{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:04:12Z","timestamp":1780765452383,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102801"],"award-info":[{"award-number":["2018AAA0102801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102803"],"award-info":[{"award-number":["2018AAA0102803"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2018ZE53052"],"award-info":[{"award-number":["2018ZE53052"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2021JM- 074"],"award-info":[{"award-number":["2021JM- 074"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772424"],"award-info":[{"award-number":["61772424"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702418"],"award-info":[{"award-number":["61702418"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602383"],"award-info":[{"award-number":["61602383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3533256","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T18:50:42Z","timestamp":1737658242000},"page":"5762-5775","source":"Crossref","is-referenced-by-count":7,"title":["KPDepth-VO: Self-Supervised Learning of Scale-Consistent Visual Odometry and Depth With Keypoint Features From Monocular Video"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2142-0632","authenticated-orcid":false,"given":"Changhao","family":"Wang","sequence":"first","affiliation":[{"name":"Visual Intelligent Processing Laboratory, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-4074","authenticated-orcid":false,"given":"Guanwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Visual Intelligent Processing Laboratory, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1003-4381","authenticated-orcid":false,"given":"Zhengyun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Visual Intelligent Processing Laboratory, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9715-6957","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Visual Intelligent Processing Laboratory, School of Electronics and Information, Northwestern Polytechnical University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906584"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263484"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326373"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref9","first-page":"35","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","author":"Bian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01484-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3215587"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197374"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2623335"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00716"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3053412"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3384911"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3121483"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01298"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288547"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3418271"},{"key":"ref37","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"2","author":"Eigen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01254"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16329"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981595"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207105"},{"key":"ref45","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. NeurIPS","author":"Kendall"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_43"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183836"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793984"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/34.601246"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00600"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00737"},{"key":"ref58","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3071886"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561642"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref65","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794425"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10851359.pdf?arnumber=10851359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T17:55:00Z","timestamp":1749578100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10851359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3533256","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}