{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:22:13Z","timestamp":1790727733551,"version":"4.1.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T00:00:00Z","timestamp":1530748800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T00:00:00Z","timestamp":1530748800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["Australian Research Council (ARC) Discovery Project DP160101458"],"award-info":[{"award-number":["Australian Research Council (ARC) Discovery Project DP160101458"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10514-018-9776-8","type":"journal-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T16:34:08Z","timestamp":1530808448000},"page":"1005-1022","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Viewpoint invariant semantic object and scene categorization with RGB-D sensors"],"prefix":"10.1007","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-4355","authenticated-orcid":false,"given":"Hasan F. M.","family":"Zaki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faisal","family":"Shafait","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,7,5]]},"reference":[{"issue":"5","key":"9776_CR1","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1109\/TRO.2008.2004514","volume":"24","author":"A Angeli","year":"2008","unstructured":"Angeli, A., Filliat, D., Doncieux, S., & Meyer, J. A. (2008). Fast and incremental method for loop-closure detection using bags of visual words. IEEE Transactions on Robotics, 24(5), 1027\u20131037.","journal-title":"IEEE Transactions on Robotics"},{"key":"9776_CR2","doi-asserted-by":"crossref","unstructured":"Asif, U., Bennamoun, M., & Sohel, F. (2015). Discriminative feature learning for efficient rgb-d object recognition. In IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2015 (pp. 272\u2013279). IEEE.","DOI":"10.1109\/IROS.2015.7353385"},{"key":"9776_CR3","doi-asserted-by":"crossref","unstructured":"Asif, U., Bennamoun, M., & Sohel, F. (2015). Efficient RGB-D object categorization using cascaded ensembles of randomized decision trees. In Proceedings of ICRA, (pp. 1295\u20131302).","DOI":"10.1109\/ICRA.2015.7139358"},{"issue":"9","key":"9776_CR4","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1109\/TPAMI.2015.2500224","volume":"38","author":"H Azizpour","year":"2016","unstructured":"Azizpour, H., Razavian, A. S., Sullivan, J., Maki, A., & Carlsson, S. (2016). Factors of transferability for a generic convnet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(9), 1790\u20131802. \n                    https:\/\/doi.org\/10.1109\/TPAMI.2015.2500224\n                    \n                  .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9776_CR5","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.neucom.2015.03.017","volume":"165","author":"J Bai","year":"2015","unstructured":"Bai, J., Wu, Y., Zhang, J., & Chen, F. (2015). Subset based deep learning for RGB-D object recognition. Neurocomputing, 165, 280\u2013292.","journal-title":"Neurocomputing"},{"issue":"1","key":"9776_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio, Y. (2009). Learning deep architectures for AI. Foundations and Trends\u00ae in Machine Learning, 2(1), 1\u2013127.","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"9776_CR7","first-page":"153","volume":"19","author":"Y Bengio","year":"2007","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007). Greedy layer-wise training of deep networks. Advances in Neural Information Processing Systems, 19, 153.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"9776_CR8","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE PAMI, 35(8), 1798\u20131828.","journal-title":"IEEE PAMI"},{"key":"9776_CR9","doi-asserted-by":"crossref","unstructured":"Blum, M., Springenberg, J.T., Wulfing, J., & Riedmiller, M. (2012). A learned feature descriptor for object recognition in RGB-D data. In Proceedings of ICRA (pp. 1298\u20131303).","DOI":"10.1109\/ICRA.2012.6225188"},{"key":"9776_CR10","doi-asserted-by":"crossref","unstructured":"Bo, L., Ren, X., & Fox, D. (2011). Depth kernel descriptors for object recognition. In Proceedings of IROS (pp. 821\u2013826).","DOI":"10.1109\/IROS.2011.6095119"},{"key":"9776_CR11","unstructured":"Bo, L., Ren, X., & Fox, D. (2012). Unsupervised feature learning for rgb-d based object recognition. In Proceedings of ISER."},{"key":"9776_CR12","doi-asserted-by":"crossref","unstructured":"Browatzki, B., Fischer, J., Graf, B., Bulthoff, H., & Wallraven, C. (2011). Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset. In IEEE international conference on computer vision workshops (ICCVW) (pp. 1189\u20131195).","DOI":"10.1109\/ICCVW.2011.6130385"},{"key":"9776_CR13","unstructured":"Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Return of the devil in the details: Delving deep into convolutional nets. In Proceedings of BMVC. arXiv preprint \n                    arXiv:1405.3531\n                    \n                  ."},{"key":"9776_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Zhao, X., Huang, K., & Tan, T. (2014). Semi-supervised learning for RGB-D object recognition. In Proceedings of ICPR (pp. 2377\u20132382).","DOI":"10.1109\/ICPR.2014.412"},{"key":"9776_CR15","unstructured":"Coates, A., Ng, A., & Lee, H. (2011). An analysis of single-layer networks in unsupervised feature learning. In Proceedings of AISTATS (pp. 215\u2013223)."},{"key":"9776_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition, 2009, CVPR 2009 (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9776_CR17","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 Proceedings of ECCV (pp. 345\u2013360).","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"9776_CR18","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 CVPR.","DOI":"10.1109\/CVPR.2015.7298642"},{"issue":"9","key":"9776_CR19","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), 1904\u20131916.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"9776_CR20","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"G Hinton","year":"2006","unstructured":"Hinton, G., Osindero, S., & Teh, Y. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527\u20131554.","journal-title":"Neural Computation"},{"key":"9776_CR21","unstructured":"Hinton, G.E. (2012). A practical guide to training restricted boltzmann machines. In Neural networks: Tricks of the trade (pp. 599\u2013619). Springer."},{"issue":"1","key":"9776_CR22","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1), 489\u2013501.","journal-title":"Neurocomputing"},{"issue":"2","key":"9776_CR23","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","volume":"42","author":"GB Huang","year":"2012","unstructured":"Huang, G. B., Zhou, H., Ding, X., & Zhang, R. (2012). Extreme learning machine for regression and multiclass classification. IEEE Trans on Systems, Man, and Cybernetics, Part B: Cybernetics, 42(2), 513\u2013529.","journal-title":"IEEE Trans on Systems, Man, and Cybernetics, Part B: Cybernetics"},{"key":"9776_CR24","unstructured":"Jhuo, I.H., Gao, S., Zhuang, L., Lee, D., & Ma, Y. (2014). Unsupervised feature learning for RGB-D image classification. In Proceedings of ACCV (pp. 276\u2013289)."},{"key":"9776_CR25","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In Proceedings of NIPS (pp. 1097\u20131105)."},{"key":"9776_CR26","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., & Fox, D. (2011). A large-scale hierarchical multi-view RGB-D object dataset. In Proceedings of ICRA (pp. 1817\u20131824).","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"9776_CR27","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In proceedings of CVPR (Vol. 2, pp. 2169\u20132178).","DOI":"10.1109\/CVPR.2006.68"},{"key":"9776_CR28","unstructured":"Le, Q.V., Karpenko, A., Ngiam, J., & Ng, A.Y. (2011). Ica with reconstruction cost for efficient overcomplete feature learning. In Advances in neural information processing systems (pp. 1017\u20131025)."},{"key":"9776_CR29","unstructured":"Liao, Y., Kodagoda, S., Wang, Y., Shi, L., & Liu, Y. (2016). Understand scene categories by objects: A semantic regularized scene classifier using convolutional neural networks. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 2318\u20132325). IEEE."},{"key":"9776_CR30","doi-asserted-by":"crossref","unstructured":"Liu, L., Shen, C., & van den Hengel, A. (2015). The treasure beneath convolutional layers: Cross convolutional layer pooling for image classification. In Proceedings of CVPR.","DOI":"10.1109\/CVPR.2015.7299107"},{"key":"9776_CR31","unstructured":"Liu, W., Ji, R., & Li, S. (2015). Towards 3D object detection with bimodal deep boltzmann machines over RGBD imagery. In Proceedings of CVPR."},{"issue":"2","key":"9776_CR32","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"9776_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRO.2015.2496823","volume":"32","author":"S Lowry","year":"2016","unstructured":"Lowry, S., Snderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., et al. (2016). Visual place recognition: A survey. IEEE Transactions on Robotics, 32(1), 1\u201319. \n                    https:\/\/doi.org\/10.1109\/TRO.2015.2496823\n                    \n                  .","journal-title":"IEEE Transactions on Robotics"},{"issue":"6","key":"9776_CR34","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1145\/360825.360839","volume":"18","author":"BT Phong","year":"1975","unstructured":"Phong, B. T. (1975). Illumination for computer generated pictures. Communications of the ACM, 18(6), 311\u2013317.","journal-title":"Communications of the ACM"},{"key":"9776_CR35","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014). CNN features off-the-shelf: An astounding baseline for recognition. In Proceedings of computer vision and pattern recognition workshops (CVPRW) (pp. 512\u2013519).","DOI":"10.1109\/CVPRW.2014.131"},{"key":"9776_CR36","doi-asserted-by":"crossref","unstructured":"Schwarz, M., Schulz, H., & Behnke, S. (2015). RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features. In Proceedings of ICRA.","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"9776_CR37","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) (pp. 601\u2013608). IEEE","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"9776_CR38","unstructured":"Socher, R., Huval, B., Bath, B., Manning, C.D., & Ng, A. (2012). Convolutional-recursive deep learning for 3D object classification. In Proceedings of NIPS (pp. 665\u2013673)."},{"key":"9776_CR39","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., & Xiao, J. (2015). Sun rgb-d: A rgb-d scene understanding benchmark suite. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 567\u2013576).","DOI":"10.1109\/CVPR.2015.7298655"},{"issue":"1","key":"9776_CR40","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929\u20131958.","journal-title":"The Journal of Machine Learning Research"},{"key":"9776_CR41","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., & Learned-Miller, E. (2015). Multi-view convolutional neural networks for 3d shape recognition. In Proceedings of the IEEE international conference on computer vision (pp. 945\u2013953).","DOI":"10.1109\/ICCV.2015.114"},{"key":"9776_CR42","doi-asserted-by":"crossref","unstructured":"Torralba, A., Murphy, K.P., Freeman, W.T., & Rubin, M.A. (2003). Context-based vision system for place and object recognition. In Proceedings of ninth IEEE international conference on Computer vision, 2003 (pp. 273\u2013280). IEEE.","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"9776_CR43","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1109\/TIP.2015.2393057","volume":"24","author":"M Uzair","year":"2015","unstructured":"Uzair, M., Mahmood, A., & Mian, A. (2015). Hyperspectral face recognition with spatiospectral information fusion and pls regression. IEEE Transactions on Image Processing, 24, 1127\u20131137. \n                    https:\/\/doi.org\/10.1109\/TIP.2015.2393057\n                    \n                  .","journal-title":"IEEE Transactions on Image Processing"},{"key":"9776_CR44","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., & Fulkerson, B. (2010). Vlfeat: An open and portable library of computer vision algorithms. In Proceedings of the international conference on multimedia (pp. 1469\u20131472). ACM.","DOI":"10.1145\/1873951.1874249"},{"key":"9776_CR45","unstructured":"Vedaldi, A., & Lenc, K. (2014). Matconvnet-convolutional neural networks for matlab. arXiv preprint \n                    arXiv:1412.4564\n                    \n                  ."},{"issue":"3","key":"9776_CR46","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1145\/566654.566576","volume":"21","author":"T Welsh","year":"2002","unstructured":"Welsh, T., Ashikhmin, M., & Mueller, K. (2002). Transferring color to greyscale images. ACM Transactions on Graphics, 21(3), 277\u2013280. \n                    https:\/\/doi.org\/10.1145\/566654.566576\n                    \n                  .","journal-title":"ACM Transactions on Graphics"},{"key":"9776_CR47","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015). 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1912\u20131920)."},{"key":"9776_CR48","doi-asserted-by":"crossref","unstructured":"Yang, J., Yu, K., Gong, Y., & Huang, T. (2009). Linear spatial pyramid matching using sparse coding for image classification. In IEEE conference on computer vision and pattern recognition, 2009, CVPR 2009 (pp. 1794\u20131801). IEEE","DOI":"10.1109\/CVPR.2009.5206757"},{"key":"9776_CR49","doi-asserted-by":"crossref","unstructured":"Yang, S., & Ramanan, D. (2015). Multi-scale recognition with DAG-CNNS. In Proceedings of the IEEE international conference on computer vision (pp. 1215\u20131223).","DOI":"10.1109\/ICCV.2015.144"},{"key":"9776_CR50","doi-asserted-by":"publisher","unstructured":"Zaki, H.F., Shafait, F., & Mian, A. (2015). Localized deep extreme learning machines for efficient RGB-D object recognition. In Proceedings of digital image computing: Techniques and applications (DICTA) (pp. 1\u20138). \n                    https:\/\/doi.org\/10.1109\/DICTA.2015.7371280\n                    \n                  .","DOI":"10.1109\/DICTA.2015.7371280"},{"key":"9776_CR51","doi-asserted-by":"crossref","unstructured":"Zaki, H.F.M., Shafait, F., & Mian, A. (2016). Convolutional hypercube pyramid for accurate RGB-D object category and instance recognition. In Proceedings of ICRA (to appear).","DOI":"10.1109\/ICRA.2016.7487310"},{"key":"9776_CR52","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer vision\u2014ECCV 2014 (pp. 818\u2013833). Springer.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"9776_CR53","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., & Oliva, A. (2014). Learning deep features for scene recognition using places database. In Proceedings of NIPS (pp. 487\u2013495)."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-018-9776-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-018-9776-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-018-9776-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T08:32:17Z","timestamp":1589704337000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-018-9776-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,5]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["9776"],"URL":"https:\/\/doi.org\/10.1007\/s10514-018-9776-8","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,5]]},"assertion":[{"value":"28 November 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}