{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:47:32Z","timestamp":1782406052768,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62271103"],"award-info":[{"award-number":["62271103"]}],"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":["61871066"],"award-info":[{"award-number":["61871066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Technology Research and Development Program (863 Program) of China","award":["2015AA016306"],"award-info":[{"award-number":["2015AA016306"]}]},{"name":"Natural Science Foundation of Liaoning Province of China","award":["20170540159"],"award-info":[{"award-number":["20170540159"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"publisher","award":["DUT17LAB04"],"award-info":[{"award-number":["DUT17LAB04"]}],"id":[{"id":"10.13039\/501100012226","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":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3544336","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:54:06Z","timestamp":1740146046000},"page":"7896-7910","source":"Crossref","is-referenced-by-count":2,"title":["High-Order Multi-Scale Attention and Vertical Discriminator Enhanced CLIP for Monocular Depth Estimation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-6449","authenticated-orcid":false,"given":"Ying","family":"Zou","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6822-9667","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2642-8489","authenticated-orcid":false,"given":"Fuliang","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587587"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207105"},{"key":"ref3","article-title":"Orthographic feature transform for monocular 3D object detection","author":"Roddick","year":"2018","journal-title":"arXiv:1811.08188"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/vehicles6010013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316835"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272949"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref11","first-page":"1","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"27","author":"Eigen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00389"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.01.016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00045"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275584"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_20"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340948"},{"key":"ref24","article-title":"Semantically-guided representation learning for self-supervised monocular depth","author":"Guizilini","year":"2020","journal-title":"arXiv:2002.12319"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3118681"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00550"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00218"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00069"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.228"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01251-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/I2CT54291.2022.9824488"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108206"},{"key":"ref40","article-title":"EdgeConv with attention module for monocular depth estimation","author":"Lee","year":"2021","journal-title":"arXiv:2106.08615"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.65"},{"key":"ref42","article-title":"DepthFormer: Exploiting long-range correlation and local information for accurate monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2203.14211"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref44","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Han Lee","year":"2019","journal-title":"arXiv:1907.10326"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104784"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10898074.pdf?arnumber=10898074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:42Z","timestamp":1767638442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10898074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3544336","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}