{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:27:12Z","timestamp":1760056032496,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723377"},{"type":"electronic","value":"9783031723384"}],"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\/978-3-031-72338-4_16","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T10:03:01Z","timestamp":1726480981000},"page":"223-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Object Permanence from\u00a0Videos via\u00a0Latent Imaginations"],"prefix":"10.1007","author":[{"given":"Manuel","family":"Traub","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederic","family":"Becker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebsastian","family":"Otte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin V.","family":"Butz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aguiar, A., Baillargeon, R.: 2.5-Month-old reasoning about occlusion events. Infant Behav. Develop. 19, 293 (1996)","DOI":"10.1016\/S0163-6383(96)90347-1"},{"issue":"3","key":"16_CR2","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/0010-0277(85)90008-3","volume":"20","author":"R Baillargeon","year":"1985","unstructured":"Baillargeon, R., Spelke, E.S., Wasserman, S.: Object permanence in five-month-old infants. Cognition 20(3), 191\u2013208 (1985). https:\/\/doi.org\/10.1016\/0010-0277(85)90008-3","journal-title":"Cognition"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1111\/tops.12502","volume":"13","author":"DA Baldwin","year":"2021","unstructured":"Baldwin, D.A., Kosie, J.E.: How does the mind render streaming experience as events? Top. Cogn. Sci. 13, 79\u2013105 (2021). https:\/\/doi.org\/10.1111\/tops.12502","journal-title":"Top. Cogn. Sci."},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J. Image Video Process. 2008, 1\u201310 (2008). https:\/\/doi.org\/10.1155\/2008\/246309","journal-title":"EURASIP J. Image Video Process."},{"key":"16_CR5","doi-asserted-by":"publisher","unstructured":"Burgess, C.P., et al.: MONet: unsupervised scene decomposition and representation (2019). https:\/\/doi.org\/10.48550\/arXiv.1901.11390","DOI":"10.48550\/arXiv.1901.11390"},{"issue":"1","key":"16_CR6","first-page":"1","volume":"4","author":"MV Butz","year":"2008","unstructured":"Butz, M.V.: How and why the brain lays the foundations for a conscious self. Constructivist Found. 4(1), 1\u201342 (2008)","journal-title":"Constructivist Found."},{"issue":"1","key":"16_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s13218-021-00705-x","volume":"35","author":"MV Butz","year":"2021","unstructured":"Butz, M.V.: Towards strong AI. KI - K\u00fcnstliche Intelligenz 35(1), 91\u2013101 (2021). https:\/\/doi.org\/10.1007\/s13218-021-00705-x","journal-title":"KI - K\u00fcnstliche Intelligenz"},{"issue":"1","key":"16_CR8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1111\/tops.12522","volume":"13","author":"MV Butz","year":"2021","unstructured":"Butz, M.V., Achimova, A., Bilkey, D., Knott, A.: Event-predictive cognition: a root for conceptual human thought. Top. Cogn. Sci. 13(1), 10\u201324 (2021). https:\/\/doi.org\/10.1111\/tops.12522","journal-title":"Top. Cogn. Sci."},{"key":"16_CR9","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198739692.001.0001","volume-title":"How the Mind Comes into Being: Introducing Cognitive Science from a Functional and Computational Perspective","author":"MV Butz","year":"2017","unstructured":"Butz, M.V., Kutter, E.F.: How the Mind Comes into Being: Introducing Cognitive Science from a Functional and Computational Perspective. Oxford University Press, Oxford (2017)"},{"issue":"3","key":"16_CR10","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1017\/S0140525X12000477","volume":"36","author":"A Clark","year":"2013","unstructured":"Clark, A.: Whatever next? Predictive brains, situated agents, and the future of cognitive science. Behav. Brain Sci. 36(3), 181\u2013204 (2013). https:\/\/doi.org\/10.1017\/S0140525X12000477","journal-title":"Behav. Brain Sci."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Den\u00a0Ouden, H., Kok, P., De\u00a0Lange, F.: How prediction errors shape perception, attention, and motivation. Front. Psychol. 3 (2012)","DOI":"10.3389\/fpsyg.2012.00548"},{"key":"16_CR12","first-page":"9112","volume":"34","author":"D Ding","year":"2021","unstructured":"Ding, D., Hill, F., Santoro, A., Reynolds, M., Botvinick, M.: Attention over learned object embeddings enables complex visual reasoning. Adv. Neural Inf. Process. Syst. 34, 9112\u20139124 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR13","unstructured":"Elsayed, G.F., Mahendran, A., van Steenkiste, S., Greff, K., Mozer, M.C., Kipf, T.: SAVi++: towards end-to-end object-centric learning from real-world videos. arXiv preprint arXiv:2206.07764 [cs] (2022)"},{"key":"16_CR14","unstructured":"Girdhar, R., Ramanan, D.: CATER: a diagnostic dataset for compositional actions and temporal reasoning. arXiv preprint arXiv:1910.04744 (2019)"},{"key":"16_CR15","unstructured":"Greff, K., Van\u00a0Steenkiste, S., Schmidhuber, J.: On the binding problem in artificial neural networks. arXiv preprint arXiv:2012.05208 (2020)"},{"key":"16_CR16","unstructured":"Gumbsch, C., Butz, M.V., Martius, G.: Sparsely changing latent states for prediction and planning in partially observable domains. arXiv preprint arXiv:2110.15949 (2022)"},{"key":"16_CR17","unstructured":"Gumbsch, C., Sajid, N., Martius, G., Butz, M.V.: Learning hierarchical world models with adaptive temporal abstractions from discrete latent dynamics. In: Sixteenth European Workshop on Reinforcement Learning (2023)"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Ha, D., Schmidhuber, J.: World Models. arXiv preprint arXiv:1803.10122 [cs, stat] (2018) https:\/\/doi.org\/10.5281\/zenodo.1207631","DOI":"10.5281\/zenodo.1207631"},{"key":"16_CR19","unstructured":"Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 (2020)"},{"key":"16_CR20","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: Proceedings of the 36th International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019). ISSN: 2640-3498"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"16_CR22","unstructured":"Jiang, J., Janghorbani, S., Melo, G.D., Ahn, S.: Scalor: generative world models with scalable object representations. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=SJxrKgStDH"},{"issue":"1","key":"16_CR23","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35\u201345 (1960). https:\/\/doi.org\/10.1115\/1.3662552","journal-title":"J. Basic Eng."},{"key":"16_CR24","unstructured":"Kipf, T., et al.: Conditional object-centric learning from video. arXiv preprint arXiv:2111.12594 [cs, stat] (2022)"},{"key":"16_CR25","unstructured":"Kossen, J., Stelzner, K., Hussing, M., Voelcker, C., Kersting, K.: Structured object-aware physics prediction for video modeling and planning. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=B1e-kxSKDH"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Kuperberg, G.R.: Tea with milk? a hierarchical generative framework of sequential event comprehension. Topics Cognit. Sci. 13, 256\u2013298 (2021). https:\/\/doi.org\/10.1111\/tops.12518","DOI":"10.1111\/tops.12518"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building Machines That Learn and Think Like People. arXiv preprint arXiv:1604.00289 (2016)","DOI":"10.1017\/S0140525X16001837"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Lin, Y., Stavans, M., Baillargeon, R.: Infants\u2019 physical reasoning and the cognitive architecture that supports it. In: Cambridge Handbook of Cognitive Development, pp. 168\u2013194 (2022)","DOI":"10.1017\/9781108399838.012"},{"key":"16_CR29","unstructured":"Lin, Z., Wu, Y.F., Peri, S., Fu, B., Jiang, J., Ahn, S.: Improving generative imagination in object-centric world models. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 6140\u20136149. PMLR (2020)"},{"key":"16_CR30","unstructured":"Liu, L., et al.: On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265 (2021)"},{"issue":"4","key":"16_CR31","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1037\/0033-295x.104.4.686","volume":"104","author":"Y Munakata","year":"1997","unstructured":"Munakata, Y., Mcclelland, J., Johnson, M., Siegler, R.: Rethinking infant knowledge: toward an adaptive process account of successes and failures in object permanence tasks. Psychol. Rev. 104(4), 686\u2013713 (1997). https:\/\/doi.org\/10.1037\/0033-295x.104.4.686","journal-title":"Psychol. Rev."},{"issue":"9","key":"16_CR32","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1038\/s41562-022-01394-8","volume":"6","author":"LS Piloto","year":"2022","unstructured":"Piloto, L.S., Weinstein, A., Battaglia, P., Botvinick, M.: Intuitive physics learning in a deep-learning model inspired by developmental psychology. Nat. Hum. Behav. 6(9), 1257\u20131267 (2022). https:\/\/doi.org\/10.1038\/s41562-022-01394-8","journal-title":"Nat. Hum. Behav."},{"key":"16_CR33","unstructured":"Seitzer, M., et al.: Bridging the gap to real-world object-centric learning. arXiv preprint arXiv:2209.14860 [cs] (2023)"},{"key":"16_CR34","unstructured":"Smith, K.A., et al.: Modeling expectation violation in intuitive physics with coarse probabilistic object representations. In: Neural Information Processing Systems (NIPS) (2019)"},{"issue":"4","key":"16_CR35","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1037\/0033-295x.99.4.605","volume":"99","author":"ES Spelke","year":"1992","unstructured":"Spelke, E.S., Breinlinger, K., Macomber, J., Jacobson, K.: Origins of knowledge. Psychol. Rev. 99(4), 605\u2013632 (1992). https:\/\/doi.org\/10.1037\/0033-295x.99.4.605","journal-title":"Psychol. Rev."},{"issue":"1","key":"16_CR36","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/j.1467-7687.2007.00569.x","volume":"10","author":"ES Spelke","year":"2007","unstructured":"Spelke, E.S., Kinzler, K.D.: Core knowledge. Dev. Sci. 10(1), 89\u201396 (2007). https:\/\/doi.org\/10.1111\/j.1467-7687.2007.00569.x","journal-title":"Dev. Sci."},{"issue":"9","key":"16_CR37","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.tics.2009.06.003","volume":"13","author":"C Summerfield","year":"2009","unstructured":"Summerfield, C., Egner, T.: Expectation (and attention) in visual cognition. Trends Cogn. Sci. 13(9), 403\u2013409 (2009)","journal-title":"Trends Cogn. Sci."},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Traub, M., Becker, F., Sauter, A., Otte, S., Butz, M.V.: Loci-segmented: improving scene segmentation learning. arXiv preprint arXiv:2310.10410 [cs] version: 1 (2023)","DOI":"10.1007\/978-3-031-72338-4_4"},{"key":"16_CR39","unstructured":"Traub, M., Otte, S., Menge, T., Karlbauer, M., Thuemmel, J., Butz, M.V.: Learning what and where: disentangling location and identity tracking without supervision. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=NeDc-Ak-H_"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"4","key":"16_CR41","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., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR42","unstructured":"Weihs, L., et al.: Benchmarking progress to infant-level physical reasoning in AI. Trans. Mach. Learn. Res. (2022). https:\/\/openreview.net\/forum?id=9NjqD9i48M"},{"key":"16_CR43","unstructured":"Wu, P., Escontrela, A., Hafner, D., Abbeel, P., Goldberg, K.: Daydreamer: world models for physical robot learning. In: Liu, K., Kulic, D., Ichnowski, J. (eds.) Proceedings of The 6th Conference on Robot Learning. Proceedings of Machine Learning Research, vol.\u00a0205, pp. 2226\u20132240. PMLR (2023)"},{"key":"16_CR44","unstructured":"Yi, K., et al.: CLEVRER: CoLlision events for video REpresentation and reasoning. arXiv preprint arXiv:1910.01442 (2020)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, J., Chen, T., Li, B., Xue, X.: Compositional scene representation learning via reconstruction: a survey. arXiv preprint arXiv:2202.07135 (2023)","DOI":"10.1109\/TPAMI.2023.3286184"},{"issue":"2","key":"16_CR46","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1037\/0033-2909.133.2.273","volume":"133","author":"JM Zacks","year":"2007","unstructured":"Zacks, J.M., Speer, N.K., Swallow, K.M., Braver, T.S., Reynolds, J.R.: Event perception: a mind-brain perspective. Psychol. Bull. 133(2), 273\u2013293 (2007). https:\/\/doi.org\/10.1037\/0033-2909.133.2.273","journal-title":"Psychol. Bull."},{"key":"16_CR47","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72338-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T07:50:11Z","timestamp":1759996211000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72338-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723377","9783031723384"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72338-4_16","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":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}