{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:41:09Z","timestamp":1780501269622,"version":"3.54.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012458","type":"print"},{"value":"9783030012465","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01246-5_43","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T20:14:56Z","timestamp":1538770496000},"page":"724-739","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking"],"prefix":"10.1007","author":[{"given":"Oliver","family":"Groth","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian B.","family":"Fuchs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ingmar","family":"Posner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Vedaldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"45","key":"43_CR1","doi-asserted-by":"publisher","first-page":"18327","DOI":"10.1073\/pnas.1306572110","volume":"110","author":"PW Battaglia","year":"2013","unstructured":"Battaglia, P.W., Hamrick, J.B., Tenenbaum, J.B.: Simulation as an engine of physical scene understanding. Proc. Natl. Acad. Sci. 110(45), 18327\u201318332 (2013). https:\/\/doi.org\/10.1073\/pnas.1306572110. http:\/\/www.pnas.org\/cgi\/doi\/10.1073\/pnas.1306572110","journal-title":"Proc. Natl. Acad. Sci."},{"key":"43_CR2","unstructured":"Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Advances in Neural Information Processing Systems, pp. 4502\u20134510 (2016)"},{"key":"43_CR3","unstructured":"Chang, M.B., Ullman, T., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics, pp. 1\u201315 (2016). http:\/\/arxiv.org\/abs\/1612.00341"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"43_CR5","unstructured":"Fragkiadaki, K., Agrawal, P., Levine, S., Malik, J.: Learning visual predictive models of physics for playing billiards, pp. 1\u201312 (2015). http:\/\/arxiv.org\/abs\/1511.07404"},{"key":"43_CR6","doi-asserted-by":"publisher","unstructured":"Furrer, F., et al.: Autonomous robotic stone stacking with online next best object target pose planning. In: Proceedings - IEEE International Conference on Robotics and Automation, pp. 2350\u20132356 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989272","DOI":"10.1109\/ICRA.2017.7989272"},{"key":"43_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/978-3-642-15561-1_35","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Gupta","year":"2010","unstructured":"Gupta, A., Efros, A.A., Hebert, M.: Blocks world revisited: image understanding using qualitative geometry and mechanics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 482\u2013496. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_35"},{"key":"43_CR8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.cognition.2016.08.012","volume":"157","author":"Jessica B. Hamrick","year":"2016","unstructured":"Hamrick, J.B., Battaglia, P.W., Griffiths, T.L., Tenenbaum, J.B.: Inferring mass in complex scenes by mental simulation. Cognition 157 (2016). https:\/\/doi.org\/10.1016\/j.cognition.2016.08.012","journal-title":"Cognition"},{"key":"43_CR9","unstructured":"Hinton, G., Srivastava, N., Swersky, K.: Coursera, neural networks for machine learning, lecture 6e (2014). http:\/\/www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf"},{"issue":"5","key":"43_CR10","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/TPAMI.2014.2359435","volume":"37","author":"Z Jia","year":"2015","unstructured":"Jia, Z., Gallagher, A.C., Saxena, A., Chen, T.: 3D reasoning from blocks to stability. IEEE Trans. Pattern Anal. Mach. Intell. 37(5), 905\u2013918 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2014.2359435","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"43_CR11","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.cviu.2010.08.002","volume":"115","author":"H Kjellstr\u00f6m","year":"2011","unstructured":"Kjellstr\u00f6m, H., Romero, J., Kragi\u0107, D.: Visual object-action recognition: inferring object affordances from human demonstration. Comput. Vis. Image Underst. 115(1), 81\u201390 (2011). https:\/\/doi.org\/10.1016\/j.cviu.2010.08.002","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"43_CR12","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPAMI.2015.2430335","volume":"38","author":"HS Koppula","year":"2016","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 14\u201329 (2016). https:\/\/doi.org\/10.1109\/TPAMI.2015.2430335","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"43_CR13","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.protcy.2014.09.007","volume":"15","author":"Johannes G\u00fcnther","year":"2014","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1\u20139 (2012). https:\/\/doi.org\/10.1016\/j.protcy.2014.09.007","journal-title":"Procedia Technology"},{"issue":"10","key":"43_CR14","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1016\/j.tics.2017.06.002","volume":"21","author":"JR Kubricht","year":"2017","unstructured":"Kubricht, J.R., Holyoak, K.J., Lu, H.: Intuitive physics: current research and controversies. Trends Cogn. Sci. 21(10), 749\u2013759 (2017). https:\/\/doi.org\/10.1016\/j.tics.2017.06.002","journal-title":"Trends Cogn. Sci."},{"key":"43_CR15","unstructured":"Lerer, A., Gross, S., Fergus, R.: Learning physical intuition of block towers by example. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML 2016, pp. 430\u2013438. JMLR.org (2016). http:\/\/dl.acm.org\/citation.cfm?id=3045390.3045437"},{"key":"43_CR16","unstructured":"Li, W., Azimi, S., Leonardis, A., Fritz, M.: To fall or not to fall: a visual approach to physical stability prediction. arXiv preprint arXiv:1604.00066 (2016)"},{"key":"43_CR17","doi-asserted-by":"publisher","unstructured":"Li, W., Leonardis, A., Fritz, M.: Visual stability prediction for robotic manipulation. In: Proceedings - IEEE International Conference on Robotics and Automation, pp. 2606\u20132613 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989304","DOI":"10.1109\/ICRA.2017.7989304"},{"key":"43_CR18","doi-asserted-by":"publisher","unstructured":"Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian image understanding: unfolding the dynamics of objects in static images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.383","DOI":"10.1109\/CVPR.2016.383"},{"key":"43_CR19","doi-asserted-by":"publisher","unstructured":"Ornan, O., Degani, A.: Toward autonomous disassembling of randomly piled objects with minimal perturbation. IEEE International Conference on Intelligent Robots and Systems, pp. 4983\u20134989 (2013). https:\/\/doi.org\/10.1109\/IROS.2013.6697076","DOI":"10.1109\/IROS.2013.6697076"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"43_CR21","doi-asserted-by":"publisher","unstructured":"Wang, J., Rogers, P., Parker, L., Brooks, D., Stilman, M.: Robot Jenga: autonomous and strategic block extraction. In: 2009 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, pp. 5248\u20135253 (2009). https:\/\/doi.org\/10.1109\/IROS.2009.5354303","DOI":"10.1109\/IROS.2009.5354303"},{"issue":"2","key":"43_CR22","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1088\/0264-9381\/12\/2\/003","volume":"12","author":"P Demkin","year":"1995","unstructured":"Wieber, P.B.: On the stability of walking systems. In: Proceedings of the Third IARP International Workshop on Humanoid and Human Friendly Robotics, pp. 1\u20137 (2002). https:\/\/doi.org\/10.1088\/0264-9381\/12\/2\/003","journal-title":"Classical and Quantum Gravity"},{"key":"43_CR23","unstructured":"Wu, J., Lu, E., Kohli, P., Freeman, W.T., Tenenbaum, J.B.: Learning to see physics via visual de-animation. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"43_CR24","unstructured":"Wu, J., Yildirim, I., Lim, J., Freeman, W., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Advances in Neural Information Processing Systems 28 (NIPS 2015), pp. 1\u20139 (2015)"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Reinforcement and imitation learning for diverse visuomotor skills. CoRR abs\/1802.09564 (2018). http:\/\/arxiv.org\/abs\/1802.09564","DOI":"10.15607\/RSS.2018.XIV.009"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01246-5_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:25:45Z","timestamp":1664929545000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01246-5_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012458","9783030012465"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01246-5_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}