{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:42:57Z","timestamp":1776753777326,"version":"3.51.2"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319541921","type":"print"},{"value":"9783319541938","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-54193-8_26","type":"book-chapter","created":{"date-parts":[[2017,3,10]],"date-time":"2017-03-10T04:24:07Z","timestamp":1489119847000},"page":"412-428","source":"Crossref","is-referenced-by-count":19,"title":["Learning to Extract Motion from Videos in Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Damien","family":"Teney","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martial","family":"Hebert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,11]]},"reference":[{"key":"26_CR1","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. CoRR NIPS Spotlight Session abs\/1406.2199 (2014)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, X., Jiang, Y.G., Ye, H., Xue, X.: Modeling spatial-temporal clues in a hybrid deep learning framework for video classification. In: ACM Multimedia Conference (2015)","DOI":"10.1145\/2733373.2806222"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Ye, H., Wu, Z., Zhao, R.W., Wang, X., Jiang, Y.G., Xue, X.: Evaluating two-stream CNN for video classification. In: ACM on International Conference on Multimedia Retrieval (ICMR) (2015)","DOI":"10.1145\/2671188.2749406"},{"key":"26_CR4","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3D: generic features for video analysis. CoRR abs\/1412.0767 (2014)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Teney, D., Brown, M.: Segmentation of dynamic scenes with distributions of spatiotemporally oriented energies. In: British Machine Vision Conference (BMVC) (2014)","DOI":"10.5244\/C.28.37"},{"key":"26_CR6","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1109\/TPAMI.2011.221","volume":"34","author":"KG Derpanis","year":"2012","unstructured":"Derpanis, K.G., Wildes, R.P.: Spacetime texture representation and recognition based on a spatiotemporal orientation analysis. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 34, 1193\u20131205 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.175"},{"key":"26_CR8","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TPAMI.2010.143","volume":"33","author":"T Brox","year":"2011","unstructured":"Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 33, 500\u2013513 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Fischer, P., Dosovitskiy, A., Ilg, E., H\u00e4usser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., Brox, T.: Flownet: learning optical flow with convolutional networks. CoRR abs\/1504.06852 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"26_CR12","unstructured":"Konda, K.R., Memisevic, R.: Unsupervised learning of depth and motion. CoRR abs\/1312.3429 (2013)"},{"key":"26_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-642-15567-3_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"GW Taylor","year":"2010","unstructured":"Taylor, G.W., Fergus, R., LeCun, Y., Bregler, C.: Convolutional learning of spatio-temporal features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 140\u2013153. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15567-3_11"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Olshausen, B.: Learning sparse, overcomplete representations of time-varying natural images. In: ICIP, vol. 1, pp. I-41 (2003)","DOI":"10.1109\/ICIP.2003.1246893"},{"key":"26_CR15","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"11","author":"BKP Horn","year":"1981","unstructured":"Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 11, 185\u2013203 (1981)","journal-title":"Artif. Intell."},{"key":"26_CR16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2015.02.008","volume":"393","author":"D Fortun","year":"2015","unstructured":"Fortun, D., Bouthemy, P., Kervrann, C.: Optical flow modeling and computation: a survey. Comput. Vis. Image Underst. (CVIU) 393, 1\u201321 (2015)","journal-title":"Comput. Vis. Image Underst. (CVIU)"},{"key":"26_CR17","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1364\/JOSAA.4.001455","volume":"4","author":"DJ Heeger","year":"1987","unstructured":"Heeger, D.J.: Model for the extraction of image flow. J. Opt. Soc. Am. A 4, 1455\u20131471 (1987)","journal-title":"J. Opt. Soc. Am. A"},{"key":"26_CR18","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1364\/JOSAA.2.000284","volume":"2","author":"EH Adelson","year":"1985","unstructured":"Adelson, E.H., Bergen, J.: Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A 2, 284\u2013299 (1985)","journal-title":"J. Opt. Soc. Am. A"},{"key":"26_CR19","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1038\/nn1786","volume":"9","author":"NC Rust","year":"2006","unstructured":"Rust, N.C., Mante, V., Simoncelli, E.P., Movshon, J.A.: How MT cells analyze the motion of visual patterns. Nature Neurosci. 9, 1421\u20131431 (2006)","journal-title":"Nature Neurosci."},{"key":"26_CR20","first-page":"342","volume":"39","author":"F Solari","year":"2015","unstructured":"Solari, F., Chessa, M., Medathati, N., Kornprobst, P.: What can we expect from a V1-MT feedforward architecture for optical flow estimation? Signal Process.: Image Commun. 39, 342\u2013354 (2015)","journal-title":"Signal Process.: Image Commun."},{"key":"26_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/978-3-642-13772-3_27","volume-title":"Image Analysis and Recognition","author":"V Ulman","year":"2010","unstructured":"Ulman, V.: Improving accuracy of optical flow of heeger\u2019s original method on biomedical images. In: Campilho, A., Kamel, M. (eds.) ICIAR 2010. LNCS, vol. 6111, pp. 263\u2013273. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-13772-3_27"},{"key":"26_CR22","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TPAMI.2010.64","volume":"32","author":"KG Derpanis","year":"2010","unstructured":"Derpanis, K.G., Wildes, R.P.: The structure of multiplicative motions in natural imagery. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 32, 1310\u20131316 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (PAMI)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Teney, D., Brown, M., Kit, D., Hall, P.: Learning similarity metrics for dynamic scene segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298820"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Fasel, B., Gatica-Perez, D.: Rotation-invariant neoperceptron. In: International Conference on Pattern Recognition (ICPR) (2006)","DOI":"10.1109\/ICPR.2006.1020"},{"key":"26_CR25","unstructured":"Le, Q.V., Ngiam, J., Chen, Z., Chia, D., Koh, P.W., Ng, A.Y.: Tiled convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2010)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Dieleman, S., Willett, K.W., Dambre, J.: Rotation-invariant convolutional neural networks for galaxy morphology prediction. CoRR abs\/1503.07077 (2015)","DOI":"10.1093\/mnras\/stv632"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Laptev, D., Buhmann, J.M.: Transformation-invariant convolutional jungles. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298923"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Rowley, H., Baluja, S., Kanade, T.: Rotation invariant neural network-based face detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1998)","DOI":"10.21236\/ADA341629"},{"key":"26_CR29","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"26_CR30","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations equivariant to ego-motion. CoRR abs\/1505.02206 (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"26_CR32","unstructured":"Niyogi, S.A.: Fitting models to distributed representations of vision. In: International Joint Conference on Artificial Intelligence, San Francisco, CA, USA, pp. 3\u20139. Morgan Kaufmann Publishers Inc. (1995)"},{"key":"26_CR33","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/BF00056772","volume":"5","author":"D Fleet","year":"1990","unstructured":"Fleet, D., Jepson, A.: Computation of component image velocity from local phase information. Int. J. Comput. Vis. (IJCV) 5, 77\u2013104 (1990)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"26_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-642-35289-8_3","volume-title":"Neural Networks: Tricks of the Trade","author":"YA LeCun","year":"2012","unstructured":"LeCun, Y.A., Bottou, L., Orr, G.B., M\u00fcller, K.-R.: Efficient BackProp. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 9\u201348. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-35289-8_3"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Memin, E., Perez, P.: A multigrid approach for hierarchical motion estimation. In: IEEE Intenational Conference on Computer Vision (ICCV) (1998)","DOI":"10.1109\/ICCV.1998.710828"},{"key":"26_CR36","unstructured":"Anonymous: Website to be provided upon acceptance of the paper. http:\/\/damienteney.info\/cnnFlow.htm"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. In: International Conference on Computer Vision (ICCV) (2007)","DOI":"10.1109\/ICCV.2007.4408903"},{"key":"26_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-642-33783-3_44","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DJ Butler","year":"2012","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-33783-3_44"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432\u20132439. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"26_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004). doi: 10.1007\/978-3-540-24673-2_3"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54193-8_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T17:33:50Z","timestamp":1658770430000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-54193-8_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319541921","9783319541938"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54193-8_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}