{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T15:33:33Z","timestamp":1772897613827,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"47-48","license":[{"start":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T00:00:00Z","timestamp":1562284800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T00:00:00Z","timestamp":1562284800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s11042-019-07882-w","type":"journal-article","created":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T11:02:41Z","timestamp":1562324561000},"page":"35475-35489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Indoor scene understanding via RGB-D image segmentation employing depth-based CNN and CRFs"],"prefix":"10.1007","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-4495","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[]},{"given":"Junhua","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Yongfeng","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"7882_CR1","first-page":"99","volume":"PP","author":"FI Alam","year":"2017","unstructured":"Alam FI, Zhou J, Liew WC et al (2017) Conditional random field and deep feature learning for hyperspectral image segmentation[J]. IEEE Trans Geosci Remote Sens PP:99","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"7882_CR2","unstructured":"Badrinarayanan V, Handa A, Cipolla R (2015) Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293"},{"key":"7882_CR3","unstructured":"Chen S, de Bruijne M (2018) An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. arXiv preprint arXiv:1811.03549"},{"issue":"4","key":"7882_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2016","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2016) DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs[J]. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7882_CR5","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking Atrous convolution for semantic image segmentationar. Xiv preprint arXiv: 1706.05587"},{"key":"7882_CR6","doi-asserted-by":"crossref","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) r-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), pp 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"7882_CR7","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected CRFs. Computer Science (4):357\u2013361"},{"key":"7882_CR8","unstructured":"Chunfang ZH (2012) Image semantic segmentation based on conditional random field. Computer CD Software and Applications (9):21\u201323"},{"key":"7882_CR9","unstructured":"Couprie C, Farabet C, Najman L, LeCun Y (2013) Indoor semantic segmentation using depth information. arXiv preprint arXiv: 1301.3572"},{"key":"7882_CR10","doi-asserted-by":"publisher","unstructured":"Ding G, Guo Y, Chen K et al (2019) DECODE: deep confidence network for robust image classification[J]. IEEE Trans Image Process. https:\/\/doi.org\/10.1109\/TIP.2019.2902115","DOI":"10.1109\/TIP.2019.2902115"},{"issue":"2","key":"7882_CR11","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1109\/TCE.2012.6227420","volume":"58","author":"J Han","year":"2012","unstructured":"Han J, Pauwels EJ, Zeeuw PMD et al (2012) Employing a RGB-D sensor for real-time tracking of humans across multiple re-entries in a smart environment[J]. IEEE Trans Consum Electron 58(2):255\u2013263","journal-title":"IEEE Trans Consum Electron"},{"key":"7882_CR12","unstructured":"Han J, Shao L, Xu D, Shotton J (2013) Enhanced computer vision with microsoft kinect sensor: A review. IEEE Trans Cybern 43(5):1318\u20131334"},{"key":"7882_CR13","unstructured":"Hazirbas C, Ma L, Domokos C et al (2016) FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture[C]. In: Asian conference on computer vision. Springer, Cham"},{"key":"7882_CR14","doi-asserted-by":"crossref","unstructured":"Janoch A, Karayev S, Jia Y, Barron JT, Fritz M, Saenko K, Darrell T (2013) A category-level 3d object dataset: Putting the kinect to work. In: Consumer depth cameras for computer vision. Springer, London, pp 141\u2013165","DOI":"10.1007\/978-1-4471-4640-7_8"},{"key":"7882_CR15","doi-asserted-by":"crossref","unstructured":"Jiang J, Zhang Z, Huang Y, Zheng L (2017) Incorporating depth into both cnn and crf for indoor semantic segmentation. In 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), IEEE, pp 525\u2013530","DOI":"10.1109\/ICSESS.2017.8342970"},{"key":"7882_CR16","unstructured":"Kendall A, Badrinarayanan V, Cipolla R (2015) Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv: 1511.02680"},{"key":"7882_CR17","unstructured":"Kr\u00e4henb\u00fchl, Philipp, Koltun V (2012) Efficient inference in fully connected CRFs with Gaussian edge potentials[J]. In Advances in neural information processing systems, pp 109\u2013117"},{"key":"7882_CR18","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks[C]. In: NIPS. Curran Associates Inc. In Advances in neural information processing systems, pp 1097\u20131105"},{"key":"7882_CR19","unstructured":"Lafferty J, McCallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data[J]"},{"key":"7882_CR20","unstructured":"Li X, Belaroussi R (2016) Semi-dense 3D semantic mapping from monocular SLAM[J]. arXiv preprint arXiv:1611.04144"},{"key":"7882_CR21","doi-asserted-by":"crossref","unstructured":"Li Z, Gan Y, Liang X et al (2016) LSTM-CF: unifying context modeling and fusion with LSTMs for RGB-D scene labeling[J]. In European conference on computer vision Springer, Cham, pp 541\u2013557","DOI":"10.1007\/978-3-319-46475-6_34"},{"key":"7882_CR22","unstructured":"Lin G, Shen C, Anton VDH et al (2017) Exploring context with deep structured models for semantic segmentation[J]. IEEE Trans Pattern Anal Mach Intell 40(6):1352\u20131366"},{"issue":"4","key":"7882_CR23","first-page":"640","volume":"39","author":"J Long","year":"2014","unstructured":"Long J, Shelhamer E, Darrell T (2014) Fully convolutional networks for semantic segmentation[J]. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"7882_CR24","doi-asserted-by":"publisher","first-page":"4357","DOI":"10.1109\/TIP.2018.2835143","volume":"27","author":"S Luan","year":"2018","unstructured":"Luan S, Chen C, Zhang B et al (2018) Gabor convolutional networks[J]. IEEE Trans Image Process 27(9):4357\u20134366","journal-title":"IEEE Trans Image Process"},{"key":"7882_CR25","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation[J]. In Proceedings of the IEEE international conference on computer vision, pp 1520\u20131528","DOI":"10.1109\/ICCV.2015.178"},{"key":"7882_CR26","unstructured":"Pang Y, Cao J, Li X (2015) Cascade learning by optimally partitioning[J]. IEEE transactions on cybernetics 47(12):4148\u20134161"},{"key":"7882_CR27","unstructured":"Pang Y, Xie J, Nie F et al (2018) Spectral clustering by joint spectral embedding and spectral rotation[J]. IEEE Transactions on Cybernetics, pp 1\u201312"},{"key":"7882_CR28","unstructured":"Pang Y, Zhou B, Nie F (2017) Simultaneously learning Neighborship and projection matrix for supervised dimensionality reduction[J]. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"7882_CR29","unstructured":"Paszke A, Chaurasia A, Kim S et al (2016) ENet: a deep neural network architecture for real-time semantic segmentation[J]. arXiv preprint arXiv:1606.02147."},{"key":"7882_CR30","unstructured":"Paszke A, Gross S, Chintala S et al (2017) Automatic differentiation in pytorch [J]"},{"key":"7882_CR31","unstructured":"Ren X, Bo L, Fox D (2012) RGB-(D) scene labeling: features and algorithms[C]. In: Computer vision and pattern recognition (CVPR), 2012 IEEE conference on. IEEE"},{"key":"7882_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation[J]. In International Conference on Medical image computing and computer-assisted intervention Springer, Cham, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"7882_CR33","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE (1986) Learning representations by back-propagating errors[J]. Nature 323:533\u2013536","journal-title":"Nature"},{"issue":"3","key":"7882_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2014","unstructured":"Russakovsky O, Deng J, Su H et al (2014) ImageNet large scale visual recognition challenge[J]. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"7882_CR35","doi-asserted-by":"crossref","unstructured":"Sakkos D, Liu H, Han J et al (2018) End-to-end video background subtraction with 3d convolutional neural networks [J]. Multimedia Tools and Applications 77(17):23023\u201323041","DOI":"10.1007\/s11042-017-5460-9"},{"key":"7882_CR36","doi-asserted-by":"crossref","unstructured":"Silberman N, Fergus R (2011) Indoor scene segmentation using a structured light sensor[C]. In: 2011 IEEE international conference on computer vision workshops (ICCV workshops). IEEE Computer Society, pp 601\u2013608","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"7882_CR37","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P et al (2012) Indoor segmentation and support inference from RGBD images[J]. In European Conference on Computer Vision. Springer, Berlin, Heidelberg, pp 746\u2013760","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"7882_CR38","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition[J]. Computer Science arXiv preprint arXiv:1409.1556"},{"key":"7882_CR39","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg SP, Xiao JSUN (2015) RGB-D: a RGB-D scene understanding benchmark suite[C]. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE","DOI":"10.1109\/CVPR.2015.7298655"},{"issue":"10","key":"7882_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9497-0","volume":"61","author":"H Sun","year":"2018","unstructured":"Sun H, Pang Y (2018) GlanceNets \u2014 efficient convolutional neural networks with adaptive hard example mining[J]. SCIENCE CHINA Inf Sci 61(10):109101","journal-title":"SCIENCE CHINA Inf Sci"},{"key":"7882_CR41","unstructured":"Teichmann MTT, Cipolla R (2018) Convolutional CRFs for semantic segmentation [J]. arXiv preprint arXiv:1805.04777"},{"key":"7882_CR42","unstructured":"Teichmann M, Weber M, Zoellner M et al (2016) MultiNet: real-time joint semantic reasoning for autonomous driving[J]. In 2018 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp 1013\u20131020"},{"key":"7882_CR43","unstructured":"Wang CY, Chen JZ, Li W (2014) Review on superpixel segmentation algorithms. Application research of Computers 31(1):6\u201312"},{"key":"7882_CR44","doi-asserted-by":"crossref","unstructured":"Wu G, Han J, Lin Z et al (2018) Joint image-text hashing for fast large-scale cross-media retrieval using self-supervised deep learning[J]. IEEE Transactions on Industrial Electronics","DOI":"10.1109\/TIE.2018.2873547"},{"issue":"4","key":"7882_CR45","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TIP.2018.2882155","volume":"28","author":"G Wu","year":"2019","unstructured":"Wu G, Han J, Guo Y et al (2019) Unsupervised deep video hashing via balanced code for large-scale video retrieval[J]. IEEE Trans Image Process 28(4):1993\u20132007","journal-title":"IEEE Trans Image Process"},{"key":"7882_CR46","doi-asserted-by":"crossref","unstructured":"Xiao J, Owens A, Torralba A (2013) SUN3D: a database of big spaces reconstructed using SfM and object labels[C]. In: 2013 IEEE international conference on computer vision (ICCV). IEEE Computer Society","DOI":"10.1109\/ICCV.2013.458"},{"issue":"1","key":"7882_CR47","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1109\/TITS.2017.2749965","volume":"19","author":"C Yan","year":"2017","unstructured":"Yan C, Xie H, Yang D et al (2017) Supervised hash coding with deep neural network for environment perception of intelligent vehicles[J]. IEEE Trans Intell Transp Syst 19(1):284\u2013295","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"12","key":"7882_CR48","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1109\/TMM.2018.2838320","volume":"20","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Chen J et al (2018) A fast Uyghur text detector for complex background images[J]. IEEE Transactions on Multimedia 20(12):3389\u20133398","journal-title":"IEEE Transactions on Multimedia"},{"key":"7882_CR49","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv:1511.07122"},{"key":"7882_CR50","unstructured":"Zhao H, Shi J, Qi X et al (2016) Pyramid scene parsing network[J]. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890"},{"key":"7882_CR51","doi-asserted-by":"crossref","unstructured":"Zhao B, Feng J, Wu X et al (2017) A survey on deep learning-based fine-grained object classification and semantic segmentation[J]. International Journal of Automation and Computing 14(2):119\u2013135","DOI":"10.1007\/s11633-017-1053-3"},{"key":"7882_CR52","doi-asserted-by":"crossref","unstructured":"Zheng S, Jayasumana S, Romera-Paredes B et al (2015) Conditional random fields as recurrent neural networks[J]","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07882-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-07882-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07882-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,5]],"date-time":"2020-12-05T19:18:26Z","timestamp":1607195906000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-07882-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,5]]},"references-count":52,"journal-issue":{"issue":"47-48","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["7882"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-07882-w","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,5]]},"assertion":[{"value":"1 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}