{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:01:21Z","timestamp":1757451681601,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534314","type":"proceedings-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T20:40:52Z","timestamp":1632256852000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Monte Carlo Dropout Ensembles for Robust Illumination Estimation"],"prefix":"10.1109","author":[{"given":"Firas","family":"Laakom","sequence":"first","affiliation":[{"name":"Tampere University,Computing and Communication Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenni","family":"Raitoharju","sequence":"additional","affiliation":[{"name":"Finnish Environment Institute,Programme for Environmental Information,Jyv&#x00E4;skyl&#x00E4;,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Iosifidis","sequence":"additional","affiliation":[{"name":"Aarhus University,Department of Engineering,Aarhus,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jarno","family":"Nikkanen","sequence":"additional","affiliation":[{"name":"Xiaomi Technologies, Xiaomi Finland Oy,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moncef","family":"Gabbouj","sequence":"additional","affiliation":[{"name":"Tampere University,Computing and Communication Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"3","article-title":"Gaussian process deep belief networks: A smooth generative model of shape with uncertainty propagation","author":"di martino","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref38","first-page":"207","article-title":"Deep gaussian processes","author":"damianou","year":"2013","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297710"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247659"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713044"},{"key":"ref30","first-page":"1050","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref37","volume":"405","author":"bernardo","year":"2009","journal-title":"Bayesian Theory"},{"key":"ref36","first-page":"189","article-title":"Analysis on the dropout effect in convolutional neural networks","author":"park","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref35","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.614"},{"key":"ref10","article-title":"Color correction between gray world and white patch","author":"rizzi","year":"2002","journal-title":"Proc Int Soc Opt Eng"},{"key":"ref40","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901808"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"37","DOI":"10.2352\/CIC.2004.12.1.art00008","article-title":"Shades of gray and colour constancy","author":"finlayson","year":"2004","journal-title":"Color Imaging Conference"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206497"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.76"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301275"},{"key":"ref17","first-page":"4085","article-title":"FC4: Fully convolutional color constancy with confidence-weighted pooling","author":"hu","year":"2017","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9002684"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004921"},{"key":"ref28","article-title":"Sensor-independent illumination estimation for dnn models","author":"afifi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2118224"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00163"},{"journal-title":"Practical colour constancy","year":"1999","author":"barnard","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00825"},{"key":"ref29","first-page":"2","article-title":"Dropout as a bayesian approximation: Insights and applications","volume":"1","author":"gal","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.426"},{"key":"ref8","article-title":"Unsupervised learning for color constancy","author":"banic","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298838"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1104"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53842-1_42"},{"key":"ref1","volume":"7","author":"ebner","year":"2007","journal-title":"Color Constancy"},{"key":"ref46","article-title":"Reproduction angular error: An improved performance metric for illuminant estimation","author":"finlayson","year":"2014","journal-title":"Perception"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.51"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2169-2629.2018.26.350"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190893"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.31.001049"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/978-3-319-46976-8_6","article-title":"Fast predictive image registration","author":"yang","year":"2016","journal-title":"Deep Learning and Data Labeling for Medical Applications"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899914"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2323"},{"key":"ref23","article-title":"Intel-tau: A color constancy dataset","author":"laakom","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1136\/bmj.312.7047.1654","article-title":"Statistics notes: measurement error","volume":"312","author":"bland","year":"1996","journal-title":"BMJ"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.34.001448"},{"key":"ref43","article-title":"Multi-task deep neural network to predict cpg methylation profiles from low-coverage sequencing data","author":"angermueller","year":"2015","journal-title":"NIPS MLCB workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00147"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534314.pdf?arnumber=9534314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T04:55:30Z","timestamp":1699505730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534314","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}