{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:12:17Z","timestamp":1777655537771,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006469","name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","doi-asserted-by":"publisher","award":["0022\/2019\/AKP"],"award-info":[{"award-number":["0022\/2019\/AKP"]}],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2020C01109"],"award-info":[{"award-number":["2020C01109"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223024"],"award-info":[{"award-number":["L223024"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076016"],"award-info":[{"award-number":["62076016"]}],"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":["61620106012"],"award-info":[{"award-number":["61620106012"]}],"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":["61573048"],"award-info":[{"award-number":["61573048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3224810","type":"journal-article","created":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T22:39:17Z","timestamp":1669415957000},"page":"7660-7671","source":"Crossref","is-referenced-by-count":24,"title":["Towards Comprehensive Monocular Depth Estimation: Multiple Heads are Better Than One"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8057-1599","authenticated-orcid":false,"given":"Shuwei","family":"Shao","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-1570","authenticated-orcid":false,"given":"Ran","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7748-8591","authenticated-orcid":false,"given":"Zhongcai","family":"Pei","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3242-5997","authenticated-orcid":false,"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7912-4505","authenticated-orcid":false,"given":"Weihai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7505-9512","authenticated-orcid":false,"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4334-0465","authenticated-orcid":false,"given":"Xingming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7396-6218","authenticated-orcid":false,"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref4","first-page":"126","article-title":"Depth-assisted real-time 3D object detection for augmented reality","volume-title":"Proc. 21st Int. Conf. Artif. Reality Telexistence","author":"Lee","year":"2011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102338"},{"key":"ref6","first-page":"1","article-title":"Learning depth from single monocular images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Saxena","year":"2005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.365"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2912121"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091308"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"ref16","first-page":"1","article-title":"Snapshot ensembles: Train 1, get m for free","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107582"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3206108"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref23","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref29","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eigen","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00037"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","first-page":"6881","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zheng","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref38","first-page":"14745","article-title":"TransGAN: Two transformers can make one strong GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2021"},{"issue":"1","key":"ref39","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007515423169","article-title":"An empirical comparison of voting classification algorithms: Bagging, boosting, and variants","volume":"36","author":"Bauer","year":"1999","journal-title":"Mach. Learn."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00190-X"},{"key":"ref41","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan","year":"2017"},{"key":"ref42","first-page":"6514","article-title":"Hyperparameter ensembles for robustness and uncertainty quantification","author":"Wenzel","year":"2020"},{"key":"ref43","first-page":"5505","article-title":"DVERGE: Diversifying vulnerabilities for enhanced robust generation of ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.2003.813832"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00191"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref48","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref49","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3026669"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01261"},{"key":"ref54","first-page":"1","article-title":"Automatic differentiation in pytorch","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop Autodiff","author":"Paszke","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09964065.pdf?arnumber=9964065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T23:03:34Z","timestamp":1703027014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9964065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3224810","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}