978-3-642-33765-9_15"},{"unstructured":"Larsen, A., S\u00f8nderby, S., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. In: ICML (2016)","key":"42_CR19"},{"unstructured":"Lee, X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction. In: arXiv preprint (2018)","key":"42_CR20"},{"unstructured":"Lerer, A., Gross, S., Fergus, R.: Learning physical intuition of block towers by example. In: ICML (2016)","key":"42_CR21"},{"doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian scene understanding: Unfolding the dynamics of objects in static images. In: CVPR (2016)","key":"42_CR22","DOI":"10.1109\/CVPR.2016.383"},{"unstructured":"Piloto, L., et al.: Probing physics knowledge using tools from developmental psychology. In: CoRR (2018)","key":"42_CR23"},{"unstructured":"Riochet, R., et al.: IntPhys: a framework and benchmark for visual intuitive physics reasoning. In: arXiv preprint (2018)","key":"42_CR24"},{"unstructured":"Sanchez-Gonzalez, A., et al.: Graph networks as learnable physics engines for inference and control. In: ICML (2018)","key":"42_CR25"},{"unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)","key":"42_CR26"},{"key":"42_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-319-46478-7_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Walker","year":"2016","unstructured":"Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: forecasting from static images using variational autoencoders. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 835\u2013851. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46478-7_51"},{"unstructured":"Watters, N., Tacchetti, A., Weber, T., Pascanu, R., Battaglia, P., Zoran, D.: Visual interaction networks. In: NIPS (2017)","key":"42_CR28"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Lim, J.J., Zhang, H., Tenenbaum, J.B., Freeman, W.T.: Physics 101: learning physical object properties from unlabeled videos. In: BMVC (2016)","key":"42_CR29","DOI":"10.5244\/C.30.39"},{"unstructured":"Wu, J., Lu, E., Kohli, P., Freeman, W., Tenenbaum, J.: Learning to see physics via visual de-animation. In: NIPS (2017)","key":"42_CR30"},{"key":"42_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01258-8_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Ye","year":"2018","unstructured":"Ye, T., Wang, X., Davidson, J., Gupta, A.: Interpretable intuitive physics model. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 89\u2013105. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01258-8_6"},{"unstructured":"Zhang, R., Wu, J., Zhang, C., Freeman, W., Tenenbaum, J.: A comparative evaluation of approximate probabilistic simulation and deep neural networks as accounts of human physical scene understanding. In: Annual Conference of the Cognitive Science Society (2016)","key":"42_CR32"},{"doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J., Ikeuchi, K., Zhu, S.: Scene understanding by reasoning stability and safety. In: IJCV (2015)","key":"42_CR33","DOI":"10.1007\/s11263-014-0795-4"},{"key":"42_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/978-3-319-46493-0_18","volume-title":"Computer Vision \u2013 ECCV 2016","author":"T Zhou","year":"2016","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A.A.: View synthesis by appearance flow. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 286\u2013301. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46493-0_18"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33676-9_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T17:34:46Z","timestamp":1572024886000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-33676-9_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030336752","9783030336769"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33676-9_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dortmund","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/gcpr2019.tu-dortmund.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"91","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}