{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:40:14Z","timestamp":1780497614430,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Defence Pre-Research Foundation of China","award":["61405170206"],"award-info":[{"award-number":["61405170206"]}]},{"name":"Key Research and Development Program of Shaanxi Province of China","award":["2022GY-245"],"award-info":[{"award-number":["2022GY-245"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3312950","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:36:07Z","timestamp":1694108167000},"page":"3517-3529","source":"Crossref","is-referenced-by-count":26,"title":["Unsupervised Monocular Estimation of Depth and Visual Odometry Using Attention and Depth-Pose Consistency Loss"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9841-9624","authenticated-orcid":false,"given":"Xiaogang","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyue","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5439-5860","authenticated-orcid":false,"given":"Li","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9948-453X","authenticated-orcid":false,"given":"Guo","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Automation and Information Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6394-0492","authenticated-orcid":false,"given":"Xinhong","family":"Hei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref3","first-page":"1","article-title":"Depth map generation from a single image by using a cascade of deep network","volume":"79","author":"Kim","year":"2017","journal-title":"Assoc. Realistic Media Ind."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref5","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Eigen","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref15","article-title":"Joint unsupervised learning of optical flow and depth by watching stereo videos","author":"Wang","year":"2018"},{"key":"ref16","first-page":"1","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","volume-title":"Proc. Adv. Neural Inf. Process. Sys.","author":"Bian","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2772892"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941776"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref25","first-page":"1","article-title":"Semantically-guided representation learning for self-supervised monocular depth","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guizilini","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3068834"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref31","first-page":"1908","article-title":"Unsupervised monocular depth learning in dynamic scenes","volume-title":"Proc. 4th Conf. Robot Learn.","author":"Li","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050082"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875449"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065731"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3133956"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3181062"},{"key":"ref38","first-page":"3961","article-title":"Learning deep structured multi-scale features using attention-gated CRFs for contour prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dan","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091308"},{"key":"ref41","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100895"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793621"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2997247"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref52","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representation","author":"Kingma","year":"2015"},{"key":"ref53","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD image","volume-title":"Proc. 12th Eur. Conf. Comput. Vis.","author":"Siberman","year":"2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref55","first-page":"1161","article-title":"Learning depth from single monocular images","volume-title":"Proc. Int. Conf. Neur. Inf. Process. Sys.","author":"Saxena","year":"2005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref58","first-page":"2666","article-title":"Depth from a single image by harmonizing overcomplete local network predictions","volume-title":"Proc. Neur. Inf. Process. Sys.","author":"Chakrabarti","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00412"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref65","first-page":"3","article-title":"CBAM: Convolutional block attention module","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Sanghyun","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10243088.pdf?arnumber=10243088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:00:31Z","timestamp":1710381631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3312950","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}