{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:35:14Z","timestamp":1778348114448,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["61972162"],"award-info":[{"award-number":["61972162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholar","award":["2023B1515020097"],"award-info":[{"award-number":["2023B1515020097"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 1","award":["MSS23C002"],"award-info":[{"award-number":["MSS23C002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3308551","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T17:22:23Z","timestamp":1692984143000},"page":"15081-15097","source":"Crossref","is-referenced-by-count":14,"title":["Monocular Depth Estimation for Glass Walls With Context: A New Dataset and Method"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0942-9781","authenticated-orcid":false,"given":"Yuan","family":"Liang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0158-7670","authenticated-orcid":false,"given":"Bailin","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3630-6322","authenticated-orcid":false,"given":"Wenxi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer and Data Science, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-0860","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Nursing, Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00374"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00462"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_6"},{"key":"ref15","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01321"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_35"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197518"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00286"},{"key":"ref10","first-page":"3783","article-title":"Glass object localization by joint inference of boundary and depth","author":"wang","year":"2012","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref16","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"lee","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238669"},{"key":"ref51","first-page":"11525","article-title":"Object-centric learning with slot attention","author":"locatello","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref50","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01786"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00596"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00424"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_41"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00863"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02049"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01556"},{"key":"ref49","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"ref9","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"nathan silberman","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00386"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2019.2893820"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00379"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00956"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00383"},{"key":"ref30","first-page":"4009","article-title":"AdaBins: Depth estimation using adaptive bins","author":"bhat","year":"2021","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480500","article-title":"Consistent depth of moving objects in video","volume":"40","author":"zhang","year":"2021","journal-title":"ACM Trans Graph"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01662"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00859"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00163"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00172"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref64","article-title":"Bayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding","author":"kendall","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref60","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10230851.pdf?arnumber=10230851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:52:00Z","timestamp":1701114720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10230851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":65,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3308551","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}