{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:13:27Z","timestamp":1779930807506,"version":"3.53.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Rapid-Rich Object Search (ROSE) Lab"},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Infocomm Media Development Authority, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tmm.2018.2815784","type":"journal-article","created":{"date-parts":[[2018,3,15]],"date-time":"2018-03-15T20:42:42Z","timestamp":1521146562000},"page":"2814-2823","source":"Crossref","is-referenced-by-count":50,"title":["Recurrent Spatial Pyramid CNN for Optical Flow Estimation"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3321-6759","authenticated-orcid":false,"given":"Ping","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1816-1457","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yap-Peng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Optical flow estimation with uncertainties through dynamic MRFs","author":"glocker","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70844"},{"key":"ref33","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref32","first-page":"1","article-title":"Guided image filtering","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","first-page":"839","article-title":"Bilateral filtering for gray and color images","author":"tomasi","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref30","first-page":"1164","article-title":"EpicFlow: Edge-preserving interpolation\n of correspondences for optical flow","author":"revaud","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref37","first-page":"4706","article-title":"Full flow: Optical flow estimation by global optimization over regular grids","author":"chen","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref36","first-page":"1663","article-title":"Structure-and motion-adaptive\n regularization for high accuracy optic flow","author":"wedel","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2011.236","article-title":"Motion detail\n preserving optical flow estimation","volume":"34","author":"xu","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref34","first-page":"152","article-title":"Illumination-robust variational optical flow with photometric invariants","author":"mileva","year":"0","journal-title":"Proc Pattern Recognition Symp"},{"key":"ref28","article-title":"Guided optical flow learning","author":"zhu","year":"2017"},{"key":"ref27","first-page":"2462","article-title":"FlowNet 2.0: Evolution of optical flow estimation with deep\n networks","author":"ilg","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref29","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proc COMPSTAT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2674622"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.143"},{"key":"ref22","first-page":"5704","article-title":"Efficient coarse-to-fine patch\n match for large displacement optical flow","author":"hu","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0908-3"},{"key":"ref24","first-page":"4161","article-title":"Optical flow estimation using a spatial pyramid network","author":"ranjan","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recogn"},{"key":"ref23","first-page":"471","article-title":"Fast optical flow using dense inverse\n search","author":"kroeger","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","first-page":"2758","article-title":"FlowNet: Learning optical flow with\n convolutional networks","author":"dosovitskiy","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2485538"},{"key":"ref50","first-page":"2710","article-title":"CNN-based\n patch matching for optical flow with thresholded hinge embedding loss","author":"bailer","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref51","first-page":"6921","article-title":"Optical flow\n requires multiple strategies (but only one network)","author":"schuster","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref59","first-page":"611","article-title":"A naturalistic open source\n movie for optical flow evaluation","author":"butler","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref58","first-page":"3061","article-title":"Object scene flow for autonomous vehicles","author":"menze","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref57","first-page":"3354","article-title":"Are we\n ready for autonomous driving? The KITTI vision benchmark suite","author":"geiger","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref55","first-page":"1385","article-title":"DeepFlow: Large displacement optical\n flow with deep matching","author":"weinzaepfel","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref54","author":"young","year":"1971","journal-title":"Iterative Solution of Large Linear Systems"},{"key":"ref53","article-title":"ENet: A deep neural network\n architecture for real-time semantic segmentation","author":"paszke","year":"2016"},{"key":"ref52","first-page":"6363","article-title":"InterpoNet, a brain inspired neural network for optical flow dense interpolation","author":"zweig","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2283451"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2412879"},{"key":"ref40","first-page":"83","article-title":"Learning optical flow","author":"sun","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref13","first-page":"296","article-title":"Robust dynamic motion estimation over time","author":"black","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/83.668027"},{"key":"ref15","first-page":"25","article-title":"High accuracy optical flow estimation\n based on a theory for warping","author":"brox","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-3960-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref18","first-page":"1019","article-title":"Dense, accurate optical flow estimation with piecewise parametric model","author":"yang","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref19","first-page":"1410","article-title":"Robust optical flow estimation of\n double-layer images under transparency or reflection","author":"yang","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2545401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2299515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2481711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.902875"},{"key":"ref49","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291958"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2645404"},{"key":"ref46","first-page":"4015","article-title":"Flow\n fields: Dense correspondence fields for highly accurate large displacement optical flow estimation","author":"bailer","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref45","first-page":"4236","article-title":"PatchBatch: A batch augmented loss for optical flow","author":"gadot","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref48","first-page":"3","article-title":"Back\n to basics: Unsupervised learning of optical flow via brightness constancy and motion smoothness","author":"jason","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","first-page":"154","article-title":"Exploiting semantic information and deep matching for\n optical flow","author":"bai","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","first-page":"111","article-title":"Computing nearest-neighbor fields via propagation-assisted KD-trees","author":"he","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref41","first-page":"3534","article-title":"Fast edge-preserving\n patchmatch for large displacement optical flow","author":"bao","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref44","first-page":"2443","article-title":"Large displacement optical flow from nearest neighbor fields","author":"chen","year":"0","journal-title":"Proc IEEE Comput Vis Pattern Recognit"},{"key":"ref43","first-page":"1607","article-title":"Coherency sensitive hashing","author":"korman","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8466674\/08316969.pdf?arnumber=8316969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:13Z","timestamp":1642004233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8316969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2815784","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}