{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T07:26:13Z","timestamp":1774769173448,"version":"3.50.1"},"reference-count":71,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2009"],"award-info":[{"award-number":["U23B2009"]}],"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":["92270116"],"award-info":[{"award-number":["92270116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3416065","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T20:15:22Z","timestamp":1719260122000},"page":"3964-3976","source":"Crossref","is-referenced-by-count":105,"title":["BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation"],"prefix":"10.1109","volume":"33","author":[{"given":"Zhenyu","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2006-3832","authenticated-orcid":false,"given":"Xuyang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Engineering and Computer Science, Australian National University, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8857-1785","authenticated-orcid":false,"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1582-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_23"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_15"},{"key":"ref6","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1089\/cpb.2007.9935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0189275"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01313"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00746"},{"key":"ref13","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. NeurIPS","volume":"27","author":"Eigen"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120670"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821979"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00481"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3074306"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref22","first-page":"503","article-title":"Robust semi-supervised monocular depth estimation with reprojected distances","volume-title":"Proc. CoRL","author":"Guizilini"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01241"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506550"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00996"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","article-title":"A survey on visual transformer","author":"Han","year":"2020","journal-title":"arXiv:2012.12556"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref45","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv:2012.15460"},{"key":"ref46","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2021","journal-title":"arXiv:2112.01527"},{"key":"ref47","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NeurIPS","volume":"34","author":"Cheng"},{"key":"ref48","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_14"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3043781"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref54","article-title":"VA-DepthNet: A variational approach to single image depth prediction","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref55","article-title":"Bidirectional attention network for monocular depth estimation","author":"Aich","year":"2020","journal-title":"arXiv:2009.00743"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16282"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00012"},{"key":"ref60","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","article-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2018","journal-title":"arXiv:1812.11941"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref66","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/98"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref69","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. NeurIPS","author":"Kendall"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01124"},{"key":"ref71","article-title":"DepthFormer: Exploiting long-range correlation and local information for accurate monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2203.14211"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10570231.pdf?arnumber=10570231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T17:53:08Z","timestamp":1719856388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3416065","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}