{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:51:20Z","timestamp":1740160280092,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T00:00:00Z","timestamp":1570665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T00:00:00Z","timestamp":1570665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s13042-019-01020-6","type":"journal-article","created":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T10:48:24Z","timestamp":1570704504000},"page":"615-627","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Unsupervised learning of monocular depth and ego-motion with space\u2013temporal-centroid loss"],"prefix":"10.1007","volume":"11","author":[{"given":"Junning","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Qunxing","family":"Su","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2603-4754","authenticated-orcid":false,"given":"Pengyuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yanlong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,10]]},"reference":[{"issue":"10","key":"1020_CR1","first-page":"1","volume":"38","author":"S Wu","year":"2017","unstructured":"Wu S, Zhao H, Sun S (2017) Depth estimation from infrared video using local-feature-flow neural network. Int J Mach Learn Cybern 38(10):1\u201310","journal-title":"Int J Mach Learn Cybern"},{"issue":"01","key":"1020_CR2","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s13042-013-0188-y","volume":"05","author":"GL Marcialis","year":"2014","unstructured":"Marcialis GL, Roli F, Fadda G (2014) A novel method for head pose estimation based on the \u201cVitrubyn Man\u201d. Int J Mach Learn Cybern 05(01):111\u2013124","journal-title":"Int J Mach Learn Cybern"},{"key":"1020_CR3","doi-asserted-by":"crossref","unstructured":"Kendall A, Grimes M, Cipolla R (2015) PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on computer vision (ICCV), pp. 2938\u20132946","DOI":"10.1109\/ICCV.2015.336"},{"key":"1020_CR4","doi-asserted-by":"crossref","unstructured":"Clark R, Wang S, Wen H, Markham A, Trigoni N (2017) VINet: visual-inertial odometry as a sequence-to-sequence learning problem. AAAI, pp. 3995\u20134001","DOI":"10.1609\/aaai.v31i1.11215"},{"key":"1020_CR5","doi-asserted-by":"crossref","unstructured":"Chaoyang Wang, Jos\u00b4e Miguel Buenaposada, Rui Zhu et al. \u201cLearning Depth from Monocular Videos using Direct Methods,\u201d in Conference on Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2018.00216"},{"key":"1020_CR6","unstructured":"Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. Adv Neural Inf Process Syst, pp. 2017\u20132025"},{"key":"1020_CR7","doi-asserted-by":"crossref","unstructured":"Yang Z, Wang P, Xu W (2018) Unsupervised learning of geometry with edge-aware depth-normal consistency. Conference on the Association for the advance of artificial intelligence (AAAI)","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"1020_CR8","doi-asserted-by":"crossref","unstructured":"Li R, Liu Q, Gui J, Gu D, Hu H (2017) Indoor relocalization in challenging environments with dual-stream convolutional neural networks. IEEE Trans Automat Sci Eng","DOI":"10.1109\/TASE.2017.2664920"},{"key":"1020_CR9","unstructured":"Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two frame stereo correspondence algorithms. IJCV"},{"key":"1020_CR10","doi-asserted-by":"crossref","unstructured":"Song S, Chandraker M (2014) Robust scale estimation in real-time monocular sfm for autonomous driving. In Proceedings of the IEEE Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2014.203"},{"key":"1020_CR11","doi-asserted-by":"crossref","unstructured":"Flynn J, Neulander I, Philbin J, Snavely N (2016) Deep-stereo: learning to predict new views from the worlds imagery. In CVPR","DOI":"10.1109\/CVPR.2016.595"},{"key":"1020_CR12","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. NIPS"},{"key":"1020_CR13","doi-asserted-by":"crossref","unstructured":"Liu F, Shen C, Lin G, Reid I (2015) Learning depth from single monocular images using deep convolutional neural fields. PAMI","DOI":"10.1109\/TPAMI.2015.2505283"},{"issue":"5","key":"1020_CR14","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena A, Sun M, Ng AY (2009) Make3D: learning 3D scene structure from a single still image. IEEE Trans Pattern Anal Mach Intell 31(5):824\u2013840","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10","key":"1020_CR15","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"FY Liu","year":"2016","unstructured":"Liu FY, Shen CH, Lin GS et al (2016) Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024\u20132039","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1020_CR16","doi-asserted-by":"crossref","unstructured":"Ummenhofer B, Zhou H, Uhrig J et al (2016) DeMoN: depth and motion network for learning monocular stereo","DOI":"10.1109\/CVPR.2017.596"},{"key":"1020_CR17","unstructured":"Li B, Shen C, Dai Y et al (2015) Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs[C]\/\/IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, pp. 1119\u20131127"},{"key":"1020_CR18","unstructured":"Jayaraman D, Grauman K (2015) Learning image representations tied to ego-motion[C]\/\/IEEE International Conference on Computer Vision. IEEE, pp 1413\u20131421"},{"key":"1020_CR19","unstructured":"Yan X, Yang J, Yumer E et al (2016) Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. Adv Neural Inf Process Syst. pp. 1696\u20131704"},{"key":"1020_CR20","unstructured":"Rezende DJ, Eslami SMA, Mohamed S et al (2016) Unsupervised learning of 3d structure from images. Adv Neural Inf Process Syst, 4997\u20135005"},{"key":"1020_CR21","doi-asserted-by":"crossref","unstructured":"Zhou T, Brown M, Snavely N et al (2017) Unsupervised learning of depth and ego-motion from video[C]\/\/IEEE Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.700"},{"key":"1020_CR22","doi-asserted-by":"crossref","unstructured":"Yin Z, Shi J (2018) GeoNet: unsupervised learning of dense depth, optical flow and camera pose. [C]\/\/Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00212"},{"key":"1020_CR23","doi-asserted-by":"crossref","unstructured":"Xie J, Girshick R, Farhadi A (2016) Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"1020_CR24","doi-asserted-by":"crossref","unstructured":"Godard C, Aodha OM, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency","DOI":"10.1109\/CVPR.2017.699"},{"key":"1020_CR25","doi-asserted-by":"crossref","unstructured":"Garg R, Vijay KBG, Carneiro G et al (2016) Unsupervised CNN for single view depth estimation: geometry to the rescue[J]. pp. 740\u2013756","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"1020_CR26","doi-asserted-by":"crossref","unstructured":"Mahjourian, Wicke M, Angelova A (2018) Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00594"},{"key":"1020_CR27","doi-asserted-by":"crossref","unstructured":"Zhan H, Garg R, Weerasekera CS et al (2018) Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction.[C]\/\/Conference on computer vision and pattern recognition, 2018","DOI":"10.1109\/CVPR.2018.00043"},{"key":"1020_CR28","doi-asserted-by":"crossref","unstructured":"Li R, Wang S, Long Z et al (2018) UnDeepVO: monocular visual odometry through unsupervised deeplearning. Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"1020_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1020_CR30","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (ICLR)"},{"issue":"11","key":"1020_CR31","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-019-01020-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-019-01020-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-019-01020-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T09:54:53Z","timestamp":1664618093000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-019-01020-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,10]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1020"],"URL":"https:\/\/doi.org\/10.1007\/s13042-019-01020-6","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2019,10,10]]},"assertion":[{"value":"10 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}