{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T07:21:42Z","timestamp":1648538502208},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2020,11,1]]},"DOI":"10.1587\/transfun.2020eal2024","type":"journal-article","created":{"date-parts":[[2020,4,29]],"date-time":"2020-04-29T22:11:28Z","timestamp":1588198288000},"page":"1312-1318","source":"Crossref","is-referenced-by-count":0,"title":["OFR-Net: Optical Flow Refinement with a Pyramid Dense Residual Network"],"prefix":"10.1587","volume":"E103.A","author":[{"given":"Liping","family":"ZHANG","sequence":"first","affiliation":[{"name":"Graduate School at Shenzhen, Tsinghua University"}]},{"given":"Zongqing","family":"LU","sequence":"additional","affiliation":[{"name":"Graduate School at Shenzhen, Tsinghua University"}]},{"given":"Qingmin","family":"LIAO","sequence":"additional","affiliation":[{"name":"Graduate School at Shenzhen, Tsinghua University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] Y. Zhang, J. Zheng, C. Zhang, and B. Li, \u201cAn effective motion object detection method using optical flow estimation under a moving camera,\u201d J. Vis. Commun. Image R., vol.55, pp.215-228, 2018. 10.1016\/j.jvcir.2018.06.006","DOI":"10.1016\/j.jvcir.2018.06.006"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] Y. Li, Q. Miao, K. Tian, Y. Fan, X. Xu, Z. Ma, and J. Song, \u201cLarge-scale gesture recognition with a fusion of RGB-D data based on optical flow and the C3D model,\u201d Pattern Recogn. Lett., vol.119, pp.187-194, 2019. 10.1016\/j.patrec.2017.12.003","DOI":"10.1016\/j.patrec.2017.12.003"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Menze and A. Geiger, \u201cObject scene flow for autonomous vehicles,\u201d CVPR, pp.3061-3070, 2015. 10.1109\/cvpr.2015.7298925","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] Z. Tu, W. Xie, D. Zhang, R. Poppe, R.C. Veltkamp, B. Li, and J. Yuan, \u201cA survey of variational and CNN-based optical flow techniques,\u201d Signal Processing: Image Communication, vol.72, pp.9-24, 2019. 10.1016\/j.image.2018.12.002","DOI":"10.1016\/j.image.2018.12.002"},{"key":"5","unstructured":"[5] K. Simonyan and A. Zisserman, \u201cTwo-stream convolutional networks for action recognition in videos,\u201d NIPS, pp.568-576, 2014."},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] A.B. Mabrouk and E. Zagrouba, \u201cSpatio-temporal feature using optical flow based distribution for violence detection,\u201d Pattern Recogn. Lett., vol.92, pp.62-67, 2017. 10.1016\/j.patrec.2017.04.015","DOI":"10.1016\/j.patrec.2017.04.015"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] B.K. Horn and B.G. Schunck, \u201cDetermining optical flow,\u201d Artif. Intell., vol.17, no.1-3, pp.185-203, 1981. 10.1016\/0004-3702(81)90024-2","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"8","unstructured":"[8] D. Eigen, C. Puhrsch, and R. Fergus, \u201cDepth map prediction from a single image using a multi-scale deep network,\u201d NIPS, pp.2366-2374, 2014."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] K. He, G. Gkioxari, P. Doll\u00e1r, and R. Girshick, \u201cMask R-CNN,\u201d ICCV, pp.2961-2969, 2017. 10.1109\/iccv.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert, \u201cHigh accuracy optical flow estimation based on a theory for warping,\u201d ECCV, pp.25-36, 2004. 10.1007\/978-3-540-24673-2_3","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen, \u201cIllumination-invariance optical flow estimation using weighted regularization transform,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.30, no.2, pp.495-508, 2020. 10.1109\/tcsvt.2019.2890861","DOI":"10.1109\/TCSVT.2019.2890861"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] D. Sun, X. Yang, M.Y. Liu, and J. Kautz, \u201cPWC-Net: CNNs for optical flow using pyramid, warping, and cost volume,\u201d CVPR, pp.8934-8943, 2018. 10.1109\/cvpr.2018.00931","DOI":"10.1109\/CVPR.2018.00931"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] D. Sun, S. Roth, and M.J. Black, \u201cSecrets of optical flow estimation and their principles,\u201d CVPR, pp.2432-2439, 2010. 10.1109\/cvpr.2010.5539939","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers, \u201cAn improved algorithm for TV-L1 optical flow,\u201d Statistical and Geometrical Approaches to Visual Motion Analysis, pp.23-45, Springer, 2009. 10.1007\/978-3-642-03061-1_2","DOI":"10.1007\/978-3-642-03061-1_2"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] J. Xiao, H. Cheng, H. Sawhney, C. Rao, and M. Isnardi, \u201cBilateral filtering-based optical flow estimation with occlusion detection,\u201d ECCV, pp.211-224, 2006. 10.1007\/11744023_17","DOI":"10.1007\/11744023_17"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Hazirbas, V. Golkov, P. van der Smagt, D. Cremers, and T. Brox, \u201cFlowNet: Learning optical flow with convolutional networks,\u201d ICCV, 2015. 10.1109\/iccv.2015.316","DOI":"10.1109\/ICCV.2015.316"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid, \u201cEpicFlow: Edge-preserving interpolation of correspondences for optical flow,\u201d CVPR, pp.1164-1172, 2015. 10.1109\/cvpr.2015.7298720","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] P. Doll\u00e1r and C.L. Zitnick, \u201cStructured forests for fast edge detection,\u201d ICCV, pp.1841-1848, 2013. 10.1109\/iccv.2013.231","DOI":"10.1109\/ICCV.2013.231"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Hur and S. Roth, \u201cIterative residual refinement for joint optical flow and occlusion estimation,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.5754-5763, 2019. 10.1109\/cvpr.2019.00590","DOI":"10.1109\/CVPR.2019.00590"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d CVPR, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] G. Huang, Z. Liu, L. Van Der Maaten, and K.Q. Weinberger, \u201cDensely connected convolutional networks,\u201d CVPR, pp.4700-4708, 2017. 10.1109\/cvpr.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] W. Yang, X. Zhang, Y. Tian, W. Wang, J.H. Xue, and Q. Liao, \u201cDeep learning for single image super-resolution: A brief review,\u201d IEEE Trans. Multimedia, vol.21, no.12, pp.3106-3121, 2019. 10.1109\/tmm.2019.2919431","DOI":"10.1109\/TMM.2019.2919431"},{"key":"23","unstructured":"[23] W.S. Lai, J.B. Huang, and M.H. Yang, \u201cSemi-supervised learning for optical flow with generative adversarial networks,\u201d Advances in Neural Information Processing Systems, pp.354-364, 2017."},{"key":"24","unstructured":"[24] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, \u201cGenerative adversarial nets,\u201d Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence, and K.Q. Weinberger, eds., pp.2672-2680, Curran Associates, 2014."},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] D. Fortun, P. Bouthemy, and C. Kervrann, \u201cOptical flow modeling and computation: A survey,\u201d Comput. Vis. Image Und., vol.134, pp.1-21, 2015. 10.1016\/j.cviu.2015.02.008","DOI":"10.1016\/j.cviu.2015.02.008"},{"key":"26","unstructured":"[26] X. Glorot, A. Bordes, and Y. Bengio, \u201cDeep sparse rectifier neural networks,\u201d AISTATS, pp.315-323, 2011."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] N. Mayer, E. Ilg, P. Hausser, P. Fischer, D. Cremers, A. Dosovitskiy, and T. Brox, \u201cA large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation,\u201d CVPR, pp.4040-4048, 2016. 10.1109\/cvpr.2016.438","DOI":"10.1109\/CVPR.2016.438"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] D.J. Butler, J. Wulff, G.B. Stanley, and M.J. Black, \u201cA naturalistic open source movie for optical flow evaluation,\u201d ECCV, pp.611-625, 2012. 10.1007\/978-3-642-33783-3_44","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"29","unstructured":"[29] P. Team et al., \u201cPytorch: Tensors and dynamic neural networks in python with strong GPU acceleration,\u201d 2017."},{"key":"30","unstructured":"[30] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv:1412.6980, 2014."}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/11\/E103.A_2020EAL2024\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,7]],"date-time":"2020-11-07T03:31:40Z","timestamp":1604719900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/11\/E103.A_2020EAL2024\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,1]]},"references-count":30,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2020eal2024","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,1]]}}}