{"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":1780765452049,"version":"3.54.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"STI2030-Major Projects","award":["2022ZD0204600"],"award-info":[{"award-number":["2022ZD0204600"]}]},{"DOI":"10.13039\/100012542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2022ZYD0112"],"award-info":[{"award-number":["2022ZYD0112"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076055"],"award-info":[{"award-number":["62076055"]}],"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":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3263484","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T17:58:14Z","timestamp":1680285494000},"page":"6173-6184","source":"Crossref","is-referenced-by-count":14,"title":["Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1934-2698","authenticated-orcid":false,"given":"Yijun","family":"Cao","sequence":"first","affiliation":[{"name":"MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4320-1967","authenticated-orcid":false,"given":"Xian-Shi","family":"Zhang","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9027-8468","authenticated-orcid":false,"given":"Fuya","family":"Luo","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1779-1753","authenticated-orcid":false,"given":"Chuan","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Electric and Information Engineering, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7395-3131","authenticated-orcid":false,"given":"Yong-Jie","family":"Li","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3766"},{"key":"ref57","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018","journal-title":"arXiv 1807 06757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0102-6"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref58","first-page":"313","article-title":"Integrating egocentric localization for more realistic point-goal navigation agents","author":"datta","year":"2021","journal-title":"Proc Conf Robot Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.31.061307.090723"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0301-0082(98)00004-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref55","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc Conf Workshop Neural Inf Process Syst (NIPS)"},{"key":"ref10","article-title":"3D hierarchical refinement and augmentation for unsupervised learning of depth and pose from monocular video","author":"wang","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref54","article-title":"Pyrobot: An open-source robotics framework for research and benchmarking","author":"murali","year":"2019","journal-title":"arXiv 1906 08236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(97)00078-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","first-page":"1","article-title":"Learning to explore using active neural slam","author":"chaplot","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203974"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2987685"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00322"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.11.067"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080928"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3118681"},{"key":"ref44","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7722-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.199.1.201"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature03721"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00040-018-0647-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00284"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.10-02-00420.1990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00239813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00877"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_42"},{"key":"ref36","first-page":"1","article-title":"BA-Net: Dense bundle adjustment network","author":"tang","year":"2019","journal-title":"Proc ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2705103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01582"},{"key":"ref1","first-page":"1","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"wijmans","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197374"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01559"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"ref21","first-page":"1","article-title":"VTNet: Visual transformer network for object goal navigation","author":"du","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume":"33","author":"deng","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01509"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00182"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10089465.pdf?arnumber=10089465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:34:11Z","timestamp":1698086051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":61,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3263484","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}