{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T19:29:57Z","timestamp":1786908597962,"version":"build-2736575974"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"7-8","license":[{"start":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T00:00:00Z","timestamp":1558396800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T00:00:00Z","timestamp":1558396800000},"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":[[2020,2]]},"DOI":"10.1007\/s11042-019-7684-3","type":"journal-article","created":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T20:21:12Z","timestamp":1558556472000},"page":"4499-4524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["A survey on indoor RGB-D semantic segmentation: from hand-crafted features to deep convolutional neural networks"],"prefix":"10.1007","volume":"79","author":[{"given":"Fahimeh","family":"Fooladgar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3831-0878","authenticated-orcid":false,"given":"Shohreh","family":"Kasaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,21]]},"reference":[{"issue":"11","key":"7684_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta R, Shaji A, Smith K, Lucchi A, Fua P, S\u00fcsstrunk S et al (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274\u20132282","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"7684_CR2","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898\u2013916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR3","unstructured":"Armeni I, Sax S, Zamir AR, Savarese S (2017) Joint 2d-3d-semantic data for indoor scene understanding. arXiv:\n1702.01105"},{"key":"7684_CR4","unstructured":"Badrinarayanan V, Handa A, Cipolla R (2015) Segnet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv:\n1505.07293"},{"issue":"12","key":"7684_CR5","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR6","doi-asserted-by":"crossref","unstructured":"Banica D, Sminchisescu C (2015) Second-order constrained parametric proposals and sequential search-based structured prediction for semantic segmentation in rgb-d images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3517\u20133526","DOI":"10.1109\/CVPR.2015.7298974"},{"key":"7684_CR7","unstructured":"Bo L, Ren X, Fox D (2010) Kernel descriptors for visual recognition. In: Advances in neural information processing systems, pp 244\u2013252"},{"key":"7684_CR8","unstructured":"Cadena C, Ko\u0161ecka J (2013) Semantic parsing for priming object detection in rgb-d scenes. In: 3rd workshop on semantic perception, mapping and exploration. Citeseer"},{"key":"7684_CR9","doi-asserted-by":"crossref","unstructured":"Chang A, Dai A, Funkhouser T, Halber M, Nie\u00dfner M, Savva M, Song S, Zeng A, Zhang Y (2017) Matterport3d: learning from rgb-d data in indoor environments. arXiv:\n1709.06158","DOI":"10.1109\/3DV.2017.00081"},{"key":"7684_CR10","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2015) Semantic image segmentation with deep convolutional nets and fully connected crfs. In: International conference on learning representations"},{"issue":"4","key":"7684_CR11","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR12","doi-asserted-by":"crossref","unstructured":"Cheng Y, Cai R, Li Z, Zhao X, Huang K (2017) Localitysensitive deconvolution networks with gated fusion for rgb-d indoor semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), vol 3","DOI":"10.1109\/CVPR.2017.161"},{"key":"7684_CR13","unstructured":"Couprie C, Farabet C, Najman L, LeCun Y (2013) Indoor semantic segmentation using depth information. arXiv:\n1301.3572"},{"key":"7684_CR14","doi-asserted-by":"crossref","unstructured":"Csurka G, Larlus D, Perronnin F, Meylan F (2013) What is a good evaluation measure for semantic segmentation?. In: BMVC, vol 27. Citeseer","DOI":"10.5244\/C.27.32"},{"key":"7684_CR15","doi-asserted-by":"crossref","unstructured":"Eigen D, Fergus R (2015) Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE international conference on computer vision, pp 2650\u20132658","DOI":"10.1109\/ICCV.2015.304"},{"issue":"8","key":"7684_CR16","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915\u20131929","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR17","doi-asserted-by":"crossref","unstructured":"Firman M (2016) Rgbd datasets: past, present and future. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 19\u201331","DOI":"10.1109\/CVPRW.2016.88"},{"key":"7684_CR18","doi-asserted-by":"crossref","unstructured":"Fooladgar F, Kasaei S (2015) Learning strengths and weaknesses of classifiers for rgb-d semantic segmentation. In: 2015 9th Iranian conference on machine vision and image processing (MVIP). IEEE, pp 176\u2013179","DOI":"10.1109\/IranianMVIP.2015.7397531"},{"key":"7684_CR19","doi-asserted-by":"crossref","unstructured":"Fooladgar F, Kasaei S (2015) Semantic segmentation of rgb-d images using 3d and local neighbouring features. In: 2015 International conference on digital image computing: techniques and applications (DICTA). IEEE, pp 1\u20137","DOI":"10.1109\/DICTA.2015.7371307"},{"key":"7684_CR20","unstructured":"Garcia-Garcia A, Orts-Escolano S, Oprea S, Villena-Martinez V, Garcia-Rodriguez J (2017) A review on deep learning techniques applied to semantic segmentation. arXiv:\n1704.06857"},{"key":"7684_CR21","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"7684_CR22","doi-asserted-by":"crossref","unstructured":"Gupta S, Arbelaez P, Malik J (2013) Perceptual organization and recognition of indoor scenes from rgb-d images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 564\u2013571","DOI":"10.1109\/CVPR.2013.79"},{"key":"7684_CR23","doi-asserted-by":"crossref","unstructured":"Gupta S, Girshick R, Arbel\u00e1ez P, Malik J (2014) Learning rich features from rgb-d images for object detection and segmentation. In: European conference on computer vision. Springer, pp 345\u2013360","DOI":"10.1007\/978-3-319-10584-0_23"},{"issue":"5","key":"7684_CR24","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/TCYB.2013.2265378","volume":"43","author":"J Han","year":"2013","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","journal-title":"IEEE Trans Cybern"},{"key":"7684_CR25","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Girshick R, Malik J (2015) Hypercolumns for object segmentation and fine-grained localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 447\u2013456","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"7684_CR26","unstructured":"Hazirbas C, Ma L, Domokos C, Cremers D (2016) Fusenet: incorporating depth into semantic segmentation via fusion-based cnn architecture. In: Asian conference on computer vision. Springer, pp 213\u2013228"},{"key":"7684_CR27","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7684_CR28","doi-asserted-by":"crossref","unstructured":"Hermans A, Floros G, Leibe B (2014) Dense 3d semantic mapping of indoor scenes from rgb-d images. In: 2014 IEEE international conference on robotics and automation (ICRA). IEEE, pp 2631\u20132638","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"7684_CR29","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, vol 1, p 3","DOI":"10.1109\/CVPR.2017.243"},{"key":"7684_CR30","doi-asserted-by":"crossref","unstructured":"J\u00e9gou S, Drozdzal M, Vazquez D, Romero A, Bengio Y (2017) The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 1175\u20131183","DOI":"10.1109\/CVPRW.2017.156"},{"key":"7684_CR31","unstructured":"Kendall A, Badrinarayanan V, Cipolla R (2015) Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv:\n1511.02680"},{"key":"7684_CR32","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/001","volume-title":"Markov random fields and their applications","author":"R Kindermann","year":"1980","unstructured":"Kindermann R (1980) Markov random fields and their applications. American Mathematical Society, Providence"},{"key":"7684_CR33","unstructured":"Kong S, Fowlkes C (2018) Pixel-wise attentional gating for parsimonious pixel labeling. arXiv:\n1805.01556"},{"key":"7684_CR34","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"issue":"11","key":"7684_CR35","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"7684_CR36","doi-asserted-by":"crossref","unstructured":"Li Z, Gan Y, Liang X, Yu Y, Cheng H, Lin L (2016) Lstm-cf: unifying context modeling and fusion with lstms for rgb-d scene labeling. In: European conference on computer vision. Springer, pp 541\u2013557","DOI":"10.1007\/978-3-319-46475-6_34"},{"key":"7684_CR37","doi-asserted-by":"crossref","unstructured":"Lin D, Chen G, Cohen-Or D, Heng PA, Huang H (2017) Cascaded feature network for semantic segmentation of rgb-d images. In: 2017 IEEE international conference on computer vision (ICCV). IEEE, pp 1320\u20131328","DOI":"10.1109\/ICCV.2017.147"},{"key":"7684_CR38","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) Refinenet: multi-path refinement networks for high-resolution semantic segmentation. In: Cvpr, vol 1, p 5","DOI":"10.1109\/CVPR.2017.549"},{"issue":"6","key":"7684_CR39","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1109\/TPAMI.2017.2708714","volume":"40","author":"G Lin","year":"2018","unstructured":"Lin G, Shen C, Van Den Hengel A, Reid I (2018) Exploring context with deep structured models for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 40(6):1352\u20131366","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR40","unstructured":"Liu W, Rabinovich A, Berg AC (2015) Parsenet: looking wider to see better. arXiv:\n1506.04579"},{"issue":"17","key":"7684_CR41","doi-asserted-by":"publisher","first-page":"22475","DOI":"10.1007\/s11042-018-6056-8","volume":"77","author":"H Liu","year":"2018","unstructured":"Liu H, Wu W, Wang X, Qian Y (2018) RGB-D joint modelling with scene geometric information for indoor semantic segmentation. Multimed Tools Appl 77(17):22475\u201322488","journal-title":"Multimed Tools Appl"},{"key":"7684_CR42","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"7684_CR43","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"J Long","year":"2017","unstructured":"Long J, Shelhamer E, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR44","doi-asserted-by":"crossref","unstructured":"McCormac J, Handa A, Leutenegger S, Davison AJ (2017) Scenenet rgb-d: can 5m synthetic images beat generic imagenet pre-training on indoor segmentation. In: Proceedings of the international conference on computer vision (ICCV), vol 4","DOI":"10.1109\/ICCV.2017.292"},{"key":"7684_CR45","doi-asserted-by":"crossref","unstructured":"M\u00fcller AC, Behnke S (2014) Learning depth-sensitive conditional random fields for semantic segmentation of rgb-d images. In: 2014 IEEE international conference on robotics and automation (ICRA). Citeseer, pp 6232\u20136237","DOI":"10.1109\/ICRA.2014.6907778"},{"key":"7684_CR46","unstructured":"Naseer M, Khan SH, Porikli F (2018) Indoor scene understanding in 2.5\/3d: a survey. arXiv:\n1803.03352"},{"key":"7684_CR47","doi-asserted-by":"crossref","unstructured":"Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1520\u20131528","DOI":"10.1109\/ICCV.2015.178"},{"key":"7684_CR48","unstructured":"Park SJ, Hong KS, Lee S (2017) Rdfnet: Rgb-d multi-level residual feature fusion for indoor semantic segmentation. In: The IEEE international conference on computer vision (ICCV)"},{"key":"7684_CR49","doi-asserted-by":"crossref","unstructured":"Qi X, Liao R, Jia J, Fidler S, Urtasun R (2017) 3d graph neural networks for rgbd semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5199\u20135208","DOI":"10.1109\/ICCV.2017.556"},{"key":"7684_CR50","unstructured":"Ren X, Bo L, Fox D (2012) Rgb-(d) scene labeling: features and algorithms. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2759\u20132766"},{"key":"7684_CR51","doi-asserted-by":"crossref","unstructured":"Reynolds J, Murphy K (2007) Figure-ground segmentation using a hierarchical conditional random field. In: Fourth Canadian conference on computer and robot vision, 2007. CRV\u201907. IEEE, pp 175\u2013182","DOI":"10.1109\/CRV.2007.32"},{"key":"7684_CR52","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"7684_CR53","unstructured":"Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Advances in neural information processing systems, pp 3856\u20133866"},{"issue":"5","key":"7684_CR54","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1109\/TPAMI.2015.2473846","volume":"38","author":"M Seyedhosseini","year":"2016","unstructured":"Seyedhosseini M, Tasdizen T (2016) Semantic image segmentation with contextual hierarchical models. IEEE Trans Pattern Anal Mach Intell 38(5):951","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7684_CR55","doi-asserted-by":"crossref","unstructured":"Shotton J, Winn J, Rother C, Criminisi A (2006) Textonboost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: European conference on computer vision. Springer, pp 1\u201315","DOI":"10.1007\/11744023_1"},{"key":"7684_CR56","doi-asserted-by":"crossref","unstructured":"Silberman N, Fergus R (2011) Indoor scene segmentation using a structured light sensor. In: 2011 IEEE international conference on computer vision workshops (ICCV Workshops). IEEE, pp 601\u2013608","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"7684_CR57","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European conference on computer vision. Springer, pp 746\u2013760","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"7684_CR58","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:\n1409.1556"},{"issue":"6-8","key":"7684_CR59","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1007\/s00371-014-0965-y","volume":"30","author":"X Song","year":"2014","unstructured":"Song X, Zhong F, Wang Y, Qin X (2014) Estimation of kinect depth confidence through self-training. Vis Comput 30(6-8):855\u2013865","journal-title":"Vis Comput"},{"key":"7684_CR60","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) Sun rgb-d: a rgb-d scene understanding benchmark suite. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 567\u2013576","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"7684_CR61","doi-asserted-by":"crossref","unstructured":"Song X, Zheng J, Zhong F, Qin X (2018) Modeling deviations of rgb-d cameras for accurate depth map and color image registration. Multimed Tools Appl, 1\u201327","DOI":"10.1007\/s11042-017-5081-3"},{"issue":"4","key":"7684_CR62","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/s11554-013-0379-5","volume":"10","author":"J St\u00fcckler","year":"2015","unstructured":"St\u00fcckler J., Waldvogel B, Schulz H, Behnke S (2015) Dense real-time mapping of object-class semantics from rgb-d video. J Real-Time Image Proc 10(4):599\u2013609","journal-title":"J Real-Time Image Proc"},{"key":"7684_CR63","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"7684_CR64","doi-asserted-by":"crossref","unstructured":"Wang W, Neumann U (2018) Depth-aware cnn for rgb-d segmentation. arXiv:\n1803.06791","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"7684_CR65","doi-asserted-by":"crossref","unstructured":"Wang J, Wang Z, Tao D, See S, Wang G (2016) Learning common and specific features for rgb-d semantic segmentation with deconvolutional networks. In: European conference on computer vision. Springer, pp 664\u2013679","DOI":"10.1007\/978-3-319-46454-1_40"},{"key":"7684_CR66","unstructured":"Yang MY, Forstner W (2011) A hierarchical conditional random field model for labeling and classifying images of man-made scenes. In: 2011 IEEE international conference on computer vision workshops (ICCV Workshops). IEEE, pp 196\u2013203"},{"issue":"1","key":"7684_CR67","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2011.05.013","volume":"45","author":"D Zhang","year":"2012","unstructured":"Zhang D, Islam MM, Lu G (2012) A review on automatic image annotation techniques. Pattern Recogn 45(1):346\u2013362","journal-title":"Pattern Recogn"},{"key":"7684_CR68","doi-asserted-by":"crossref","unstructured":"Zheng S, Cheng MM, Warrell J, Sturgess P, Vineet V, Rother C, Torr PH (2014) Dense semantic image segmentation with objects and attributes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3214\u20133221","DOI":"10.1109\/CVPR.2014.411"},{"key":"7684_CR69","doi-asserted-by":"crossref","unstructured":"Zheng S, Jayasumana S, Romera-Paredes B, Vineet V, Su Z, Du D, Huang C, Torr PH (2015) Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 1529\u20131537","DOI":"10.1109\/ICCV.2015.179"},{"key":"7684_CR70","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jvcir.2015.10.012","volume":"34","author":"H Zhu","year":"2016","unstructured":"Zhu H, Meng F, Cai J, Lu S (2016) Beyond pixels: a comprehensive survey from bottom-up to semantic image segmentation and cosegmentation. J Vis Commun Image Represent 34:12\u201327","journal-title":"J Vis Commun Image Represent"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7684-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-7684-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-7684-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T23:17:01Z","timestamp":1589930221000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-7684-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,21]]},"references-count":70,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["7684"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-7684-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,21]]},"assertion":[{"value":"31 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}