图像分类中的判别性增强研究
|
摘要
数字图像的智能分析与理解是当前多媒体研究领域的热点和难点问题,图像分类是数字图像分析与理解中的一项最基本也是最重要的研究内容。图像分类根据图像的语义特点将图像划分为不同种类。它首先使用计算机视觉技术抽取图像的视觉特征作为图像的表达,然后借助机器学习的方法对图像进行分类。对图像分类的研究可以促进网络图像检索、智能视频监控、生物特征识别等众多实际应用的发展。
虽然图像分类具有广阔的应用前景,但是当前对图像分类的研究还远远不能满足实际应用的需要,这是因为在图像分类中存在底层视觉描述与高层人类感知之间的语义鸿沟。在这个开放性的问题中起到关键作用的是分类系统判别能力的强弱。因此,本论文围绕图像分类中的判别性增强,开展了以下系统性的研究工作,取得了相关的研究成果：
1)通过归纳总结当前最优秀的底层特征编码方法,提出使用图像表达中的两个基本元素——底层特征与视觉词包之间的关系来进行底层特征编码。考虑到底层特征与视觉词包的特性,本论文使用直接加性核映射的方式将它们分别映射到一个高维空间中,在该空间中使用向量差的方式描述底层特征与视觉词包之间的关系。本论文提出的方法更具一般性。研究结果表明,最后得到的底层特征编码响应与传统方法相比具有更强的判别性。在公开数据库上的图像分类的性能得到了提升。
2)指出现有图像表达方法中存在的两个关键的局限性。为了降低图像可变性对分类性能的影响,本论文提出基于可变性分析对影响图像分类性能的潜在因子进行建模。同时,为了增强图像表达的判别性,本论文提出了一种判别式的图像表达框架,该框架基于偏最小二乘方法,将每幅图像表达成一个低维的特征向量。这极大地减轻了分类器的训练和特征的存储的负担。由于该框架结合了图像的类别标签,因此最终的图像表达在不同类别之间具有较强的判别性。在主流公开数据库上的实验结果验证了本论文方法的有效性。
3)提出了一种在线判别式的参数化图像相似度度量学习算法。该算法结合当前最基本的图像表达框架,提出使用图像相似度成对约束的方法学习参数化的相似度度量。图像相似度成对约束将图像类别信息进行了编码,使得学习之后的同类别图像之间的相似度要大于不同类别之间图像之间的相似度,增强了相似度度量的判别性。同时,本论文提出的在线学习算法解决了基于成对约束而导致的大规模的学习问题。实验结果表明,本论文提出的算法取得了优异的分类性能,并且大幅度提升了传统离线算法的学习效率。
4)针对图像分类中的分类器模型提出了一种全局和局部分类器训练方法。以监控场景中的运动目标为研究载体,本论文分析了多类分类的特征空间分布特性,并指出同时考虑输入空间的全局和局部特性进行分类器构造。本论文初始聚类和聚类优化的方法将输入空间划分成若干个不相交的子聚类。使用这些子聚类训练得到的全局分类器表达了输入空间的全局信息。在每个子聚类中训练得到的子分类器表达了输入空间的局部信息。本论文提出的训练模型能够处理输入空间复杂的数据分布。实验结果和实际应用系统分别证明了本论文方法的优越性和实用性。
Intelligent image understanding and analysis are hot and difficult research topics in the multimedia community. Image classification is the most basic and important aspect for image understanding and analysis. Image classification task is about to di-vide images into semantic categories. First, image classification uses computer vision methods to extract the visual features to represent the images. Then a classification step is performed by using machine learning algorithms. The research of image classi-ficationcan promote the development of web image retrieval, intelligent video sur-veillance, biometrics recognition and so on.
In spite of so many applications, the current research on image classification can-not satisfy the demand for real applications. The semantic gap occurs between the low-level visual representation and the high-level human sense is the main prob-lem.The rationale behind this problem is the discriminative ability of the image classi-fication system.Thus, this dissertation focuses on the research of the discrimination enhanced image classification. The main research work and contributions are as fol-lows:
1) The state-of-the-art low-level feature coding methods have been studied and low-level feature coding is performed by the relationship between two impor-tant factors which are low-level feature and codebook. Considering the cha-racteristics of these two factors, this dissertation proposes to use explicit addi-tive kernel maps to transform the low-level feature and codebook into a high-er feature space for separabability enhancement. The vector difference be-tween the low-level feature and codebook in the transformed feature space is utilized to describe their relationship.This dissertation proposes a generalized low-level feature coding method.The research illustrates that the proposed method has more powerful discriminative ability.The performance of image classification on the public dataset has been improved.
2) The limitations of the existing image representation methods have been pointed out. In order to minimize the impact of the variability in image classi-fication, this dissertation proposes to model the latent factors that have the in-fluence onthe final classification performance by the analysis of the variabili- ty of image classification. Meanwhile, this dissertation proposes a discrimina-tive frameworkto enhance the discrimination of the image representation. The framework can represent each image by a low-dimensional feature vector based on partial least square method. This dramatically reduces the burdens of the classifier training and the feature storage. Because the framework uses the image labels, the final image representation has strong discriminative ability among different image classes. The effectiveness of the proposed method has been proved on the popular image classification datasets.
3) An online discriminative parametric image similarity metric learning algo-rithm has been proposed. Based on the basic image representation framework, the proposed algorithm uses the pairwise constraints to learn the parametric image similarity metric.The pairwise constraintsencode theimage label prior so thatan image may have larger similarity between the images in the same class than those in the different classes after learning. Therefore, the discri-minative ability of the learned similarity measure is enhanced.Meanwhile, this dissertation proposes an online learning algorithm to deal with the large scale learning problem which is the consequence of the pairwise constraints. As shown in the experimental results, the proposed online learning algorithm achieves the promising performance and improves the efficiency of the rela-tive offline learning algorithm.
4) A global and local training framework whichcan be applied to image classifi-cation has been proposed.Considering the moving object classification, this dissertation analyzes the distribution of the input space and points out that there are global and local information that can be used for classifier training. Using initial clustering and clusters refinement, this dissertation dividesthe input space into several local clusters. A trainedglobal classifier captures the global information while the localclassifiers can capture the local information. This frameworkcan deal with the problem of complex data distribution ofin-put feature space, especially for video surveillance. Theexperimental results and the real application system illustrate the advantages and the practicability ofthe proposed method respectively.
虽然图像分类具有广阔的应用前景,但是当前对图像分类的研究还远远不能满足实际应用的需要,这是因为在图像分类中存在底层视觉描述与高层人类感知之间的语义鸿沟。在这个开放性的问题中起到关键作用的是分类系统判别能力的强弱。因此,本论文围绕图像分类中的判别性增强,开展了以下系统性的研究工作,取得了相关的研究成果：
1)通过归纳总结当前最优秀的底层特征编码方法,提出使用图像表达中的两个基本元素——底层特征与视觉词包之间的关系来进行底层特征编码。考虑到底层特征与视觉词包的特性,本论文使用直接加性核映射的方式将它们分别映射到一个高维空间中,在该空间中使用向量差的方式描述底层特征与视觉词包之间的关系。本论文提出的方法更具一般性。研究结果表明,最后得到的底层特征编码响应与传统方法相比具有更强的判别性。在公开数据库上的图像分类的性能得到了提升。
2)指出现有图像表达方法中存在的两个关键的局限性。为了降低图像可变性对分类性能的影响,本论文提出基于可变性分析对影响图像分类性能的潜在因子进行建模。同时,为了增强图像表达的判别性,本论文提出了一种判别式的图像表达框架,该框架基于偏最小二乘方法,将每幅图像表达成一个低维的特征向量。这极大地减轻了分类器的训练和特征的存储的负担。由于该框架结合了图像的类别标签,因此最终的图像表达在不同类别之间具有较强的判别性。在主流公开数据库上的实验结果验证了本论文方法的有效性。
3)提出了一种在线判别式的参数化图像相似度度量学习算法。该算法结合当前最基本的图像表达框架,提出使用图像相似度成对约束的方法学习参数化的相似度度量。图像相似度成对约束将图像类别信息进行了编码,使得学习之后的同类别图像之间的相似度要大于不同类别之间图像之间的相似度,增强了相似度度量的判别性。同时,本论文提出的在线学习算法解决了基于成对约束而导致的大规模的学习问题。实验结果表明,本论文提出的算法取得了优异的分类性能,并且大幅度提升了传统离线算法的学习效率。
4)针对图像分类中的分类器模型提出了一种全局和局部分类器训练方法。以监控场景中的运动目标为研究载体,本论文分析了多类分类的特征空间分布特性,并指出同时考虑输入空间的全局和局部特性进行分类器构造。本论文初始聚类和聚类优化的方法将输入空间划分成若干个不相交的子聚类。使用这些子聚类训练得到的全局分类器表达了输入空间的全局信息。在每个子聚类中训练得到的子分类器表达了输入空间的局部信息。本论文提出的训练模型能够处理输入空间复杂的数据分布。实验结果和实际应用系统分别证明了本论文方法的优越性和实用性。
Intelligent image understanding and analysis are hot and difficult research topics in the multimedia community. Image classification is the most basic and important aspect for image understanding and analysis. Image classification task is about to di-vide images into semantic categories. First, image classification uses computer vision methods to extract the visual features to represent the images. Then a classification step is performed by using machine learning algorithms. The research of image classi-ficationcan promote the development of web image retrieval, intelligent video sur-veillance, biometrics recognition and so on.
In spite of so many applications, the current research on image classification can-not satisfy the demand for real applications. The semantic gap occurs between the low-level visual representation and the high-level human sense is the main prob-lem.The rationale behind this problem is the discriminative ability of the image classi-fication system.Thus, this dissertation focuses on the research of the discrimination enhanced image classification. The main research work and contributions are as fol-lows:
1) The state-of-the-art low-level feature coding methods have been studied and low-level feature coding is performed by the relationship between two impor-tant factors which are low-level feature and codebook. Considering the cha-racteristics of these two factors, this dissertation proposes to use explicit addi-tive kernel maps to transform the low-level feature and codebook into a high-er feature space for separabability enhancement. The vector difference be-tween the low-level feature and codebook in the transformed feature space is utilized to describe their relationship.This dissertation proposes a generalized low-level feature coding method.The research illustrates that the proposed method has more powerful discriminative ability.The performance of image classification on the public dataset has been improved.
2) The limitations of the existing image representation methods have been pointed out. In order to minimize the impact of the variability in image classi-fication, this dissertation proposes to model the latent factors that have the in-fluence onthe final classification performance by the analysis of the variabili- ty of image classification. Meanwhile, this dissertation proposes a discrimina-tive frameworkto enhance the discrimination of the image representation. The framework can represent each image by a low-dimensional feature vector based on partial least square method. This dramatically reduces the burdens of the classifier training and the feature storage. Because the framework uses the image labels, the final image representation has strong discriminative ability among different image classes. The effectiveness of the proposed method has been proved on the popular image classification datasets.
3) An online discriminative parametric image similarity metric learning algo-rithm has been proposed. Based on the basic image representation framework, the proposed algorithm uses the pairwise constraints to learn the parametric image similarity metric.The pairwise constraintsencode theimage label prior so thatan image may have larger similarity between the images in the same class than those in the different classes after learning. Therefore, the discri-minative ability of the learned similarity measure is enhanced.Meanwhile, this dissertation proposes an online learning algorithm to deal with the large scale learning problem which is the consequence of the pairwise constraints. As shown in the experimental results, the proposed online learning algorithm achieves the promising performance and improves the efficiency of the rela-tive offline learning algorithm.
4) A global and local training framework whichcan be applied to image classifi-cation has been proposed.Considering the moving object classification, this dissertation analyzes the distribution of the input space and points out that there are global and local information that can be used for classifier training. Using initial clustering and clusters refinement, this dissertation dividesthe input space into several local clusters. A trainedglobal classifier captures the global information while the localclassifiers can capture the local information. This frameworkcan deal with the problem of complex data distribution ofin-put feature space, especially for video surveillance. Theexperimental results and the real application system illustrate the advantages and the practicability ofthe proposed method respectively.
引文
[1]I. Biederman, "Visual object recognition "Proceedings of An Invitation to Cog-nitiveScience, MIT Press,121-165,1995.
[2]H. Jegou, M. Douze, C. Schmid, and P. Perez,"Aggregating localdescriptors into a compact image representation,"IEEE International Conference on Computer Vision and Pattern Recognition,2010.
[3]G. Csurka, C. Bray, C. Dance, and L. Fan,"Visual categorization withbags of keypoints,"European Conference on Computer Vision,2004.
[4]T. Deselaersand V. Ferrari, "Visual and semantic similarity in ImageNet", IEEE International Conference on Computer Vision and Pattern Recognition,2011.
[5]V. Ablavsky and S. Sclaroff, "Learning parameterized histogram kernels on the simplex manifoldfor image and action classification," International Conference on Computer Vision,2011.
[6]H. Cai, F. Yan, and K. Mikolajczyk, "Learning weights for codebook in image classification and retrieval," IEEE International Conference on Computer Vision and Pattern Recognition,2010.
[7]Z. Harchaoui, M. Douze, M. Paulin, M. Dudik, and J. Malick, "Large-scale im-age classification with trace-norm regularization,"IEEE International Confe-rence on Computer Vision and Pattern Recognition,2012.
[8]X. Zhao, J. Ding, K. Huang, and T. Tan, "Global and local training for moving object classification in surveillance-oriented scene, "Asian Conference on Pat-tern Recognition,2011.
[9]L. Yang, N. Zheng, J. Yang, M. Chen, and H. Chen, "A biasedsampling strategy for object categorization,"Internatioal Conference on Computer Vision,2009.
[10]A. Frome, Y. Singer, F. Sha, and J. Malik,"Learning globally-consistent local distance functions for shape-based image retrievaland classifica-tion,"International Conference on Computer Vision,2007.
[11]A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, "Generic object recognition with boosting,"IEEE Transactions onPattern Analysis and Machine Intelligence, 28(3):pp.416-430, Mar 2006.
[12]T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, andT. Poggio, "Robust object recognition withcortex-Like mechanisms,"IEEE Transactions onPattern Analy-sis and Machine Intelligence,29(3):pp.411-426, Mar 2007.
[13]X. Wang, M. Yang, T. Cour, S. Zhu, K. Yu, T. X. Han, "Contextual weighting for vocabulary tree based image retrieval," International Conference on Com- puter Vision,2011.
[14]S. Lazebnik, C. Schmid, and J. Ponce,"Beyond bags of visual-words:spatial pyramid matching for recognizing natural scene categories,"IEEE International Conference on Computer Vision and Pattern Recognition,2006.
[15]Jan C. van Gemert, Jan-Mark Geusebroek, Cor J. Veenman, and Arnold W.M. Smeulders, "Kernel codebooks for scene categorization,"European Conference on Computer Vision,2008.
[16]E.Rosch and C. B. Mervis,"Family resemblances:Studies in the internal struc-ture ofcategories,"Cognitive Psychology,573-605,1975.
[17]A. Vailaya, A. Figueiredo, A. K. Jain, "Image classification for con-tent-basedindexing,"IEEE Transactions on Image Processing,10(1):pp. 117-130,2001.
[18]K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, "Wallflower:principles and practice of background maintenance,"International Conference on Computer Vision, pp.255-261,1999.
[19]I.Haritaoglu, D.Harwood, and L.Davis, "W4S:A real time system for detecting and tracking people in 2.5 D "European Conference on Computer Vision,June 1998.
[20]A. K. Jain, A. Ross, and S. Prabhakar, "An introduction to biometric recogni-tion,"IEEE Trans. on Circuits and Systems for Video Technology,14(1):pp. 4-20,2004.
[21]L. Ma, T. Tan, Y. Wang, and D. Zhang, "Efficient iris recognition by characte-rizing key local variations,"IEEE Transactions on Image Processing,13(6):pp. 739-750,2005.
[22]W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phillips,"Face Recognition:A Literature Survey,"ACM Computing Surveys, pp.399-458,2003.
[23]D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, "Handbook of fingerprint recognition,"Second Edition, Springer,2009.
[24]L. Wang, T. N. Tan, W. M. Hu, and H. Z. Ning, "Automatic gait recognition based on statistical shape analysis,"IEEE Transactions on Image Processing, 12(9):pp.1120-1131,2003.
[25]F. Perronnin and C. Dance, "Fisher kernels on visual vocabularies forimage ca-tegorization," IEEE International Conference on Computer Vision and Pattern Recognition,2007.
[26]F. Perronnin, J.Sanchez, and T. Mensink, "Improving the Fisher kernel for large-scale image classification,"European Conference on Computer Vi-sion,2010.
[27]A. Bosch, A. Zisserman, and X. Muoz, "Scene classification using a hybrid ge-nerative/discriminative approach,"Scene Transactions on Pattern Analysis and Machine Intelligence,30(4):pp.712-727, Apr 2008.
[28]C. Fellbaum, "Wordnet:an electronic lexical database,"Bradford Books,1998.
[29]D. N. Osherson, J. Stern, O. Wilkie, M. Stob, and E. E. Smith, "Default proba-bility,"Cognitive Science,15(2),1991.
[30]G. Griffin, A. Holub, and P. Perona, "The caltech-256,"Caltech Technical Re-port.
[31]J. Xiao, J. Hays, K. Ehinger, A. Oliva, and A. Torralba, "SUN database: large-scale scene recognition from abbey to zoo "IEEE Conference on Comput-er Vision and Pattern Recognition,2010.
[32]C. H. Lampert, H. Nickisch,and S. Harmeling,"Learning to detect unseen object classes by between-class attribute transfer,"IEEE Conference on Computer Vi-sion and Pattern Recognition,2009.
[33]S. E. Palmer, "The effects of contextual scenes on the identication of ob-jects,"Mememory and Cognition,3(5):pp.519-526,1975.
[34]R. Luneburg, "Mathematical analysis of binocular vision "Princeton, NJ:Princeton University Press,1947.
[35]J. Todd and J. Norman, "The visual perception of smoothly curved surfacesfrom minimal apparent motion sequences,"Perception and Psychophysics,50: pp.509-523,1991.
[36]M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in-cortex "Nature Neuroscience,2:pp.1019-1025,1999.
[37]T. Serre, L. Wolf, and T. Poggio, "Object recognition with visual-Words inspi-redby visual cortex,"IEEE Conference on Computer Vision and Pattern Recog-nition,2005.
[38]T. Joachims, "Text categorization with support vector machines:Learning with manyrelevant visual-Wotds,"European Conference on Machine Learning,1998.
[39]H. Lodhi, J. Shawe-Taylor, N. Christianini, andC. Watkins, "Text classification usingstring kernels,"Advances in Neural Information Processing Systems, Vol 13,2001.
[40]N. Cristianini, J.Shawe-Taylor, and H. Lodhi, "Latent semantic ker-nels "Journal oflntelligent Information Systems,18 (2), pp.127-152,2002.
[41]http://pascallin.ecs.soton.ac.uk/challenges/VOC/.
[42]http://trecvid.nist.gov/.
[43]J. Yang, K. Yu, Y. Gong, and T. Huang, "Linear spatial pyramidmatching using sparse coding for image classification,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[44]C. Harris and M. Stephens, "A combined corner and edge detector,"Fourth Al-vey Vision Conference, pp.147-151,1988.
[45]D. G. Lowe, "Distinctive image visual-Words from dcale-invariant key-points "International Journal of Computer Vision,2(60):pp.91-110,2004.
[46]J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust wide-baseline stereofrom maximally stable extremal regions,"Image and Vision Computing,22(10):pp. 761-767,2004.
[47]K. Mikolajczyk and C. Schmid, "Scale and affine invariant interest pointdetec-tors,"International Journal of Computer Vision,60(1):pp.63-86,2004.
[48]E. Nowak,F. Jurie, and B. Triggs, "Sampling strategies for bag-of-visual-words image classification,"European Conference on Computer Vision,2006.
[49]N. Dalal and B. Triggs, "Histograms of oriented gradients for human detec-tion,"IEEE Conference on Computer Vision and Pattern Recognition,2005.
[50]J. Wang, J. Yang, K. Yu, F. Lv, T. S. Huang, and Y. Gong, "Locali-ty-constrained linear coding for image classification,"IEEE Conference on Computer Vision and Pattern Recognition,2010.
[51]Y. Huang, K. Huang, Y. Yu, and T. Tan,"Salient coding for imageclassifica-tion,"IEEE Conference on Computer Vision and Pattern Recognition,2011.
[52]S. Gao, I. W. Tsang, L. Chia, and P. Zhao,"Local features are not lonely-lap-lacian sparse coding forimage classification,"IEEE Conference on Computer Vision and Pattern Recognition,2010.
[53]N. Morioka and S. Satoh, "Building compact local pairwise codebookwith joint feature space clustering,"European Conference on Machine Learning,2010.
[54]N. Morioka and S. Satoh, "Compact correlation coding for visual object catego-rization,"International Conference on Computer Vision,2011.
[55]A. Shabou and H. L. Borgne,"Locality-constrained and spatially regularized coding for scene categorization,"IEEE Conference on Computer Vision and Pattern Recognition,2012.
[56]X. Zhou, K. Yu, T. Zhang, and T. S. Huang, "Image classification using su-per-vector codingof local image descriptors,"European Conference on Machine Learning,2010.
[57]L. Liu, L. Wang, and X. Liu, "In defense of soft-assignment cod-ing,"International Conference on Computer Vision,2011.
[58]I. Ulusoy and C. M. Bishop,"Generative versus discriminative methods for ob-ject Recognition,"IEEE Conference on Computer Vision and Pattern Recogni- tion,2005.
[59]C. M. Bishop, and J.Lasserre, "Generative or discriminative? getting the best of both worlds,"Bayesian Statistics 8,Oxford University Press, pp.3-23,2007.
[60]M. Tipping. "The relevance vector mach.ine,"Advances in Neural Information ProcessingSystems,1999.
[61]T. Deselaersa, G. Heigold, and H. Ney, "Object classification by fusing sVMs and gaussian mixtures "Pattern Recognition,2010.
[62]M. Dixit, N. Rasiwasia and N. Vasconcelos, "Adapted Gaussian models for image classification,"IEEE Conference on Computer Vision and Pattern Recog-nition,2011.
[63]T. Jebara, "Discriminative, generative and imitative learning," PhD Thesis, Me-dia Laboratory, MIT, December 2001.
[64]T. Jaakkola and D. Haussler, "Exploiting generative models indiscriminative classifiers,"Technical report, Dept. of ComputerScience, Univ. of California, 1998.
[65]Y. Boureau J. Ponce, and Y. LeCun "A theoretical analysis of feature pooling in visual recognition."International Conferenceon Machine Learning,2010.
[66]T. Serre,L. Wolf, and T. Poggio,"Object recognition withfeatures inspired by visual cortex,"IEEE Conference on Computer Vision and Pattern Recognition, 2005.
[67]R. Chaudhry, A. Ravichandran, G. Hager, and R. Vidal, "Histograms of oriented optical flow and Binet-Cauchy kernelson nonlinear dynamical systems for the recognition of human actions,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[68]G. Lebanon, "Metric learning for text documents,"IEEE Transactions onPattern Analysis and Machine Intelligence,28(4):pp.497-508,2006.
[69]O. Chapelle, P. Haffner, and V. Vapnik, "Support vector machines for histo-grambased image classification,"IEEE Transactions on Neural Networks,10(5): pp.1055-1064,1999.
[70]H.-Y. Wang, H. Zha, and H. Qin, "Dirichlet aggregation:unsupervised learning towards an optimal metric for proportional data,"International Conferenceon Machine Learning,2007.
[71]汪洪桥,孙富春,蔡艳宁,陈宁,丁林阁,“多核学习方法,”自动化学报,第36卷,第8期,pp.1037-1050,2010年8月.
[72]P. V. Gehler and S. Nowozin, "Let the kernel figure it out:Principled learning of pre-processing for kernel classifiers,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[73]M. Varma and B. R. Babu, "More generality in efficient multiple kernel learn-ing, "International Conferenceon Machine Learning,2009.
[74]P. Viola and M. J. Jones, "Robust real-time face detection,"International Jour-nal of Computer Vision,2(57):pp.137-154, May 2004.
[75]Z. He, Z. Sun, T. Tan, X. Qiu, C. Zhong, and W. Dong, "Boosting ordinal fea-tures for accurate and fast iris recognition,"IEEE Conference on Computer Vi-sion and Pattern Recognition,2008.
[76]A. Vedaldi and A. Zisserman, "Efficient additive kernels via explicit feature maps "IEEE Conference on Computer Vision and Pattern Recognition,2010.
[77]D. Picard and P. Gosselin, "Improving image similarity with vector oflocally aggregated tensors,"IEEE International Conference on Image Processing,2011.
[78]Y. Jia and T. Darrell,"Heavy-tailed distances for gradient based image descrip-tors,"Advances in Neural Information Processing Systems, Vol 23,2011.
[79]P. J. Huber, "Robust statistical procedures,"SLAM, second edition,1996.
[80]W. Liu, P.P. Pokharel, and J.C. Principe, "Correntropy:propertiesand applica-tions in non-Gaussian signal processing,"IEEETrans. Signal Processing,55(11): pp.5286-5298, Nov.2007.
[81]J. C. Principe, W. Liu, P. Pokharel, J. Xu, and S. Seth, "Correntropy for random variables:properties, and applications in statistical inference,"Information Theoretic Learning:Renyi's Entropy and Kernel Perspectives (Information Science and Statistics) (Chapter 10),Springer Verlag,2010.
[82]J. Wu, W. Tan, and J. M. Rehg, "Efficient and effective visual codebook gener-ation using additive keraels,"Journal of Machine Learning Research,12:pp. 3097-31182011.
[83]B.Scholkopfand A. J. Smola, "Learning with kernels,"Mitpress,2002.
[84]S. Maji and A. C. Berg, "Max-margin additive classifiers fordetection,"IEEE International Conference on Computer Vision,2009.
[85]M. Hein and O. Bousquet, "Hilbertian metrics and positivedeflnite kernels on probability measures,"International Conference onArtificial Intelligence and Statistics,,2005.
[86]F. Attneave, "Some informational aspects of visual percep-tion"Psychologicalreview,1954.
[87]K. van de Sande, T. Gevers, and C. Snoek, "Evaluating color descriptorsfor ob-ject and scene recognition,"IEEE Transactions onPattern Analysis and Machine Intelligence,32(9):pp.1582-1596,2010.
[88]J.C.V.Gemert,J.M.Geusebroek,C.J.Veenman,andA.W.M. Smeulders,"Kernel codebooks for scene categorization," European Conference on Computer Vision, 2008.
[89]F. Perronnin, C. Dance, G. Csurka, andM. Bressan, "Adapted vocabularies for generic visual categorization," European Conference on Computer Vision,2006.
[90]P. Kenny, P. Ouellet, N. Dehak, V. Gupta, and P. Dumouchel, "A studyof in-terspeaker variability in speaker verification," IEEE Transactions on Au-dio,Speech, Language Processing,16(5):pp.980-988, Jul.2008.
[91]N. Dehak, P. J. Kenny, R. Dehak, P. Dumouchel, and P. Ouellet, "Front-end factor analysis for speaker verification," IEEE Transactions on Audio,Speech, Language Processing,19(4):pp.188-198,2011.
[92]M. West, "Bayesian factor regression model in the "large p, small n"paradigm,"Bayesian Statistics,7:pp.723-732,2003.
[93]P. Kenny, G. Boulianne, and P. Dumouchel, "Eigenvoice modelingwith sparse training data," IEEE Transactions on Speech, Audio Processing,13(3):pp. 345-354, May 2005.
[94]M. Li,C. Lu, A. Wang, and S. Narayanan, "Speaker verification using lasso based sparse total variability supervector and probabilistic linear discriminant analysis"presented at NIST Speaker Recognition Workshop, Atlanta,2011.
[95]R. Rosipal and N. Kramer, "Overview and recent advances in partialleast square," Subspace, Latent Structure and Feature Selection Techniques, pp. 34-51,2006.
[96]K. Chatfield,V. Lempitsky,A. Vedaldi.and A. Zisserman,"The devil is in the details:an evaluation ofrecent feature encoding methods,"British Machine Vi-sion Conference,2012.
[97]S. Maji,AC. Berg,and J. Malik, "Classification using intersection kernel support vector machines is efficient,"IEEE Conference on Computer Vision and Pattern Recognition,2008.
[98]J.V.Gemert, C.Veenman, A.Smeulders, and J.Geusebroek, "Visual word ambi-guity "IEEE Transactions on Pattern Analysis and Machine Intelligence,32(7): pp.1271-1283, July 2010.
[99]L.Bo and C.Sminchisescu, "Efficient match kernels between sets of features for visualrecognition,"Adcabces in Neural Information Processing Systems, Vol 21, 2009.
[100]O.Boiman, E.Shechtman, and M.Irani, "In defense of nearest-neighbor based imageclassification,"IEEE Conference on Computer Vision and Pattern Recog-nition,2008.
[101]A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, "Generic objectrecognition with boosting,"IEEE Transactions onPattern Analysis and Machine Intelligence, 28(3):pp.416-431,2006.
[102]J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid, "Local featuresand ker-nels for classification of texture and object categories:Acomprehensive study "InternationalJournal of Computer Vison,73(2):pp.213-238,2007.
[103]T. Tuytelaars and C. Schmid, "Vector quantizing feature space witha regular lattice," International Conference on Computer Vision,2007.
[104]Pavan K. Mallapragada, Rong Jin, and Anil K. Jain, "Online visualvocabulary pruning using pairwise constraints," IEEE Conference on Computer Vision and Pattern Recognition,2010.
[105]Kilian Q.Weinberger and Lawrence K. Saul, "Distance metric learningfor large margin nearest neighbor classification," Journal of MachineLearning Research, 2009.
[106]M. Schultz and T. Joachims, "Learning a distance metric from relativecompari-sons," Advances in Neural Information Processing Systems, Vol 16,2004.
[107]R. Yan, J. Zhang, J. Yang, and Alexander G. Hauptmann, "A discriminative learning framework with pairwise constraints for video objectclassification," IEEE Transactions on Pattern Analysis and Machine Intelligence,28(4):pp. 578-593,2006.
[108]M. Zinkevich, "Online convex programming and generalized infinitesimal gra-dient ascent,"International Conference on Machine Learning,2003.
[109]K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz,and Y. Singer, "Online passive-aggressive algorithms," Journalof Machine Learning Research,7(Mar): pp.551-585,2006.
[110]V. N. Vapnik, "Statistical learning theory," Wiley,1998.
[111]Z. Liu, K. Huang, and T. Tan, "Cast shadowremoval with GMM for surface reflectance component,"International Conference on Pattern Recogonition, 2006.
[112]H. Cheng, P. Tan, and R. Jin,"Efficientalgorithm for localized support vector machine," IEEETransactions on Knowledge and Data Engineering,22(4):pp. 537-549,2009.
[113]R. Okada, and S. Soatto, "Relevant feature selection for humanpose estimation and localization in cluttered images," European Conference on Computer Vision, 2008.
[114]S. Vijayakumar, A. D. Souza, and S. Schaal, "Incrementalonline learning in high dimensions," Neural Computation,17:pp.2602-2634,2005.
[115]T.K. Kim, and R. Cipolla, "MCBoost:multiple classifierboosting for perceptual co-clustering of images and visualfeatures," Advances in Neural Information ProcessingSystems,2008.
[116]Z. Fu, A. Robles-Kelly, and J. Zhou, "Mixinglinear SVMs for nonlinear classi-fication," IEEE Transactionson Neural Networks,21(12):pp.1963-1975,2010.
[117]K. Crammer and Y. Singer,"Ultraconservative onlinealgorithms for multiclass problems," Journalof Machine Learning Research,3:pp.951-991,2003.
[118]O. Dekel, S. Shalev-Shwartz, and Y. Singer, "The forgetron:akernel-based per-ceptron on abudget," SIAM Journal on Computing,2007.
[119]F. Orabona, J. Keshet, and B. Caputo, "The projectron:abounded kernel-based perceptron," International Conference on Machine Learning,2008.
[120]A. Saffari, M. Godec, T. Pock, C. Leistner,and H. Bischof, "Online multi-class LPBoost," IEEE Conference on Computer Vision and Pattern Recognition, 2010.
[121]A. Torralba, K. P. Murphy, and W. T. Freeman,"Sharing visual features for multi class and multiview object detection," IEEE Transactions on Pattern Analysis andMachine Intelligence,29(5):pp.854-869,2007.
[122]O. Javed, S. Ali, and M. Shah, "Online detectionand classification of moving objects using progressivelyimproving detectors," IEEE Conference on Comput-er Vision and Pattern Recognition,2005.
[123]Z. Zhang, M. Li, K. Huang, and T. Tan,"Boosting local feature descriptors for automatic objectsclassification in traffic scene surveillance," International Conference on Pattern Recogonition,2008.
[2]H. Jegou, M. Douze, C. Schmid, and P. Perez,"Aggregating localdescriptors into a compact image representation,"IEEE International Conference on Computer Vision and Pattern Recognition,2010.
[3]G. Csurka, C. Bray, C. Dance, and L. Fan,"Visual categorization withbags of keypoints,"European Conference on Computer Vision,2004.
[4]T. Deselaersand V. Ferrari, "Visual and semantic similarity in ImageNet", IEEE International Conference on Computer Vision and Pattern Recognition,2011.
[5]V. Ablavsky and S. Sclaroff, "Learning parameterized histogram kernels on the simplex manifoldfor image and action classification," International Conference on Computer Vision,2011.
[6]H. Cai, F. Yan, and K. Mikolajczyk, "Learning weights for codebook in image classification and retrieval," IEEE International Conference on Computer Vision and Pattern Recognition,2010.
[7]Z. Harchaoui, M. Douze, M. Paulin, M. Dudik, and J. Malick, "Large-scale im-age classification with trace-norm regularization,"IEEE International Confe-rence on Computer Vision and Pattern Recognition,2012.
[8]X. Zhao, J. Ding, K. Huang, and T. Tan, "Global and local training for moving object classification in surveillance-oriented scene, "Asian Conference on Pat-tern Recognition,2011.
[9]L. Yang, N. Zheng, J. Yang, M. Chen, and H. Chen, "A biasedsampling strategy for object categorization,"Internatioal Conference on Computer Vision,2009.
[10]A. Frome, Y. Singer, F. Sha, and J. Malik,"Learning globally-consistent local distance functions for shape-based image retrievaland classifica-tion,"International Conference on Computer Vision,2007.
[11]A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, "Generic object recognition with boosting,"IEEE Transactions onPattern Analysis and Machine Intelligence, 28(3):pp.416-430, Mar 2006.
[12]T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, andT. Poggio, "Robust object recognition withcortex-Like mechanisms,"IEEE Transactions onPattern Analy-sis and Machine Intelligence,29(3):pp.411-426, Mar 2007.
[13]X. Wang, M. Yang, T. Cour, S. Zhu, K. Yu, T. X. Han, "Contextual weighting for vocabulary tree based image retrieval," International Conference on Com- puter Vision,2011.
[14]S. Lazebnik, C. Schmid, and J. Ponce,"Beyond bags of visual-words:spatial pyramid matching for recognizing natural scene categories,"IEEE International Conference on Computer Vision and Pattern Recognition,2006.
[15]Jan C. van Gemert, Jan-Mark Geusebroek, Cor J. Veenman, and Arnold W.M. Smeulders, "Kernel codebooks for scene categorization,"European Conference on Computer Vision,2008.
[16]E.Rosch and C. B. Mervis,"Family resemblances:Studies in the internal struc-ture ofcategories,"Cognitive Psychology,573-605,1975.
[17]A. Vailaya, A. Figueiredo, A. K. Jain, "Image classification for con-tent-basedindexing,"IEEE Transactions on Image Processing,10(1):pp. 117-130,2001.
[18]K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, "Wallflower:principles and practice of background maintenance,"International Conference on Computer Vision, pp.255-261,1999.
[19]I.Haritaoglu, D.Harwood, and L.Davis, "W4S:A real time system for detecting and tracking people in 2.5 D "European Conference on Computer Vision,June 1998.
[20]A. K. Jain, A. Ross, and S. Prabhakar, "An introduction to biometric recogni-tion,"IEEE Trans. on Circuits and Systems for Video Technology,14(1):pp. 4-20,2004.
[21]L. Ma, T. Tan, Y. Wang, and D. Zhang, "Efficient iris recognition by characte-rizing key local variations,"IEEE Transactions on Image Processing,13(6):pp. 739-750,2005.
[22]W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phillips,"Face Recognition:A Literature Survey,"ACM Computing Surveys, pp.399-458,2003.
[23]D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, "Handbook of fingerprint recognition,"Second Edition, Springer,2009.
[24]L. Wang, T. N. Tan, W. M. Hu, and H. Z. Ning, "Automatic gait recognition based on statistical shape analysis,"IEEE Transactions on Image Processing, 12(9):pp.1120-1131,2003.
[25]F. Perronnin and C. Dance, "Fisher kernels on visual vocabularies forimage ca-tegorization," IEEE International Conference on Computer Vision and Pattern Recognition,2007.
[26]F. Perronnin, J.Sanchez, and T. Mensink, "Improving the Fisher kernel for large-scale image classification,"European Conference on Computer Vi-sion,2010.
[27]A. Bosch, A. Zisserman, and X. Muoz, "Scene classification using a hybrid ge-nerative/discriminative approach,"Scene Transactions on Pattern Analysis and Machine Intelligence,30(4):pp.712-727, Apr 2008.
[28]C. Fellbaum, "Wordnet:an electronic lexical database,"Bradford Books,1998.
[29]D. N. Osherson, J. Stern, O. Wilkie, M. Stob, and E. E. Smith, "Default proba-bility,"Cognitive Science,15(2),1991.
[30]G. Griffin, A. Holub, and P. Perona, "The caltech-256,"Caltech Technical Re-port.
[31]J. Xiao, J. Hays, K. Ehinger, A. Oliva, and A. Torralba, "SUN database: large-scale scene recognition from abbey to zoo "IEEE Conference on Comput-er Vision and Pattern Recognition,2010.
[32]C. H. Lampert, H. Nickisch,and S. Harmeling,"Learning to detect unseen object classes by between-class attribute transfer,"IEEE Conference on Computer Vi-sion and Pattern Recognition,2009.
[33]S. E. Palmer, "The effects of contextual scenes on the identication of ob-jects,"Mememory and Cognition,3(5):pp.519-526,1975.
[34]R. Luneburg, "Mathematical analysis of binocular vision "Princeton, NJ:Princeton University Press,1947.
[35]J. Todd and J. Norman, "The visual perception of smoothly curved surfacesfrom minimal apparent motion sequences,"Perception and Psychophysics,50: pp.509-523,1991.
[36]M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in-cortex "Nature Neuroscience,2:pp.1019-1025,1999.
[37]T. Serre, L. Wolf, and T. Poggio, "Object recognition with visual-Words inspi-redby visual cortex,"IEEE Conference on Computer Vision and Pattern Recog-nition,2005.
[38]T. Joachims, "Text categorization with support vector machines:Learning with manyrelevant visual-Wotds,"European Conference on Machine Learning,1998.
[39]H. Lodhi, J. Shawe-Taylor, N. Christianini, andC. Watkins, "Text classification usingstring kernels,"Advances in Neural Information Processing Systems, Vol 13,2001.
[40]N. Cristianini, J.Shawe-Taylor, and H. Lodhi, "Latent semantic ker-nels "Journal oflntelligent Information Systems,18 (2), pp.127-152,2002.
[41]http://pascallin.ecs.soton.ac.uk/challenges/VOC/.
[42]http://trecvid.nist.gov/.
[43]J. Yang, K. Yu, Y. Gong, and T. Huang, "Linear spatial pyramidmatching using sparse coding for image classification,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[44]C. Harris and M. Stephens, "A combined corner and edge detector,"Fourth Al-vey Vision Conference, pp.147-151,1988.
[45]D. G. Lowe, "Distinctive image visual-Words from dcale-invariant key-points "International Journal of Computer Vision,2(60):pp.91-110,2004.
[46]J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust wide-baseline stereofrom maximally stable extremal regions,"Image and Vision Computing,22(10):pp. 761-767,2004.
[47]K. Mikolajczyk and C. Schmid, "Scale and affine invariant interest pointdetec-tors,"International Journal of Computer Vision,60(1):pp.63-86,2004.
[48]E. Nowak,F. Jurie, and B. Triggs, "Sampling strategies for bag-of-visual-words image classification,"European Conference on Computer Vision,2006.
[49]N. Dalal and B. Triggs, "Histograms of oriented gradients for human detec-tion,"IEEE Conference on Computer Vision and Pattern Recognition,2005.
[50]J. Wang, J. Yang, K. Yu, F. Lv, T. S. Huang, and Y. Gong, "Locali-ty-constrained linear coding for image classification,"IEEE Conference on Computer Vision and Pattern Recognition,2010.
[51]Y. Huang, K. Huang, Y. Yu, and T. Tan,"Salient coding for imageclassifica-tion,"IEEE Conference on Computer Vision and Pattern Recognition,2011.
[52]S. Gao, I. W. Tsang, L. Chia, and P. Zhao,"Local features are not lonely-lap-lacian sparse coding forimage classification,"IEEE Conference on Computer Vision and Pattern Recognition,2010.
[53]N. Morioka and S. Satoh, "Building compact local pairwise codebookwith joint feature space clustering,"European Conference on Machine Learning,2010.
[54]N. Morioka and S. Satoh, "Compact correlation coding for visual object catego-rization,"International Conference on Computer Vision,2011.
[55]A. Shabou and H. L. Borgne,"Locality-constrained and spatially regularized coding for scene categorization,"IEEE Conference on Computer Vision and Pattern Recognition,2012.
[56]X. Zhou, K. Yu, T. Zhang, and T. S. Huang, "Image classification using su-per-vector codingof local image descriptors,"European Conference on Machine Learning,2010.
[57]L. Liu, L. Wang, and X. Liu, "In defense of soft-assignment cod-ing,"International Conference on Computer Vision,2011.
[58]I. Ulusoy and C. M. Bishop,"Generative versus discriminative methods for ob-ject Recognition,"IEEE Conference on Computer Vision and Pattern Recogni- tion,2005.
[59]C. M. Bishop, and J.Lasserre, "Generative or discriminative? getting the best of both worlds,"Bayesian Statistics 8,Oxford University Press, pp.3-23,2007.
[60]M. Tipping. "The relevance vector mach.ine,"Advances in Neural Information ProcessingSystems,1999.
[61]T. Deselaersa, G. Heigold, and H. Ney, "Object classification by fusing sVMs and gaussian mixtures "Pattern Recognition,2010.
[62]M. Dixit, N. Rasiwasia and N. Vasconcelos, "Adapted Gaussian models for image classification,"IEEE Conference on Computer Vision and Pattern Recog-nition,2011.
[63]T. Jebara, "Discriminative, generative and imitative learning," PhD Thesis, Me-dia Laboratory, MIT, December 2001.
[64]T. Jaakkola and D. Haussler, "Exploiting generative models indiscriminative classifiers,"Technical report, Dept. of ComputerScience, Univ. of California, 1998.
[65]Y. Boureau J. Ponce, and Y. LeCun "A theoretical analysis of feature pooling in visual recognition."International Conferenceon Machine Learning,2010.
[66]T. Serre,L. Wolf, and T. Poggio,"Object recognition withfeatures inspired by visual cortex,"IEEE Conference on Computer Vision and Pattern Recognition, 2005.
[67]R. Chaudhry, A. Ravichandran, G. Hager, and R. Vidal, "Histograms of oriented optical flow and Binet-Cauchy kernelson nonlinear dynamical systems for the recognition of human actions,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[68]G. Lebanon, "Metric learning for text documents,"IEEE Transactions onPattern Analysis and Machine Intelligence,28(4):pp.497-508,2006.
[69]O. Chapelle, P. Haffner, and V. Vapnik, "Support vector machines for histo-grambased image classification,"IEEE Transactions on Neural Networks,10(5): pp.1055-1064,1999.
[70]H.-Y. Wang, H. Zha, and H. Qin, "Dirichlet aggregation:unsupervised learning towards an optimal metric for proportional data,"International Conferenceon Machine Learning,2007.
[71]汪洪桥,孙富春,蔡艳宁,陈宁,丁林阁,“多核学习方法,”自动化学报,第36卷,第8期,pp.1037-1050,2010年8月.
[72]P. V. Gehler and S. Nowozin, "Let the kernel figure it out:Principled learning of pre-processing for kernel classifiers,"IEEE Conference on Computer Vision and Pattern Recognition,2009.
[73]M. Varma and B. R. Babu, "More generality in efficient multiple kernel learn-ing, "International Conferenceon Machine Learning,2009.
[74]P. Viola and M. J. Jones, "Robust real-time face detection,"International Jour-nal of Computer Vision,2(57):pp.137-154, May 2004.
[75]Z. He, Z. Sun, T. Tan, X. Qiu, C. Zhong, and W. Dong, "Boosting ordinal fea-tures for accurate and fast iris recognition,"IEEE Conference on Computer Vi-sion and Pattern Recognition,2008.
[76]A. Vedaldi and A. Zisserman, "Efficient additive kernels via explicit feature maps "IEEE Conference on Computer Vision and Pattern Recognition,2010.
[77]D. Picard and P. Gosselin, "Improving image similarity with vector oflocally aggregated tensors,"IEEE International Conference on Image Processing,2011.
[78]Y. Jia and T. Darrell,"Heavy-tailed distances for gradient based image descrip-tors,"Advances in Neural Information Processing Systems, Vol 23,2011.
[79]P. J. Huber, "Robust statistical procedures,"SLAM, second edition,1996.
[80]W. Liu, P.P. Pokharel, and J.C. Principe, "Correntropy:propertiesand applica-tions in non-Gaussian signal processing,"IEEETrans. Signal Processing,55(11): pp.5286-5298, Nov.2007.
[81]J. C. Principe, W. Liu, P. Pokharel, J. Xu, and S. Seth, "Correntropy for random variables:properties, and applications in statistical inference,"Information Theoretic Learning:Renyi's Entropy and Kernel Perspectives (Information Science and Statistics) (Chapter 10),Springer Verlag,2010.
[82]J. Wu, W. Tan, and J. M. Rehg, "Efficient and effective visual codebook gener-ation using additive keraels,"Journal of Machine Learning Research,12:pp. 3097-31182011.
[83]B.Scholkopfand A. J. Smola, "Learning with kernels,"Mitpress,2002.
[84]S. Maji and A. C. Berg, "Max-margin additive classifiers fordetection,"IEEE International Conference on Computer Vision,2009.
[85]M. Hein and O. Bousquet, "Hilbertian metrics and positivedeflnite kernels on probability measures,"International Conference onArtificial Intelligence and Statistics,,2005.
[86]F. Attneave, "Some informational aspects of visual percep-tion"Psychologicalreview,1954.
[87]K. van de Sande, T. Gevers, and C. Snoek, "Evaluating color descriptorsfor ob-ject and scene recognition,"IEEE Transactions onPattern Analysis and Machine Intelligence,32(9):pp.1582-1596,2010.
[88]J.C.V.Gemert,J.M.Geusebroek,C.J.Veenman,andA.W.M. Smeulders,"Kernel codebooks for scene categorization," European Conference on Computer Vision, 2008.
[89]F. Perronnin, C. Dance, G. Csurka, andM. Bressan, "Adapted vocabularies for generic visual categorization," European Conference on Computer Vision,2006.
[90]P. Kenny, P. Ouellet, N. Dehak, V. Gupta, and P. Dumouchel, "A studyof in-terspeaker variability in speaker verification," IEEE Transactions on Au-dio,Speech, Language Processing,16(5):pp.980-988, Jul.2008.
[91]N. Dehak, P. J. Kenny, R. Dehak, P. Dumouchel, and P. Ouellet, "Front-end factor analysis for speaker verification," IEEE Transactions on Audio,Speech, Language Processing,19(4):pp.188-198,2011.
[92]M. West, "Bayesian factor regression model in the "large p, small n"paradigm,"Bayesian Statistics,7:pp.723-732,2003.
[93]P. Kenny, G. Boulianne, and P. Dumouchel, "Eigenvoice modelingwith sparse training data," IEEE Transactions on Speech, Audio Processing,13(3):pp. 345-354, May 2005.
[94]M. Li,C. Lu, A. Wang, and S. Narayanan, "Speaker verification using lasso based sparse total variability supervector and probabilistic linear discriminant analysis"presented at NIST Speaker Recognition Workshop, Atlanta,2011.
[95]R. Rosipal and N. Kramer, "Overview and recent advances in partialleast square," Subspace, Latent Structure and Feature Selection Techniques, pp. 34-51,2006.
[96]K. Chatfield,V. Lempitsky,A. Vedaldi.and A. Zisserman,"The devil is in the details:an evaluation ofrecent feature encoding methods,"British Machine Vi-sion Conference,2012.
[97]S. Maji,AC. Berg,and J. Malik, "Classification using intersection kernel support vector machines is efficient,"IEEE Conference on Computer Vision and Pattern Recognition,2008.
[98]J.V.Gemert, C.Veenman, A.Smeulders, and J.Geusebroek, "Visual word ambi-guity "IEEE Transactions on Pattern Analysis and Machine Intelligence,32(7): pp.1271-1283, July 2010.
[99]L.Bo and C.Sminchisescu, "Efficient match kernels between sets of features for visualrecognition,"Adcabces in Neural Information Processing Systems, Vol 21, 2009.
[100]O.Boiman, E.Shechtman, and M.Irani, "In defense of nearest-neighbor based imageclassification,"IEEE Conference on Computer Vision and Pattern Recog-nition,2008.
[101]A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, "Generic objectrecognition with boosting,"IEEE Transactions onPattern Analysis and Machine Intelligence, 28(3):pp.416-431,2006.
[102]J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid, "Local featuresand ker-nels for classification of texture and object categories:Acomprehensive study "InternationalJournal of Computer Vison,73(2):pp.213-238,2007.
[103]T. Tuytelaars and C. Schmid, "Vector quantizing feature space witha regular lattice," International Conference on Computer Vision,2007.
[104]Pavan K. Mallapragada, Rong Jin, and Anil K. Jain, "Online visualvocabulary pruning using pairwise constraints," IEEE Conference on Computer Vision and Pattern Recognition,2010.
[105]Kilian Q.Weinberger and Lawrence K. Saul, "Distance metric learningfor large margin nearest neighbor classification," Journal of MachineLearning Research, 2009.
[106]M. Schultz and T. Joachims, "Learning a distance metric from relativecompari-sons," Advances in Neural Information Processing Systems, Vol 16,2004.
[107]R. Yan, J. Zhang, J. Yang, and Alexander G. Hauptmann, "A discriminative learning framework with pairwise constraints for video objectclassification," IEEE Transactions on Pattern Analysis and Machine Intelligence,28(4):pp. 578-593,2006.
[108]M. Zinkevich, "Online convex programming and generalized infinitesimal gra-dient ascent,"International Conference on Machine Learning,2003.
[109]K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz,and Y. Singer, "Online passive-aggressive algorithms," Journalof Machine Learning Research,7(Mar): pp.551-585,2006.
[110]V. N. Vapnik, "Statistical learning theory," Wiley,1998.
[111]Z. Liu, K. Huang, and T. Tan, "Cast shadowremoval with GMM for surface reflectance component,"International Conference on Pattern Recogonition, 2006.
[112]H. Cheng, P. Tan, and R. Jin,"Efficientalgorithm for localized support vector machine," IEEETransactions on Knowledge and Data Engineering,22(4):pp. 537-549,2009.
[113]R. Okada, and S. Soatto, "Relevant feature selection for humanpose estimation and localization in cluttered images," European Conference on Computer Vision, 2008.
[114]S. Vijayakumar, A. D. Souza, and S. Schaal, "Incrementalonline learning in high dimensions," Neural Computation,17:pp.2602-2634,2005.
[115]T.K. Kim, and R. Cipolla, "MCBoost:multiple classifierboosting for perceptual co-clustering of images and visualfeatures," Advances in Neural Information ProcessingSystems,2008.
[116]Z. Fu, A. Robles-Kelly, and J. Zhou, "Mixinglinear SVMs for nonlinear classi-fication," IEEE Transactionson Neural Networks,21(12):pp.1963-1975,2010.
[117]K. Crammer and Y. Singer,"Ultraconservative onlinealgorithms for multiclass problems," Journalof Machine Learning Research,3:pp.951-991,2003.
[118]O. Dekel, S. Shalev-Shwartz, and Y. Singer, "The forgetron:akernel-based per-ceptron on abudget," SIAM Journal on Computing,2007.
[119]F. Orabona, J. Keshet, and B. Caputo, "The projectron:abounded kernel-based perceptron," International Conference on Machine Learning,2008.
[120]A. Saffari, M. Godec, T. Pock, C. Leistner,and H. Bischof, "Online multi-class LPBoost," IEEE Conference on Computer Vision and Pattern Recognition, 2010.
[121]A. Torralba, K. P. Murphy, and W. T. Freeman,"Sharing visual features for multi class and multiview object detection," IEEE Transactions on Pattern Analysis andMachine Intelligence,29(5):pp.854-869,2007.
[122]O. Javed, S. Ali, and M. Shah, "Online detectionand classification of moving objects using progressivelyimproving detectors," IEEE Conference on Comput-er Vision and Pattern Recognition,2005.
[123]Z. Zhang, M. Li, K. Huang, and T. Tan,"Boosting local feature descriptors for automatic objectsclassification in traffic scene surveillance," International Conference on Pattern Recogonition,2008.