Showing papers by "Wentao Fan published in 2015"

Topic Novelty Detection Using Infinite Variational Inverted Dirichlet Mixture Models

Abstract: We propose model-based inference for topic novelty detection using a non-parametric Bayesian probability model. The probability model is a Dirichlet process mixture of inverted Dirichlet distributions which can be viewed as an infinite mixture model. The inference is based on variational Bayes deployed using approximate conjugate priors to the inverted Dirichlet. Detailed experimental study demonstrates the merits of our approach and shows that it gives good description of the data.

Face detection and facial expression recognition using simultaneous clustering and feature selection via an expectation propagation statistical learning framework

Abstract: In this paper, we focus on developing a novel framework which can be effectively used for both face detection (i.e. discriminate faces from non-face patterns) and facial expression recognition. The proposed statistical framework is based on a Dirichlet process mixture of generalized Dirichlet (GD) distributions used to model local binary pattern (LBP) features. Our method is built on nonparametric Bayesian analysis where the determination of the number of clusters is sidestepped by assuming an infinite number of mixture components. An unsupervised feature selection scheme is also integrated with the proposed nonparametric framework to improve modeling performance and generalization capabilities. By learning the proposed model using an expectation propagation (EP) inference approach, all the involved model parameters and feature saliencies can be evaluated simultaneously in a single optimization framework. Furthermore, the proposed framework is extended by adopting a localized feature selection scheme which has shown, according to our results, superior performance, to determine the most important facial features, as compared to the global one. The effectiveness and utility of the proposed method is illustrated through extensive empirical results using both synthetic data and two challenging applications involving face detection, and facial expression recognition.

Dynamic textures clustering using a hierarchical Pitman-Yor process mixture of Dirichlet distributions

Abstract: This paper proposes a hierarchical Pitman-Yor (HPY) process mixture of Dirichlet distributions. It can be viewed as an extension of our previous works that have considered Dirich-let process mixtures of Dirichlet distributions (i.e. infinite Dirichlet mixture models). The proposed model is learned via a variational Bayes approach and applied to the challenging problem of dynamic textures clustering.

Human Action Recognition Using Accelerated Variational Learning of Infinite Dirichlet Mixture Models

Abstract: Exploiting Dirichlet process mixture models (also known as infinite mixture models) to model visual and textual data is now standard weapon in the arsenal of machine learning. This paper proposes a new accelerated variational inference approach to learn Dirichlet process mixture models with Dirichlet distributions. The choice of using Dirichlet distribution as the basic distribution is mainly due to its flexibility for modeling proportional data. Indeed, this kind of data is naturally generated by several applications involving the representation of texts, images and videos using the bag-of-words (or "visual words" in the case of images and videos) approach. The potential of the developed learning framework is shown using a challenging real application namely human action recognition in videos.

3D object modeling and recognition via online hierarchical Pitman-yor process mixture learning

Abstract: We present a statistical framework for 3D objects modeling and recognition. Our framework is based on describing 3D objects using local descriptors from which a visual vocabulary if built and on a hierarchical Pitman-Yor process mixture of Beta-Liouville distributions. An online approach based on variational Bayes is developed for the learning of the proposed framework. The merits of our model are shown via extensive experiments.

Recognition and Clustering of Dirichlet Mixtures

Abstract: Finite mixture models of Dirichlet distributions arise in a natural way in several applications involving proportional data. The basic model assumes that the unknown density can be written as a weighted finite sum of Dirichlet distributions, with different mixing weights and different parameters. In this article, on the one hand, we aim to present the finite Dirichlet mixture. On the other hand, we discuss two learning approaches to estimate the parameters of this mixture when dealing with the case of an unknown number of components. We also show the potential of the Dirichlet mixture through a series of experiments involving artificial data and real data that concern the challenging problem of images categorization. Keywords: clustering; Dirichlet distribution; EM; mixture model; variational learning