{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:33:11Z","timestamp":1786113191327,"version":"3.56.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8461251","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"7286-7291","source":"Crossref","is-referenced-by-count":399,"title":["UnDeepVO: Monocular Visual Odometry Through Unsupervised Deep Learning"],"prefix":"10.1109","author":[{"given":"Ruihao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongbing","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2505717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref12","article-title":"DeMoN: Depth and motion network for learning monocular stereo","author":"ummenhofer","year":"2017","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref13","first-page":"3995","article-title":"VINet: Visual-Inertial odometry as a sequence-to-sequence learning problem","author":"clark","year":"2017","journal-title":"AAAI"},{"key":"ref14","author":"pillai","year":"2017","journal-title":"Towards visual ego-motion learning in robots"},{"key":"ref15","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"740","article-title":"Unsupervised CNN for single view depth estimation: Geometry to the rescue","author":"garg","year":"2016","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref17","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"godard","year":"2017","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref18","article-title":"Unsupervised learning of depth and ego-motion from video","author":"zhou","year":"2017","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: a versatile and accurate monocular SLAM system","volume":"31","author":"mur-artal","year":"2015","journal-title":"IEEE Transactions on Robotics"},{"key":"ref6","article-title":"Direct sparse odometry","author":"engel","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref5","first-page":"834","article-title":"LSD-SLAM: Large-scale direct monocular SLAM","author":"engel","year":"2014","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref8","article-title":"Indoor relocalization in challenging environments with dual-stream convolutional neural networks","author":"li","year":"2017","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref9","article-title":"VidLoc: 6-DoF video-clip relocalization","author":"clark","year":"2017","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref20","article-title":"Is L2 a good loss function for neural networks for image processing?","volume":"1511","author":"zhao","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref22","article-title":"Are we ready for autonomous driving? The KITTI vision benchmark suite","author":"geiger","year":"2012","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref23","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08461251.pdf?arnumber=8461251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:59:49Z","timestamp":1598245189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8461251","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}