{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:05:37Z","timestamp":1780589137771,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3260310","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T18:08:41Z","timestamp":1679508521000},"page":"5882-5893","source":"Crossref","is-referenced-by-count":41,"title":["METER: A Mobile Vision Transformer Architecture for Monocular Depth Estimation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9393-5248","authenticated-orcid":false,"given":"Lorenzo","family":"Papa","sequence":"first","affiliation":[{"name":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1886-3491","authenticated-orcid":false,"given":"Paolo","family":"Russo","sequence":"additional","affiliation":[{"name":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6461-1391","authenticated-orcid":false,"given":"Irene","family":"Amerini","sequence":"additional","affiliation":[{"name":"Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2020.12.089","article-title":"Deep learning for monocular depth estimation: A review","volume":"438","author":"Ming","year":"2021","journal-title":"Neurocomputing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cac51589.2020.9327548"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref6","article-title":"BinsFormer: Revisiting adaptive bins for monocular depth estimation","author":"Li","year":"2022","journal-title":"arXiv:2204.00987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3170425"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794182"},{"key":"ref9","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref13","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2877944"},{"key":"ref16","article-title":"High quality monocular depth estimation via transfer learning","author":"Alhashim","year":"2018","journal-title":"arXiv:1812.11941"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20231"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207105"},{"key":"ref26","article-title":"Global-local path networks for monocular depth estimation with vertical CutDepth","author":"Kim","year":"2022","journal-title":"arXiv:2201.07436"},{"key":"ref27","article-title":"CutDepth: Edge-aware data augmentation in depth estimation","author":"Ishii","year":"2021","journal-title":"arXiv:2107.07684"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/a13050125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593814"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00275"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref36","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref40","volume-title":"Data Smart: Using Data Science to Transform Information Into Insight","author":"Foreman","year":"2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10078346.pdf?arnumber=10078346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T07:41:30Z","timestamp":1709451690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10078346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":42,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3260310","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}