{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,8]],"date-time":"2026-11-08T02:25:09Z","timestamp":1794104709116,"version":"4.8.0"},"reference-count":51,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/cvpr.2017.441","type":"proceedings-article","created":{"date-parts":[[2017,11,9]],"date-time":"2017-11-09T21:50:33Z","timestamp":1510264233000},"page":"4141-4150","source":"Crossref","is-referenced-by-count":545,"title":["Deep Feature Flow for Video Recognition"],"prefix":"10.1109","author":[{"given":"Xizhou","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwen","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref38","article-title":"Clockwork convnets for video semantic segmentation","author":"shelhamer","year":"2016","journal-title":"ECCV"},{"key":"ref33","author":"rastegari","year":"2016","journal-title":"Xnornet Imagenet classification using binary convolutional neural networks"},{"key":"ref32","author":"ranjan","year":"2016","journal-title":"Optical flow estimation using a spatial pyramid network"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.422"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref34","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref27","author":"liu","year":"2016","journal-title":"Ssd Single shot multibox detector"},{"key":"ref29","article-title":"Indoor segmentation and support inference from rgbd images","author":"nathan silberman","year":"2012","journal-title":"ECCV"},{"key":"ref2","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"brox","year":"2004","journal-title":"ECCV"},{"key":"ref1","article-title":"Exploiting semantic information and deep matching for optical flow","author":"bai","year":"2016","journal-title":"ECCV"},{"key":"ref20","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref22","article-title":"T-cnn: Tubelets with convolutional neural networks for object detection from videos","author":"kang","year":"2016","journal-title":"CVPR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.418"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.345"},{"key":"ref23","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref26","article-title":"Sift flow: dense correspondence across difference scenes","author":"liu","year":"2008","journal-title":"ECCV"},{"key":"ref25","author":"lee","year":"2016","journal-title":"Multi-Class Multi-Object Tracking using Changing Point Detection"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref51","article-title":"Deep learning of invariant features via simulated fixations in video","author":"zou","year":"2012","journal-title":"NIPS"},{"key":"ref10","author":"fayyaz","year":"2016","journal-title":"STFCN spatio-temporal FCN for semantic video segmentation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.438"},{"key":"ref40","article-title":"Dlsfa: deeply-learned slow feature analysis for action recognition","author":"sun","year":"2014","journal-title":"CVPR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref14","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref18","author":"hubara","year":"2016","journal-title":"Quantized neural networks Training neural networks with low precision weights and activations"},{"key":"ref19","article-title":"Joint optical flow and temporally consistent semantic segmentation","author":"hur","year":"2016","journal-title":"ECCV CVRSUAD workshop"},{"key":"ref4","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"chen","year":"2015","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","author":"chen","year":"2016","journal-title":"Deeplab Semantic image segmentation with deep convolutional nets atrous convolution and fully connected crfs"},{"key":"ref8","article-title":"R-fcn: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"NIPS"},{"key":"ref7","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"NIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.650"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref48","article-title":"Accelerating very deep convolutional networks for classification and detection","author":"zhang","year":"2015","journal-title":"TPAMI"},{"key":"ref47","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.175"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-34767-5_5"}],"event":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Honolulu, HI","start":{"date-parts":[[2017,7,21]]},"end":{"date-parts":[[2017,7,26]]}},"container-title":["2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8097368\/8099483\/08099924.pdf?arnumber=8099924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,12,15]],"date-time":"2017-12-15T20:00:01Z","timestamp":1513368001000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8099924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2017.441","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}