{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T23:23:19Z","timestamp":1775344999568,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012335","name":"National Defense Basic Scientific Research Program of China","doi-asserted-by":"publisher","award":["JCKY2021130B016"],"award-info":[{"award-number":["JCKY2021130B016"]}],"id":[{"id":"10.13039\/501100012335","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":[[2024,6]]},"DOI":"10.1109\/tcsvt.2023.3335316","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:13:48Z","timestamp":1700597628000},"page":"4354-4366","source":"Crossref","is-referenced-by-count":10,"title":["HA-Bins: Hierarchical Adaptive Bins for Robust Monocular Depth Estimation Across Multiple Datasets"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6092-0712","authenticated-orcid":false,"given":"Ruijie","family":"Zhu","sequence":"first","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6348-8713","authenticated-orcid":false,"given":"Ziyang","family":"Song","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3280-8490","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-788X","authenticated-orcid":false,"given":"Jianfeng","family":"He","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Deep Space Exploration Laboratory\/School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023634"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00567"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref10","article-title":"Learning depth from single monocular images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Saxena"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1040012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3305817"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00229"},{"key":"ref17","article-title":"MovieChat: From dense token to sparse memory for long video understanding","author":"Song","year":"2023","journal-title":"arXiv:2307.16449"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref23","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019","journal-title":"arXiv:1907.10326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.52"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00389"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref33","article-title":"BinsFormer: Revisiting adaptive bins for monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2204.00987"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref36","article-title":"Towards 3D scene reconstruction from locally scale-aligned monocular video depth","author":"Xu","year":"2022","journal-title":"arXiv:2202.01470"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref38","article-title":"ZoeDepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv:2302.12288"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2962867"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929202"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128505"},{"key":"ref46","article-title":"Single-image depth perception in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00037"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505283"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00412"},{"key":"ref53","article-title":"SideRT: A real-time pure transformer architecture for single image depth estimation","author":"Shu","year":"2022","journal-title":"arXiv:2204.13892"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16282"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00177"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref65","article-title":"DiverseDepth: Affine-invariant depth prediction using diverse data","author":"Yin","year":"2020","journal-title":"arXiv:2002.00569"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3043781"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.243"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref74","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10550083\/10325550.pdf?arnumber=10325550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:37:54Z","timestamp":1736368674000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10325550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":74,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3335316","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}