{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T07:22:46Z","timestamp":1769844166156,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52372418"],"award-info":[{"award-number":["52372418"]}],"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":["62076201"],"award-info":[{"award-number":["62076201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022YFB2602203"],"award-info":[{"award-number":["2022YFB2602203"]}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Shaanxi Province of China","doi-asserted-by":"publisher","award":["2023GXLH-043"],"award-info":[{"award-number":["2023GXLH-043"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tits.2025.3581577","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:55:01Z","timestamp":1759168501000},"page":"20536-20548","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervised Monocular Depth Estimation With Progressive Enhancement of Local-to-Global Visual Perception"],"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":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9794-9889","authenticated-orcid":false,"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Xi’an University of Technology, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3802-5068","authenticated-orcid":false,"given":"Bingxing","family":"Wei","sequence":"additional","affiliation":[{"name":"China Railway First Group, Electrical Service Engineering Company Ltd., Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3876-6449","authenticated-orcid":false,"given":"Xinwei","family":"Guo","sequence":"additional","affiliation":[{"name":"China Railway First Group, Electrical Service Engineering Company Ltd., Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3290348"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00605"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275535"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160657"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3210274"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340948"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3221416"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219604"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196781"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25090"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR59233.2023.00138"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312721"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_9"},{"key":"ref22","article-title":"FlowDepth: Decoupling optical flow for self-supervised monocular depth estimation","author":"Sun","year":"2024","journal-title":"arXiv:2403.19294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3402655"},{"key":"ref26","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968283"},{"key":"ref31","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Eigen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015422"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3299935"},{"key":"ref38","article-title":"EVP: Enhanced visual perception using inverse multi-attentive feature refinement and regularized image-text alignment","author":"Lavreniuk","year":"2023","journal-title":"arXiv:2312.08548"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_34"},{"key":"ref43","article-title":"Self-supervised monocular depth estimation with large kernel attention","author":"Xiang","year":"2024","journal-title":"arXiv:2409.17895"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108790"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3301711"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3312950"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3404924"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107268"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"issue":"16","key":"ref58","first-page":"1908","article-title":"Unsupervised monocular depth learning in dynamic scenes","volume-title":"Proc. Conf. Robot. Learn.","volume":"155","author":"Li"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01399"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00482"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16281"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref66","volume-title":"Ptflops: A Flops Counting Tool for Neural Networks in PyTorch Framework","author":"Sovrasov","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3400873"},{"key":"ref68","article-title":"AsCAN: Asymmetric convolution-attention networks for efficient recognition and generation","author":"Kag","year":"2024","journal-title":"arXiv:2411.04967"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11241045\/11184682.pdf?arnumber=11184682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:43:17Z","timestamp":1762972997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11184682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":68,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3581577","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}