Image Ranking with Eye Movements (2009)
Pasupa, Kitsuchart, Szedmak, Sandor, Hardoon, David
In order to help users navigate an image search system, one could provide explicit rank information on a set of images. These rankings are learnt so to present a new set of relevant images. Although,...
Learning to Rank Images from Eye Movements (2009)
Pasupa, Kitsuchart, Saunders, Craig, Szedmak, Sandor, Klami, Arto, Kaski, Samuel, Gunn, Steve
Combining multiple information sources can improve the accuracy of search in information retrieval. This paper presents a new image search strategy which combines image features together with...
David R. Hardoon, Southampton So Bj, John Shawe-taylor, Southampton So Bj, Sandor Szedmak
In this paper we propose an approach to automatically annotate query
Towards structured output prediction of enzyme function (2008)
Astikainen, Katja, Holm, Liisa, Pitkänen, Esa, Szedmak, Sandor, Rousu, Juho
Abstract Background In this paper we describe work in progress in developing kernel methods for enzyme function prediction. Our focus is in developing so called structured output prediction methods,...
Towards structured output prediction of enzyme function (2008)
Astikainen, Katja, Holm, Liisa, Pitkänen, Esa, Szedmak, Sandor, Rousu, Juho
Background In this paper we describe work in progress in developing kernel methods for enzyme function prediction. Our focus is in developing so called structured output prediction methods, where the...
Zakria Hussain, Sandor Szedmak
The Set Covering Machine (SCM) was introduced by Marchand & Shawe–Taylor [6, 7] in which a minimum set cover of a class of examples was approximated to find a compact conjunction/disjunction of...
Juho Rousu, Sandor Szedmak, Craig Saunders, John Shawe-taylor
We present work in progress towards maximum margin hierarchical classification where the objects are allowed to belong to more than one category at a time. The classification hierarchy is represented...
Learning Hierarchies at Two-class Complexity (2008)
Sandor Szedmak, Craig Saunders, John Shawe-taylor, Juho Rousu
It is assumed that to learn discriminative identification function when the output space is a labelled hierarchy is a much more complex problem than binary classification. In this presentation we...
Towards Structured Output Prediction of Enzyme Function (2007)
Astikainen, Katja, Holm, Liisa, Pitkänen, Esa, Szedmak, Sandor, Rousu, Juho
In this paper we describe work in progress in developing kernel methods for enzyme function prediction. Our focus is in developing so called structured output prediction methods, where the enzymatic...
Efficient Algorithms for Max-Margin Structured Classification (2007)
Rousu, Juho, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John
Kernel regression based machine translation (2007)
Wang, Zhuoran, Shawe-Taylor, John, Szedmak, Sandor
We present a novel machine translation framework based on kernel regression techniques. In our model, the translation task is viewed as a string-to-string mapping, for which a regression type...
A metamorphosis of Canonical Correlation Analysis into Multivariate Maximum Margin Learning (2007)
Szedmak, Sandor, De Bie, Tijl, Hardoon, David
Canonical Correlation Analysis(CCA) is a useful tool to discover relationship between different sources of information represented by vectors. The solution of the underlying optimisation problem...
Kernel regression based machine translation (2007)
Wang, Zhuoran, Shawe-Taylor, John, Szedmak, Sandor
We present a novel machine translation framework based on kernel regression techniques. In our model, the translation task is viewed as a string-to-string mapping, for which a regression type...
Efficient algorithms for max-margin structured classification (2007)
Rousu, Juho, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John
We present a general and efficient optimisation methodology for for max-margin sructured classification tasks. The efficiency of the method relies on the interplay of several techiques:...
Efficient algorithms for max-margin structured classification (2006)
Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John, Rousu, Juho
We present a general and efficient optimization methodology for max-margin structured classification tasks. The efficiency of the method relies on the interplay of several techniques: formulation of...
Synthesis of Maximum Margin and Multiview Learning using Unlabeled Data (2006)
Szedmak, Sandor, Shawe-Taylor, John
In this presentation we show the semi-supervised learning with two input sources can be transformed into a maximum margin problem to be similar to a binary SVM. Our formulation exploits the unlabeled...
Learning via Linear Operators: Maximum Margin Regression (2006)
Szedmak, Sandor, Shawe-Taylor, John, Parado-Hernandez, Emilio
We introduce a maximum margin framework realizing a regression type learning in an arbitrary Hilbert space whilst the corresponding dual problem preserving the structure and, therefore, the...
The 2005 PASCAL Visual Object Classes Challenge (2006)
Everingham, Mark, Zisserman, Andrew, Williams, Christopher, Van Gool, Luc, Allan, Moray, Bishop, Chris, ...
The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not...
Hierarchical Multilabel Classification, Juho Rousu, Craig Saunders, Sandor Szedmak, John Shawe-taylor, P. Bennett, ...
We present a kernel-based algorithm for hierarchical text classification where the documents are allowed to belong to more than one category at a time. The classification model is a variant of the...
Two view learning: SVM-2K, theory and practice (2006)
Hongying Meng, Sandor Szedmak, David R. Hardoon, John Shawe-taylor
Kernel methods make it relatively easy to define complex highdimensional feature spaces. This raises the question of how we can identify the relevant subspaces for a particular learning task. When...
Two view learning: SVM-2K, theory and practice (2006)
Hongying Meng, Sandor Szedmak, David R. Hardoon, John Shawe-taylor
Kernel methods make it relatively easy to define complex highdimensional feature spaces. This raises the question of how we can identify the relevant subspaces for a particular learning task. When...
Learning Hierarchies at Two-class Complexity (2005)
Szedmak, Sandor, Saunders, Craig, Shawe-Taylor, John, Rousu, Juho
It is assumed that to learn discriminative identification function when the output space is a labelled hierarchy is a much more complex problem than binary classification. In this presentation we...
Learning Hierarchy via Embedding at Two-class Complexity (2005)
Szedmak, Sandor, Saunders, Craig, Shawe-Taylor, John, Rousu, Juho
Learning Hierarchy via Embedding at Two-class Complexity (2005)
Szedmak, Sandor, Saunders, Craig, Shawe-Taylor, John, Rousu, Juho
Two view learning: SVM-2K, Theory and Practice (2005)
Farquhar, Jason, Hardoon, David, Meng, Hongying, Shawe-Taylor, John, Szedmak, Sandor
Kernel methods make it relatively easy to define complex high-dimensional feature spaces. This raises the question of how we can identify the relevant subspaces for a particular learning task. When...
Kernel-based Learning of Hierarchical Multilabel Classification Models (2005)
Rousu, Juho, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John
We present a kernel-based algorithm for hierarchical text classification where the documents are allowed to belong to more than one category at a time. The classification model is a variant of the...
Multiclass Learning at One-Class Complexity (2005)
Szedmak, Sandor, Shawe-Taylor, John
We show in this paper the multiclass classification problem can be implemented in the maximum margin framework with the complexity of one binary Support Vector Machine. We show reducing the...
Learning Hierarchical Multi-Category Text Classification Models (2005)
Rousu, Juho, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John
We present a kernel-based algorithm for hierarchical text classification where the documents are allowed to belong to more than one category at a time. The classification model is a variant of the...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David, Shawe-Taylor, John, Szedmak, Sandor
In a generic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
In a genetic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Shawe-Taylor, John, Szedmak, Sandor
In a generic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Multiclass Learning at One-class Complexity (2005)
Szedmak, Sandor, Shawe-Taylor, John
We show in this paper the multiclass classification problem can be implemented in the maximum margin framework with the complexity of one binary Support Vector Machine. We show reducing the...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
In a genetic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Shawe-Taylor, John, Szedmak, Sandor
In a generic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Multiclass Learning at One-class Complexity (2005)
Szedmak, Sandor, Shawe-Taylor, John
We show in this paper the multiclass classification problem can be implemented in the maximum margin framework with the complexity of one binary Support Vector Machine. We show reducing the...
Support Vector Machine to Synthesise Kernels (2005)
Meng, Hongying, Shawe-Taylor, John, Szedmak, Sandor, Farquhar, Jason
In this paper, we introduce a new method (SVM\_2K) which amalgamates the capabilities of the Support Vector Machine (SVM) and Kernel Canonical Correlation Analysis (KCCA) to give a more sophisticated...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
In a genetic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Generic object recognition by combining distinct features in machine learning (2005)
Meng, Hongying, Hardoon, David R., Shawe-Taylor, John, Szedmak, Sandor
In a generic image object recognition or categorization system, the relevant features or descriptors from a characteristic point, patch or region of an image are often obtained by different...
Multiclass Learning at One-class Complexity (2005)
Szedmak, Sandor, Shawe-Taylor, John
We show in this paper the multiclass classification problem can be implemented in the maximum margin framework with the complexity of one binary Support Vector Machine. We show reducing the...
Learning via Linear Operators: Maximum Margin Regression (2005)
Sandor Szedmak, John Shawe-taylor, Isis Group
We introduce a maximum margin framework realizing a regression type learning in an arbitrary Hilbert space whilst the corresponding dual problem preserving the structure and, therefore, the...
Canonical Correlation Analysis: An Overview with Application to Learning Methods (2004)
Hardoon, David, Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel canonical correlation analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
On Maximum Margin Hierarchical Multilabel Classification (2004)
Rousu, Juho, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, Prof John
We present work in progress towards maximum margin hierarchical classification where the objects are allowed to belong to more than one category at a time. The classification hierarchy is represented...
Support Vector Machine to synthesise kernels (2004)
Meng, Hongying, Shawe-Taylor, John, Szedmak, Sandor, Farquhar, Jason
Suppose we are given two sets of features from distinct sources about objects that need to be classified. The question we wish to answer is how to combine them into one classification rule, which can...
Retrieving Keyword's to an Image Query using Kernel CCA (2004)
Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
In this paper we propose an approach to automatically annotate queryimages with keywords. We use kernel Canonical Correlation Analysis to learn a semantic representation between images and their...
The Linear Programming Set Covering Machine (2004)
Hussain, Zakria, Szedmak, Sandor, Shawe-Taylor, John
The Set Covering Machine (SCM) was introduced by Marchand \& Shawe--Taylor~\cite{SCM2001,SCM2002} in which a minimum set cover of a class of examples was approximated to find a compact...
Multiclass classification by L1 norm Support Vector Machine (2004)
Szedmak, Sandor, Shawe-Taylor, John, Saunders, Craig .J., Hardoon, David .R.
The multiclass classification attracts a lot of attention in recent time. It has no such an elaborated theoretical foundation than the binary classification does. Rifkin et al. (2004)...
Multiclass classification by L1 norm Support Vector Machine (2004)
Szedmak, Sandor, Shawe-Taylor, John, Saunders, Craig, Hardoon, David
Multiclass classification by L1 norm Support Vector Machine (2004)
Szedmak, Sandor, Shawe-Taylor, John, Saunders, Craig, Hardoon, David
Canonical Correlation Analysis: An Overview with Application to Learning Methods (2004)
Hardoon, David, Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
Canonical Correlation Analysis: An Overview with Application to Learning Methods (2004)
Hardoon, David, Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
Canonical Correlation Analysis: An Overview with Application to Learning Methods (2004)
Hardoon, David, Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
Pareto-optimal patterns in logical analysis of data (2004)
Peter L. Hammer, Peter L. Hammer, Alexander Kogan, Alexander Kogan, Bruno Simeone, Bruno Simeone, ...
R u t c o r
On Maximum Margin Hierarchical Multilabel Classification (2004)
Juho Rousu, Sandor Szedmak, Craig Saunders, John Shawe-taylor
We present work in progress towards maximum margin hierarchical classification where the objects are allowed to belong to more than one category at a time. The classification hierarchy is represented...
Canonical correlation analysis; An overview with application to learning methods (2003)
Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
Canonical correlation analysis; An overview with application to learning methods (2003)
Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
Canonical correlation analysis; An overview with application to learning methods (2003)
Hardoon, David R., Szedmak, Sandor, Shawe-Taylor, John
We present a general method using kernel Canonical Correlation Analysis to learn a semantic representation to web images and their associated text. The semantic space provides a common representation...
"Graduate Program in Operations Research."
A Correlation Approach for Automatic Image Annotation (0006)
Hardoon, David, Saunders, Craig, Szedmak, Sandor, Shawe-Taylor, John
Abstract. The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learning for the...