{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:55:54Z","timestamp":1773993354434,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811842","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T15:36:40Z","timestamp":1657640200000},"page":"7605-7611","source":"Crossref","is-referenced-by-count":13,"title":["Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth"],"prefix":"10.1109","author":[{"given":"Zijie","family":"Jiang","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology,Dept. of Systems and Control Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hajime","family":"Taira","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Dept. of Systems and Control Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoyuki","family":"Miyashita","sequence":"additional","affiliation":[{"name":"R&D Group,Olympus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masatoshi","family":"Okutomi","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Dept. of Systems and Control Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","first-page":"ii-b","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_47"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00631"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00570"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00877"},{"key":"ref40","first-page":"iii-c","article-title":"Unsupervised Monoc-ular Depth Estimation with Left-Right Consistency","author":"godard","year":"0","journal-title":"Proc CVPR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_42"},{"key":"ref13","first-page":"i","article-title":"Bench-marking 6DOF Outdoor Visual Localization in Changing Conditions","author":"sattler","year":"0","journal-title":"Proc CVPR"},{"key":"ref14","first-page":"ii-b","article-title":"Selective Sensor Fusion for Neural Visual-Inertial Odom-etry","volume":"2019","author":"chen","year":"0","journal-title":"Proc CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968467"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/325"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793512"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00296"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref5","first-page":"iii-c","article-title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","volume":"i","author":"bian","year":"2019","journal-title":"NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4135"},{"key":"ref8","first-page":"ii-a","article-title":"Two Stream Networks for Self-Supervised Ego-Motion Estimation","volume":"i","author":"ambrus","year":"0","journal-title":"Proc CoRL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00637"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref21","first-page":"iii-b","article-title":"Deep Multimodal Fusion by Channel Exchanging","volume":"2020","author":"wang","year":"0","journal-title":"NIPS"},{"key":"ref24","first-page":"iii-c","article-title":"Spatial Transformer Networks","volume":"ii a","author":"jaderberg","year":"2015","journal-title":"NIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref41","first-page":"iii-c","article-title":"Neuron-level Structured Pruning using Polarization Regularizer","author":"zhuang","year":"2020","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras","volume":"33","author":"mur-artal","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"key":"ref25","article-title":"Unsuper-vised Learning of Camera Pose with Compositional Re-estimation","volume":"ii a","author":"nabavi","year":"0","journal-title":"Proc WACV"},{"key":"ref43","first-page":"iv-a","author":"paszke","year":"2017","journal-title":"Automatic differentiation in pytorch[J]"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811842.pdf?arnumber=9811842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:06:46Z","timestamp":1667502406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811842","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}