Gökhan H. Bakir

Discriminative Subsequence Mining for Action Classification

Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a histogram representation, discarding the temporal order among features. But this ordering information can contain important information about the action itself e.g. consider the sport disciplines of hurdle race and long jump, where the global temporal order of motions (running, jumping) is important to discriminate between the two. In this work we propose to use a sequential representation which retains this temporal order. Further, we introduce Discriminative Subsequence Mining to find optimal discriminative subsequence patterns. In combination with the LPBoost classifier, this amounts to simultaneously learning a classification function and performing feature selection in the space of all possible feature sequences. The resulting classifier linearly combines a small number of interpretable decision functions, each checking for the presence of a single discriminative pattern. The classifier is benchmarked on the KTH action classification data set and outperforms the best known results in the literature.

Weighted Substructure Mining for Image Analysis

In Web-related applications of image categorization, it is desirable to derive an interpretable classification rule with high accuracy. Using the bag-of-words representation and the linear support vector machine, one can partly fulfill the goal, but the accuracy of linear classifiers is not high and the obtained features are not informative for users. We propose to combine item set mining and large margin classifiers to select features from the power set of all visual words. Our resulting classification rule is easier to browse and simpler to understand, because each feature has richer information. As a next step, each image is represented as a graph where nodes correspond to local image features and edges encode geometric relations between features. Combining graph mining and boosting, we can obtain a classification rule based on subgraph features that contain more information than the set features. We evaluate our algorithm in a web-retrieval ranking task where the goal is to reject outliers from a set of images returned for a keyword query. Furthermore, it is evaluated on the supervised classification tasks with the challenging VOC2005 data set. Our approach yields excellent accuracy in the unsupervised ranking task compared to a recently proposed probabilistic model and competitive results in the supervised classification task.

On the representation, learning and transfer of spatio-temporal movement characteristics

In this paper we present a learning-based approach for the modeling of complex movement sequences. Based on the method of Spatio-Temporal Morphable Models (STMMs) we derive a hierarchical algorithm that, in a first step, identifies automatically movement elements in movement sequences based on a coarse spatio-temporal description, and in a second step models these movement primitives by approximation through linear combinations of learned example movement trajectories. We describe the different steps of the algorithm and show how it can be applied for modeling and synthesis of complex sequences of human movements that contain movement elements with a variable style. The proposed method is demonstrated on different applications of movement representation relevant for imitation learning of movement styles in humanoid robotics.

Fast logistic regression for text categorization with variable-length n-grams

A common representation used in text categorization is the bag of words model (aka. unigram model). Learning with this particular representation involves typically some preprocessing, e.g. stopwords-removal, stemming. This results in one explicit tokenization of the corpus. In this work, we introduce a logistic regression approach where learning involves automatic tokenization. This allows us to weaken the a-priori required knowledge about the corpus and results in a tokenization with variable-length (word or character) n-grams as basic tokens. We accomplish this by solving logistic regression using gradient ascent in the space of all ngrams. We show that this can be done very efficiently using a branch and bound approach which chooses the maximum gradient ascent direction projected onto a single dimension (i.e., candidate feature). Although the space is very large, our method allows us to investigate variable-length n-gram learning. We demonstrate the efficiency of our approach compared to state-of-the-art classifiers used for text categorization such as cyclic coordinate descent logistic regression and support vector machines.

Building Sparse Large Margin Classifiers

This paper presents an approach to build Sparse Large Margin Classifiers (SLMC) by adding one more constraint to the standard Support Vector Machine (SVM) training problem. The added constraint explicitly controls the sparseness of the classifier and an approach is provided to solve the formulated problem. When considering the dual of this problem. it can be seen that building an SLMC is equivalent to constructing an SVM with a modified kernel function. Further analysis of this kernel function indicates that the proposed approach essentially finds a discriminating subspace that can be spanned by a small number of vectors, and in this subspace different classes of data are linearly well separated. Experimental results over several classification benchmarks show that in most cases the proposed approach outperforms the state-of-art sparse learning algorithms.

Learning to Find Graph Pre-images

We present an approach to discretizing multivariate continuous data while learning the structure of a graphical model. We derive a joint scoring function from the principle of predictive accuracy, which inherently ensures the optimal trade-off between goodness of fit and model complexity including the number of discretization levels. Using the socalled finest grid implied by the data, our scoring function depends only on the number of data points in the various discretization levels (independent of the metric used in the continuous space). Our experiments with artificial data as well as with gene expression data show that discretization plays a crucial role regarding the resulting network structure.

Learning Depth from Stereo

We compare two approaches to the problem of estimating the depth of a point in space from observing its image position in two different cameras: 1. The classical photogrammetric approach explicitly models the two cameras and estimates their intrinsic and extrinsic parameters using a tedious calibration procedure; 2. A generic machine learning approach where the mapping from image to spatial coordinates is directly approximated by a Gaussian Process regression. Our results show that the generic learning approach, in addition to simplifying the procedure of calibration, can lead to higher depth accuracies than classical calibration although no specific domain knowledge is used.

Efficient Approximations for Support Vector Machines in Object Detection

We present a new approximation scheme for support vector decision functions in object detection. In the present approach we are building on an existing algorithm where the set of support vectors is replaced by a smaller so-called reduced set of synthetic points. Instead of finding the reduced set via unconstrained optimization, we impose a structural constraint on the synthetic vectors such that the resulting approximation can be evaluated via separable filters. Applications that require scanning an entire image can benefit from this representation: when using separable filters, the average computational complexity for evaluating a reduced set vector on a test patch of size h x w drops from O(h.w) to O(h+w). We show experimental results on handwritten digits and face detection.

Multivariate Regression via Stiefel Manifold Constraints

We introduce a learning technique for regression between high-dimensional spaces. Standard methods typically reduce this task to many one-dimensional problems, with each output dimension considered independently. By contrast, in our approach the feature construction and the regression estimation are performed jointly, directly minimizing a loss function that we specify, subject to a rank constraint. A major advantage of this approach is that the loss is no longer chosen according to the algorithmic requirements, but can be tailored to the characteristics of the task at hand; the features will then be optimal with respect to this objective, and dependence between the outputs can be exploited.

On the simplification of an examples-based controller with support vector machines

Examples-based controllers use historical data to evaluate local approximation models. Large data sets make it prohibitively expensive to evaluate the best control action in real time. Support vector machines (SVM) are known for their ability to identify the minimal set of data points needed to reconstruct an optimal decision surface. A successful application is presented: the simplification of a six-dimensional robotic controller. The SVM reduced the size of the data set to 5.3% of its original size while retaining 99.7% classification accuracy, thus leading the way to online implementation. The results indicate that SVM may be highly effective for the simplification of examples-based controllers.