{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T05:57:54Z","timestamp":1726034274462},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319126098"},{"type":"electronic","value":"9783319126104"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-12610-4_13","type":"book-chapter","created":{"date-parts":[[2014,12,2]],"date-time":"2014-12-02T17:49:27Z","timestamp":1417542567000},"page":"209-224","source":"Crossref","is-referenced-by-count":30,"title":["Unsupervised Learning of Semantics of Object Detections for Scene Categorization"],"prefix":"10.1007","author":[{"given":"Gr\u00e9goire","family":"Mesnil","sequence":"first","affiliation":[]},{"given":"Salah","family":"Rifai","sequence":"additional","affiliation":[]},{"given":"Antoine","family":"Bordes","sequence":"additional","affiliation":[]},{"given":"Xavier","family":"Glorot","sequence":"additional","affiliation":[]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[]},{"given":"Pascal","family":"Vincent","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,11,23]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0893-6080(89)90014-2","volume":"2","author":"P Baldi","year":"1989","unstructured":"Baldi, P., Hornik, K.: Neural networks and principal component analysis: learning from examples without local minima. Neural Netw. 2, 53\u201358 (1989)","journal-title":"Neural Netw."},{"key":"13_CR2","first-page":"153","volume":"19","author":"Y Bengio","year":"2007","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Proc. Sys. 19, 153\u2013160 (2007)","journal-title":"Adv. Neural Inf. Proc. Sys."},{"key":"13_CR3","unstructured":"Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1\u2013127 (2009). Also published as a book. Now Publishers, 2009"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy), June 2010. Oral Presentation","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Mu\u00f1oz, X.: Scene classification via plsa. In: In Proceedings of the ECCV, pp. 517\u2013530 (2006)","DOI":"10.1007\/11744085_40"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR09 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Espinace, P., Kollar, T., Soto, A., Roy, N.: Indoor scene recognition through object detection. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Anchorage, AK (2010)","DOI":"10.1109\/ROBOT.2010.5509682"},{"key":"13_CR8","first-page":"1871","volume":"9","author":"R-E Fan","year":"2008","unstructured":"Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1778\u20131785 (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"13_CR10","unstructured":"Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)\u2014Volume 2\u2014Volume 02, CVPR\u201905, pp. 524\u2013531. IEEE Computer Society (2005)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discrimitatively trained, multiscale, deformable part model. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Gao, S., Tsang, I., Chia, L., Zhao, P.: Local features are not lonely laplacian sparse coding for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5539943"},{"key":"13_CR13","unstructured":"Goodfellow, I., Le, Q., Saxe, A., Ng, A.: Measuring invariances in deep networks. In: NIPS\u201909, pp. 646\u2013654 (2009)"},{"key":"13_CR14","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn. 42, 177\u2013196 (2001)","journal-title":"Mach. Learn."},{"issue":"3","key":"13_CR16","first-page":"577584","volume":"24","author":"D Hoiem","year":"2005","unstructured":"Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. SIGGRAPH 24(3), 577584 (2005)","journal-title":"SIGGRAPH"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Hotelling, H.: Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24, 417\u2013441, 498\u2013520 (1933)","DOI":"10.1037\/h0070888"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition?. In: Proceedings of the International Conference on Computer Vision (ICCV\u201909), pp. 2146\u20132153. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Kavukcuoglu, K., Ranzato, M., Fergus, R., LeCun, Y.: Learning invariant features through topographic filter maps. In: Proceedings of the CVPR\u201909, pp. 1605\u20131612. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206545"},{"key":"13_CR20","first-page":"1","volume":"10","author":"H Larochelle","year":"2009","unstructured":"Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. JMLR 10, 1\u201340 (2009)","journal-title":"JMLR"},{"key":"13_CR21","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition (2006)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Haffner, P., Bottou, L., Bengio, Y.: Object recognition with gradient-based learning. In: Shape, Contour and Grouping in Computer Vision, pp. 319\u2013345. Springer (1999)","DOI":"10.1007\/3-540-46805-6_19"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Li, L.-J., Fei-Fei, L.: What, where and who? classifying events by scene and object recognition. In: ICCV (2007)","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"13_CR24","unstructured":"Li-Jia Li, E.P.X., Su, H., Fei-Fei, L.: Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: Proceedings of the Neural Information Processing Systems (NIPS) (2010)"},{"key":"13_CR25","unstructured":"Li-Jia Li, Y.L., Su, H., Fei-Fei, L.: Objects as attributes for scene classification. In: European Conference of Computer Vision (ECCV), International Workshop on Parts and Attributes, Crete, Greece, September 2010"},{"key":"13_CR26","unstructured":"Mesnil, G., Dauphin, Y., Glorot, X., Rifai, S., Bengio, Y., Goodfellow, I., Lavoie, E., Muller, X., Desjardins, G., Warde-Farley, D., Vincent, P., Courville, A., Bergstra, J.: Unsupervised and transfer learning challenge: a deep learning approach. In: Guyon I., Dror, G., Lemaire, V., Taylor, G., Silver, D. (Eds.) JMLR W & CP: Proceedings of the Unsupervised and Transfer Learning challenge and workshop, vol. 27, pp. 97\u2013110 (2012)"},{"issue":"11","key":"13_CR27","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for english. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. In: Visual Perception, Progress in Brain Research, vol. 155 (2006)","DOI":"10.1016\/S0079-6123(06)55002-2"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based models. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126383"},{"issue":"6","key":"13_CR30","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","volume":"2","author":"K Pearson","year":"1901","unstructured":"Pearson, K.: On lines and planes of closest fit to systems of points in space. Phil. Mag. 2(6), 559\u2013572 (1901)","journal-title":"Phil. Mag."},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A., Recognizing indoor scenes. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Ranzato, M., Poultney, C., Chopra, S., LeCun, Y.: Efficient learning of sparse representations with an energy-based model. In: NIPS\u201906 (2007)","DOI":"10.7551\/mitpress\/7503.003.0147"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Rifai, S., Mesnil, G., Vincent, P., Muller, X., Bengio, Y., Dauphin, Y., Glorot, X.: Higher order contractive auto-encoder. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) (2011)","DOI":"10.1007\/978-3-642-23783-6_41"},{"key":"13_CR34","unstructured":"Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contracting auto-encoders: explicit invariance during feature extraction. In: Proceedings of the Twenty-eight International Conference on Machine Learning (ICML\u201911), June 2011"},{"key":"13_CR35","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. Int. J. Comput. Vision 77, 157\u2013173 (2008)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)","DOI":"10.21236\/ADA454604"},{"key":"13_CR37","unstructured":"Smeulders, A.W.M., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1349\u20131380 (2000)"},{"issue":"2","key":"13_CR38","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1023\/A:1023052124951","volume":"53","author":"A Torralba","year":"2003","unstructured":"Torralba, A.: Contextual priming for object detection. Int. J. Comput. Vis. 53(2), 169\u2013191 (2003)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A.: Extracting and composing robust features with denoising autoencoders. In: Cohen W.W., McCallum A., Roweis, S.T. (eds.) ICML\u201908, pp. 1096\u20131103. ACM (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Vogel, J., Schiele, B.: Natural scene retrieval based on a semantic modeling step. In: Proceeedings of the International Conference on Image and Video Retrieval CIVR 2004, Dublin, Ireland, LNCS, vol. 3115, pp. 7 (2004)","DOI":"10.1007\/978-3-540-27814-6_27"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: SUN database: large-scale scene recognition from abbey to zoo. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3485\u20133492. IEEE, June 2010","DOI":"10.1109\/CVPR.2010.5539970"}],"container-title":["Advances in Intelligent Systems and Computing","Pattern Recognition Applications and Methods"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-12610-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T11:30:46Z","timestamp":1690716646000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-12610-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,11,23]]},"ISBN":["9783319126098","9783319126104"],"references-count":41,"URL":"http:\/\/dx.doi.org\/10.1007\/978-3-319-12610-4_13","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2014,11,23]]}}}
