{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:52:51Z","timestamp":1783525971660,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundations of China","doi-asserted-by":"publisher","award":["61771091"],"award-info":[{"award-number":["61771091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundations of China","doi-asserted-by":"publisher","award":["61871066"],"award-info":[{"award-number":["61871066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012164","name":"National High Technology Research and Development Program (863 Program) of China","doi-asserted-by":"publisher","award":["2015AA016306"],"award-info":[{"award-number":["2015AA016306"]}],"id":[{"id":"10.13039\/501100012164","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province of China","doi-asserted-by":"publisher","award":["20170540159"],"award-info":[{"award-number":["20170540159"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Fund for the Central Universities of China","doi-asserted-by":"publisher","award":["DUT17LAB04"],"award-info":[{"award-number":["DUT17LAB04"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3120670","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T19:56:28Z","timestamp":1635364588000},"page":"8811-8822","source":"Crossref","is-referenced-by-count":37,"title":["Multi-Scale Spatial Attention-Guided Monocular Depth Estimation With Semantic Enhancement"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8538-8280","authenticated-orcid":false,"given":"Xianfa","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6822-9667","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2642-8489","authenticated-orcid":false,"given":"Fuliang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref38","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref32","first-page":"1","article-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video","author":"bian","year":"2019","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/788"},{"key":"ref37","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"531","article-title":"Mine: Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"1","article-title":"Semantically-guided representation learning for self-supervised monocular depth","author":"guizilini","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2621673"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1007\/s11263-018-1081-7","article-title":"Depth-based hand pose estimation: Methods, data, and challenges","volume":"126","author":"supan?i?","year":"2018","journal-title":"Int J Comput Vis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941776"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"ref21","first-page":"740","article-title":"Unsupervised CNN for single view depth estimation: Geometry to the rescue","author":"garg","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","first-page":"298","article-title":"Geometry meets semantics for semi-supervised monocular depth estimation","author":"ramirez","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0071-y"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316835"},{"key":"ref53","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_35"},{"key":"ref11","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 Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume":"9","author":"gutmann","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_4"},{"key":"ref14","first-page":"232","article-title":"Monocular depth estimation with affinity, vertical pooling, and label enhancement","author":"gan","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00412"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2711277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2845699"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref5","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"silberman","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_17"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref9","first-page":"1288","article-title":"Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces","author":"gupta","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref48","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160360204"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01142"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09583951.pdf?arnumber=9583951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:10Z","timestamp":1652194210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9583951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3120670","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}