We present our work towards creating a dataset, which is intended to be used for the implementation of a home care services system for the deaf. The dataset includes recorded realistic scenarios of interactions between deaf patients and mental health experts in their native sign language. The scenarios allow for contextualized representations, in contrast to typical datasets presenting isolated signs or sentences. It includes continuous videos in RGB and depth, which are challenging to analyze and closely resemble real-life scenarios. The research on representation of signs is supported by providing the hand shapes and trajectories for every video using hand and skeleton models, as well as facial features. Furthermore, the dataset may be used for studying the emotional context, since such conversations are typically emotionally charged.

Using a classical result on algebraic invariants of the unimodular group, we present in this paper some basic geometric affine invariant quantities, and we use them to construct some distinctive descriptors for object detection. Although full affine invariance cannot be guaranteed due to noncommutativity of camera blur with affine maps and the domain problem (that is, the difficulty of finding an affine covariant domain), the proposed descriptors behave more robustly than SIFT with respect to affine deformations. This is supported by our comparisons both with the version of SIFT computed on an affine normalized neighborhood, and with ASIFT, which solves both the previously mentioned camera blur and domain problems by cleverly sampling the orbit of affine transformations of the images.

We present a method for detecting appearances of logos in low-resolution video sequences. The method is based on matching of SIFT descriptors, plus several heuristics. The logos must come from a small database of possible logos. The emphasis is not on speed but on reliability, although the method can be executed in real time using a parallel computer.

In this paper, we present an incremental method for model selection and learning of Gaussian mixtures based on the recently proposed variational Bayes approach. The method adds components to the mixture using a Bayesian splitting test procedure: a component is split into two components and then variational update equations are applied only to the parameters of the two components. As a result, either both components are retained in the model or one of them is found to be redundant and is eliminated from the model. In our approach, the model selection problem is treated locally, in a region of the data space, so we can set more informative priors based on the local data distribution. A modified Bayesian mixture model is presented to implement this approach, along with a learning algorithm that iteratively applies a splitting test on each mixture component. Experimental results and comparisons with two other techniques testify for the adequacy of the proposed approach.

We present a Bayesian method for mixture model training that simultaneously treats the feature selection and the model selection problem. The method is based on the integration of a mixture model formulation that takes into account the saliency of the features and a Bayesian approach to mixture learning that can be used to estimate the number of mixture components. The proposed learning algorithm follows the variational framework and can simultaneously optimize over the number of components, the saliency of the features, and the parameters of the mixture model. Experimental results using high-dimensional artificial and real data illustrate the effectiveness of the method.

The probabilistic radial basis function (PRBF) network constitutes a probabilistic version of the RBF network for classification that extends the typical mixture model approach to classification by allowing the sharing of mixture components among all classes. The typical learning method of PRBF for a classification task employs the expectation-maximization (EM) algorithm and depends strongly on the initial parameter values. In this paper, we propose a technique for incremental training of the PRBF network for classification. The proposed algorithm starts with a single component and incrementally adds more components at appropriate positions in the data space. The addition of a new component is based on criteria for detecting a region in the data space that is crucial for the classification task. After the addition of all components, the algorithm splits every component of the network into subcomponents, each one corresponding to a different class. Experimental results using several well-known classification data sets indicate that the incremental method provides solutions of superior classification performance compared to the hierarchical PRBF training method. We also conducted comparative experiments with the support vector machines method and present the obtained results along with a qualitative comparison of the two approaches.