{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:41:34Z","timestamp":1743118894222,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031064326"},{"type":"electronic","value":"9783031064333"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06433-3_23","type":"book-chapter","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T18:03:24Z","timestamp":1652551404000},"page":"265-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cycle Consistency Based Method for\u00a0Learning Disentangled Representation for\u00a0Stochastic Video Prediction"],"prefix":"10.1007","author":[{"given":"Ujjwal","family":"Tiwari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. Aditya","family":"Sreekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anoop","family":"Namboodiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,15]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Bubi\u0107, A., Cramon, D., Schubotz, R.: Prediction, cognition and the brain. Front. Hum. Neurosci. 4, 25 (2010)","DOI":"10.3389\/fnhum.2010.00025"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_45","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Soran, B., Farhadi, A., Shapiro, L.: Generating notifications for missing actions: don\u2019t forget to turn the lights off! In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4669\u20134677 (2015)","DOI":"10.1109\/ICCV.2015.530"},{"key":"23_CR4","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. arXiv:1511.05440 (2015)"},{"key":"23_CR5","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMS. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"23_CR6","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2016)"},{"key":"23_CR7","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Advances in Neural Information Processing Systems, pp. 64\u201372 (2016)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Paxton, C., Barnoy, Y., Katyal, K., Arora, R., Hager, G.D.: Visual robot task planning. arXiv:1804.00062 (2018)","DOI":"10.1109\/ICRA.2019.8793736"},{"key":"23_CR9","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. arXiv:1706.08033 (2017)"},{"key":"23_CR10","unstructured":"Hsieh, J.-T., Liu, B., Huang, D.-A., Fei-Fei, L.F., Niebles, J.C.: Learning to decompose and disentangle representations for video prediction. In: Advances in Neural Information Processing Systems, pp. 517\u2013526 (2018)"},{"key":"23_CR11","unstructured":"Denton, E.L., et al.: Unsupervised learning of disentangled representations from video. In: Advances in Neural Information Processing Systems, pp. 4414\u20134423 (2017)"},{"key":"23_CR12","unstructured":"Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction. arXiv:1804.01523 (2018)"},{"key":"23_CR13","unstructured":"Denton, E., Fergus, R.: Stochastic video generation with a learned prior. arXiv:1802.07687 (2018)"},{"key":"23_CR14","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R.H., Levine, S.: Stochastic variational video prediction. arXiv:1710.11252 (2017)"},{"key":"23_CR15","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv:1412.6604 (2014)"},{"key":"23_CR16","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Advances in Neural Information Processing Systems, pp. 613\u2013621 (2016)"},{"key":"23_CR17","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv:1605.08104 (2016)"},{"key":"23_CR18","unstructured":"Chiappa, S., Racaniere, S., Wierstra, D., Mohamed, S.: Recurrent environment simulators. arXiv:1704.02254 (2017)"},{"key":"23_CR19","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: Advances in Neural Information Processing Systems, pp. 2863\u20132871 (2015)"},{"key":"23_CR20","unstructured":"Jia, X., De Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: Advances in Neural Information Processing Systems, pp. 667\u2013675 (2016)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Liu, W., Sharma, A., Camps, O., Sznaier, M.: Dyan: a dynamical atoms-based network for video prediction. In: European Conference on Computer Vision, pp. 175\u2013191. Springer (2018)","DOI":"10.1007\/978-3-030-01258-8_11"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Dense optical flow prediction from a static image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2443\u20132451 (2015)","DOI":"10.1109\/ICCV.2015.281"},{"key":"23_CR23","unstructured":"Henaff, M., Zhao, J., LeCun, Y.: Prediction under uncertainty with error-encoding networks. arXiv:1711.04994 (2017)"},{"key":"23_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 (2013)"},{"key":"23_CR25","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"23_CR26","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Berg, T.L.: Learning temporal transformations from time-lapse videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 262\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_16","DOI":"10.1007\/978-3-319-46484-8_16"},{"key":"23_CR27","unstructured":"Kalchbrenner, N., et al.: Video pixel networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR.org, pp. 1771\u20131779 (2017)"},{"key":"23_CR28","unstructured":"Salimans, T., Karpathy, A., Chen, X., Kingma, D.P.: PixelCNN++: improving the pixelCNN with discretized logistic mixture likelihood and other modifications. arXiv:1701.05517 (2017)"},{"key":"23_CR29","unstructured":"Reed, S., et al.: Parallel multiscale autoregressive density estimation. arXiv:1703.03664 (2017)"},{"key":"23_CR30","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434 (2015)"},{"key":"23_CR31","unstructured":"Ebert, F., Finn. C., Lee, A.X., Levine, S.: Self-supervised visual planning with temporal skip connections. arXiv:1710.05268 (2017)"},{"issue":"4","key":"23_CR32","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06433-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:11:59Z","timestamp":1709813519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06433-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031064326","9783031064333"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06433-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lecce","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"23 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2021.org\/","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":"Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"168","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":"55% - 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":"4","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)"}}]}}