{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:51:55Z","timestamp":1761126715273,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319464923"},{"type":"electronic","value":"9783319464930"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46493-0_17","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:59:53Z","timestamp":1474037993000},"page":"269-285","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["\u201cWhat Happens If...\u201d Learning to Predict the Effect of Forces in Images"],"prefix":"10.1007","author":[{"given":"Roozbeh","family":"Mottaghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Rastegari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","first-page":"18327","DOI":"10.1073\/pnas.1306572110","volume":"110","author":"P Battaglia","year":"2013","unstructured":"Battaglia, P., Hamrick, J., Tenenbaum, J.B.: Simulation as an engine of physical scene understanding. PNAS 110, 18327\u201318332 (2013)","journal-title":"PNAS"},{"key":"17_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/3-540-47969-4_37","volume-title":"Computer Vision \u2014 ECCV 2002","author":"KS Bhat","year":"2002","unstructured":"Bhat, K.S., Seitz, S.M., Popovi\u0107, J., Khosla, P.K.: Computing the physical parameters of rigid-body motion from video. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 551\u2013565. Springer, Heidelberg (2002). doi:\n                      10.1007\/3-540-47969-4_37"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Brubaker, M.A., Sigal, L., Fleet, D.J.: Estimating contact dynamics. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459407"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y.W., Pantofaru, C., Savarese, S.: Understanding indoor scenes using 3d geometric phrases. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.12"},{"key":"17_CR5","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: NIPS (2014)"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88, 303\u2013338 (2010)","journal-title":"IJCV"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Zitnick, C.: Predicting object dynamics in scenes. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.260"},{"key":"17_CR8","unstructured":"Fragkiadaki, K., Agrawal, P., Levine, S., Malik, J.: Learning predictive visual models of physics for playing billiards. In: ICLR (2016)"},{"key":"17_CR9","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). doi:\n                      10.1007\/978-3-642-15561-1_35"},{"key":"17_CR10","unstructured":"Hamrick, J., Battaglia, P., Tenenbaum., J.B.: Internal physics models guide probabilistic judgments about object dynamics. In: Annual Meeting of the Cognitive Science Society (2011)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR12","unstructured":"Heitz, G., Gould, S., Saxena, A., Koller, D.: Cascaded classification models: Combining models for holistic scene understanding. In: NIPS (2008)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Jia, Z., Gallagher, A., Saxena, A., Chen, T.: 3d-based reasoning with blocks, support, and stability. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.8"},{"key":"17_CR14","first-page":"1021","volume":"31","author":"Y Jiang","year":"2012","unstructured":"Jiang, Y., Lim, M., Zheng, C., Saxena, A.: Learning to place new objects in a scene. IJRR 31, 1021\u20131043 (2012)","journal-title":"IJRR"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"17_CR16","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). doi:\n                      10.1007\/978-3-642-33765-9_15"},{"key":"17_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"17_CR18","unstructured":"Le, Q.V., Jaitly, N., Hinton, G.E.: A simple way to initialize recurrent networks of rectified linear units. In: ArXiv (2015)"},{"key":"17_CR19","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. In: ArXiv (2015)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Li, L.J., Socher, R., Fei-Fei, L.: Towards total scene understanding: Classification, annotation and segmentation in an automatic framework. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206718"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Lin, D., Fidler, S., Urtasun, R.: Holistic scene understanding for 3d object detection with rgbd cameras. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.179"},{"key":"17_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10602-1_48"},{"key":"17_CR23","unstructured":"Michalski, V., Memisevic, R., Konda, K.: Modeling deep temporal dependencies with recurrent grammar cells. In: NIPS (2014)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian image understanding: Unfolding the dynamics of objects in static images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.383"},{"key":"17_CR25","unstructured":"Murphy, K., Torralba, A., Freeman, W.T.: Using the forest to see the trees: a graphical model relating features, objects, and scenes. In: NIPS (2003)"},{"key":"17_CR26","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.P.: Action-conditional video prediction using deep networks in atari games. In: NIPS (2015)"},{"key":"17_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-319-10578-9_12","volume-title":"Computer Vision \u2013 ECCV 2014","author":"SL Pintea","year":"2014","unstructured":"Pintea, S.L., Gemert, J.C., Smeulders, A.W.M.: D\u00e9j\u00e0 Vu: motion prediction in static. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 172\u2013187. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10578-9_12"},{"key":"17_CR28","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. In: ArXiv (2014)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Keskin, C., Kohli, P., Izadi, S.: Computationally bounded retrieval. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298757"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Salzmann, M., Urtasun, R.: Physically-based motion models for 3d tracking: a convex formulation. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126480"},{"key":"17_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33715-4_54"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun rgb-d: A rgb-d scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"17_CR33","unstructured":"Sutskever, I., Hinton, G.E., Taylor, G.W.: The recurrent temporal restricted boltzmann machine. In: NIPS (2008)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: A neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Vondrak, M., Sigal, L., Jenkins, O.C.: Physical simulation for probabilistic motion tracking. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587580"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: Unsupervised visual prediction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Dense optical flow prediction from a static image. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.281"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Fouhey, D.F., Gupta, A.: Designing deep networks for surface normal estimation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298652"},{"key":"17_CR39","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, W.T., Tenenbaum, J.B.: Galileo: Perceiving physical object properties by integrating a physics engine with deep learning. In: NIPS (2015)"},{"key":"17_CR40","unstructured":"Yao, J., Fidler, S., Urtasun, R.: Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation. In: CVPR (2012)"},{"key":"17_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-642-15552-9_51","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Yuen","year":"2010","unstructured":"Yuen, J., Torralba, A.: A data-driven approach for event prediction. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 707\u2013720. Springer, Heidelberg (2010). doi:\n                      10.1007\/978-3-642-15552-9_51"},{"key":"17_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-319-10599-4_43","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Zhang","year":"2014","unstructured":"Zhang, Y., Song, S., Tan, P., Xiao, J.: PanoContext: a whole-room 3D context model for panoramic scene understanding. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 668\u2013686. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10599-4_43"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J.C., Ikeuchi, K., Zhu, S.C.: Beyond point clouds: Scene understanding by reasoning geometry and physics. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.402"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J.C., Ikeuchi, K., Zhu, S.C.: Detecting potential falling objects by inferring human action and natural disturbance. In: ICRA (2014)","DOI":"10.1109\/ICRA.2014.6907351"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46493-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:18:58Z","timestamp":1602292738000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46493-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464923","9783319464930"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46493-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}