{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:49:01Z","timestamp":1761896941710,"version":"3.40.3"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030114787"},{"type":"electronic","value":"9783030114794"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-11479-4_2","type":"book-chapter","created":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T14:03:33Z","timestamp":1551103413000},"page":"21-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deep Learning for Scene Understanding"],"prefix":"10.1007","author":[{"given":"Uzair","family":"Nadeem","sequence":"first","affiliation":[]},{"given":"Syed Afaq Ali","family":"Shah","sequence":"additional","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,26]]},"reference":[{"issue":"5","key":"2_CR1","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/34.765655","volume":"21","author":"AE Johnson","year":"1999","unstructured":"A.E. Johnson, M. Hebert, Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 433\u2013449 (1999)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"D.G. Lowe, Object recognition from local scale-invariant features, in The proceedings of the IEEE International Conference on Computer Vision (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"issue":"8","key":"2_CR3","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1016\/0031-3203(90)90135-8","volume":"23","author":"L Wang","year":"1990","unstructured":"L. Wang, D.-C. He, Texture classification using texture spectrum. Pattern Recognit. 23(8), 905\u2013910 (1990)","journal-title":"Pattern Recognit."},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/978-3-642-15558-1_26","volume-title":"Computer Vision \u2013 ECCV 2010","author":"Federico Tombari","year":"2010","unstructured":"F. Tombari, S. Salti, L. Di Stefano, Unique signatures of histograms for local surface description, in European Conference on Computer Vision (Berlin, Heidelberg, 2010)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"S.A.A. Shah, M. Bennamoun, F. Boussaid, Performance evaluation of 3D local surface descriptors for low and high resolution range image registration, in International Conference on Digital lmage Computing: Techniques and Applications (2014)","DOI":"10.1109\/DICTA.2014.7008123"},{"key":"2_CR6","unstructured":"Y. Guo, F.A. Sohel, M. Bennamoun, J. Wan, M. Lu, RoPS: a local feature descriptor for 3D rigid objects based on rotational projection statistics, in International Conference on Communications, Signal Processing, and Their Applications (2013)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"L. Bo, X. Ren, D. Fox, Depth kernel descriptors for object recognition, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (2011)","DOI":"10.1109\/IROS.2011.6095119"},{"issue":"11","key":"2_CR8","doi-asserted-by":"publisher","first-page":"2270","DOI":"10.1109\/TPAMI.2014.2316828","volume":"36","author":"Y Guo","year":"2014","unstructured":"Y. Guo, M. Bennamoun, F. Sohel, M. Lu, J. Wan, 3D object recognition in cluttered scenes with local surface features: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2270\u20132287 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.1017\/atsip.2013.9","volume":"3","author":"L Deng","year":"2014","unstructured":"L. Deng, A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Trans. Signal Inf. Process. 3, e2 (2014)","journal-title":"APSIPA Trans. Signal Inf. Process."},{"issue":"4","key":"2_CR10","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TPAMI.2014.2353635","volume":"37","author":"M Hayat","year":"2015","unstructured":"M. Hayat, M. Bennamoun, S. An, Deep reconstruction models for image set classification. IEEE Trans. Pattern Anal. Mach. Intell. 37(4), 713\u2013727 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1016\/j.neucom.2015.10.004","volume":"174","author":"SAA Shah","year":"2016","unstructured":"S.A.A. Shah, M. Bennamoun, F. Boussaid, Iterative deep learning for image set based face and object recognition. Neurocomputing 174, 866\u2013874 (2016)","journal-title":"Neurocomputing"},{"key":"2_CR12","unstructured":"A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov et al., Going deeper with convolutions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR15","unstructured":"C.R. Qi, H. Su, K. Mo, L.J. Guibas, PointNet: deep learning on point sets for 3D classification and segmentation. \n                  arXiv:1612.00593\n                  \n                 (2016)"},{"issue":"2","key":"2_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"P. Viola, M.J. Jones, Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"F.R.M. Al-Osaimi, M. Bennamoun, 3D face surface analysis and recognition based on facial surface features, in 3D Face Modeling, Analysis and Recognition (Wiley, 2013), pp. 39\u201376","DOI":"10.1002\/9781118592656.ch2"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Y. Taigman, M. Yang, M. Ranzato, L. Wolf, Deepface: closing the gap to human-level performance in face verification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"E.G. Ortiz, A. Wright, M. Shah, Face recognition in movie trailers via mean sequence sparse representation-based classification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/CVPR.2013.453"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"S.A.A. Shah, U. Nadeem, M. Bennamoun, F. Sohel, R. Togneri, Efficient image set classification using linear regression based image reconstruction, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2017)","DOI":"10.1109\/CVPRW.2017.88"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"H. Li, Z. Lin, X. Shen, J. Brandt, G. Hua, A convolutional neural network cascade for face detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"J. Lu, G. Wang, W. Deng, P. Moulin, J. Zhou, Multi-manifold deep metric learning for image set classification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298717"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"F. Schroff, D. Kalenichenko, J. Philbin, FaceNet: a unified embedding for face recognition and clustering, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"D. Karatzas, L. Gomez-Bigorda, A. Nicolaou, S. Ghosh, A. Bagdanov, M. Iwamura et al., ICDAR 2015 competition on robust reading, in 13th International Conference on Document Analysis and Recognition (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"issue":"7","key":"2_CR25","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Q. Ye, D. Doermann, Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"M. Jaderberg, K. Simonyan, A. Vedaldi, A. Zisserman, Reading text in the wild with convolutional neural networks. Int. J. Comput. Vis. 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR27","unstructured":"T. Wang, D.J. Wu, A. Coates, A.Y. Ng, End-to-end text recognition with convolutional neural networks, in 21st International Conference on Pattern Recognition (2012)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"B. Epshtein, E. Ofek, Y. Wexler, Detecting text in natural scenes with stroke width transform, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"B. Epshtein, E. Ofek, Y. Wexler, Detecting text in natural scenes with stroke width transform, in Proceedings of the IEEE Conference IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"H. Chen, S.S. Tsai, G. Schroth, D.M. Chen, R. Grzeszczuk, B. Girod, Robust text detection in natural images with edge-enhanced maximally stable extremal regions, in 18th IEEE International Conference on Image Processing (2011)","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"L. Neumann, J. Matas, Real-time scene text localization and recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"L. Neumann, J. Matas, Scene text localization and recognition with oriented stroke detection, in Proceedings of the IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.19"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Q. Zhu, M.-C. Yeh, K.-T. Cheng, Multimodal fusion using learned text concepts for image categorization, in Proceedings of the 14th ACM International Conference on Multimedia (2006)","DOI":"10.1145\/1180639.1180698"},{"key":"2_CR34","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-642-33885-4_46","volume-title":"Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations","author":"Sezer Karaoglu","year":"2012","unstructured":"S. Karaoglu, J.C. Van Gemert, T. Gevers, Object reading: text recognition for object recognition, in European Conference on Computer Vision (ECCV) (2012)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Z. Zhang, C. Zhang, W. Shen, C. Yao, W. Liu, X. Bai, Multi-oriented text detection with fully convolutional networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.451"},{"key":"2_CR36","unstructured":"D. Eigen, C. Puhrsch, R. Fergus, Depth map prediction from a single image using a multi-scale deep network, in Advances in Neural Information Processing Systems (2014)"},{"issue":"1\u20133","key":"2_CR37","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D Scharstein","year":"2002","unstructured":"D. Scharstein, R. Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47(1\u20133), 7\u201342 (2002)","journal-title":"Int. J. Comput. Vis."},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"S. Mattoccia, S. Giardino, A. Gambini, Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering, in Asian Conference on Computer Vision (2010)","DOI":"10.1007\/978-3-642-12304-7_35"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"R.A. Hamzah, H. Ibrahim, Literature survey on stereo vision disparity map algorithms. J. Sens. (2015)","DOI":"10.1155\/2016\/8742920"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Y. Li, D.P. Huttenlocher, Learning for stereo vision using the structured support vector machine, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2008)","DOI":"10.1109\/CVPR.2008.4587699"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"A. Spyropoulos, N. Komodakis, P. Mordohai, Learning to detect ground control points for improving the accuracy of stereo matching, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.210"},{"issue":"5","key":"2_CR42","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"A. Saxena, M. Sun, A.Y. Ng, Make3D: learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell. 31(5), 824\u2013840 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"K. Karsch, C. Liu, S.B. Kang, Depth extraction from video using non-parametric sampling, in European Conference on Computer Vision (2012)","DOI":"10.1007\/978-3-642-33715-4_56"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"L. Ladicky, J. Shi, M. Pollefeys, Pulling things out of perspective, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.19"},{"issue":"2","key":"2_CR45","first-page":"1","volume":"17","author":"J Zbontar","year":"2016","unstructured":"J. Zbontar, Y. LeCun, Stereo matching by training a convolutional neural network to compare image patches. J. Mach. Learn. Res. 17(2), 1\u201332 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"D. Eigen, R. Fergus, Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture, in Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"S.N. Parizi, J.G. Oberlin, P.F. Felzenszwalb, Reconfigurable models for scene recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248001"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"D. Lin, C. Lu, R. Liao, J. Jia, Learning important spatial pooling regions for scene classification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.476"},{"key":"2_CR49","unstructured":"B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, A. Oliva, Learning deep features for scene recognition using places database, in Advances in Neural Information Processing Systems (2014)"},{"issue":"10","key":"2_CR50","doi-asserted-by":"publisher","first-page":"4829","DOI":"10.1109\/TIP.2016.2599292","volume":"25","author":"M Hayat","year":"2016","unstructured":"M. Hayat, S.H. Khan, M. Bennamoun, S. An, A spatial layout and scale invariant feature representation for indoor scene classification. IEEE Trans. Image Process. 25(10), 4829\u20134841 (2016)","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"2_CR51","doi-asserted-by":"publisher","first-page":"3372","DOI":"10.1109\/TIP.2016.2567076","volume":"25","author":"SH Khan","year":"2016","unstructured":"S.H. Khan, M. Hayat, M. Bennamoun, R. Togneri, F.A. Sohel, A discriminative representation of convolutional features for indoor scene recognition. IEEE Trans. Image Process. 25(7), 3372\u20133383 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"L. Herranz, S. Jiang, X. Li, Scene recognition with CNNs: objects, scales and dataset bias, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.68"},{"key":"2_CR53","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"R. Bernardi, R. Cakici, D. Elliott, A. Erdem, E.I.-C.N. Erdem, F. Keller, A. Muscat, B. Plank, Automatic description generation from images: a survey of models, datasets, and evaluation measures. J. Artif. Intell. Res. 55, 409\u2013442 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"O. Vinyals, A. Toshev, S. Bengio, D. Erhan, Show and tell: a neural image caption generator, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"X. Jia, E. Gavves, B. Fernando, T. Tuytelaars, Guiding the long-short term memory model for image caption generation, in Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.277"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"X. Chen, C. Lawrence Zitnick, Mind\u2019s eye: a recurrent visual representation for image caption generation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"L. Anne Hendricks, S. Venugopalan, M. Rohrbach, R. Mooney, K. Saenko, T. Darrell, Deep compositional captioning: describing novel object categories without paired training data, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.8"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"K. Kafle, C. Kanan, Visual question answering: datasets, algorithms, and future challenges. \n                  arXiv:1610.01465\n                  \n                 (2016)","DOI":"10.1109\/ICCV.2017.217"},{"key":"2_CR59","doi-asserted-by":"crossref","unstructured":"S. Antol, A. Agrawal, J. Lu, M. Mitchell, D. Batra, C. Lawrence Zitnick, D. Parikh, VQA: visual question answering, in Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"2_CR60","unstructured":"H. Gao, J. Mao, J. Zhou, Z. Huang, L. Wang, W. Xu, Are you talking to a machine? Dataset and methods for multilingual image question, in Advances in Neural Information Processing Systems (2015)"},{"key":"2_CR61","unstructured":"D. Harris, S. Harris, Digital Design and Computer Architecture (Morgan Kaufmann, 2010), p. 129"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Q. Wu, C. Shen, P. Wang, A. Dick, A. van den Hengel, Image captioning and visual question answering based on attributes and external knowledge, in IEEE Transactions on Pattern Analysis and Machine Intelligence (2017)","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"2_CR63","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Nathan Silberman","year":"2012","unstructured":"N. Silberman, D. Hoiem, P. Kohli, R. Fergus, Indoor segmentation and support inference from RGBD images, in European Conference on Computer Vision (ECCV) (2012)"},{"key":"2_CR64","doi-asserted-by":"crossref","unstructured":"C. Ye, Y. Yang, C. Fermuller, Y. Aloimonos, What can I do around here? Deep functional scene understanding for cognitive robots. \n                  arXiv:1602.00032\n                  \n                 (2016)","DOI":"10.1109\/ICRA.2017.7989535"},{"key":"2_CR65","unstructured":"G. Heitz, S. Gould, A. Saxena, D. Koller, Cascaded classification models: combining models for holistic scene understanding, in Advances in Neural Information Processing Systems (2009)"},{"key":"2_CR66","unstructured":"C. Li, A. Kowdle, A. Saxena, T. Chen, Towards holistic scene understanding: feedback enabled cascaded classification models, in Advances in Neural Information Processing Systems (2010)"},{"key":"2_CR67","unstructured":"J. Yao, S. Fidler, R. Urtasun, Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)"},{"issue":"3","key":"2_CR68","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1109\/TPAMI.2015.2462355","volume":"38","author":"Salman H. Khan","year":"2016","unstructured":"S. H. Khan, B Mohammed, F. Sohel, R. Togneri, Automatic shadow detection and removal from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 431\u2013446 (2016)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2_CR69","doi-asserted-by":"crossref","unstructured":"U. Asif, M. Bennamoun, F. Sohel, Simultaneous dense scene reconstruction and object labeling, in IEEE International Conference on Robotics and Automation (ICRA) (2016)","DOI":"10.1109\/ICRA.2016.7487374"},{"key":"2_CR70","doi-asserted-by":"crossref","unstructured":"U. Asif, M. Bennamoun, F.A. Sohel, RGB-D object recognition and grasp detection using hierarchical cascaded forests. IEEE Trans. Robot. (2017)","DOI":"10.1109\/TRO.2016.2638453"},{"issue":"4","key":"2_CR71","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s10032-011-0170-8","volume":"15","author":"R Jayadevan","year":"2012","unstructured":"R. Jayadevan, S.R. Kolhe, P.M. Patil, U. Pal, Automatic processing of handwritten bank cheque images: a survey. Int. J. Doc. Anal. Recognit. (IJDAR) 15(4), 267\u2013296 (2012)","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"2_CR72","unstructured":"G. Dreyfus, Neural Networks: Methodology and Applications (Springer Science & Business Media, 2005)"}],"container-title":["Smart Innovation, Systems and Technologies","Handbook of Deep Learning Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11479-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T08:15:44Z","timestamp":1557994544000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-11479-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030114787","9783030114794"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11479-4_2","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}