Tracking objects over the video frames finds many applications in surveillance [13], human activity analysis [4] and gesture recognition [6],[12]. It becomes a very challenging task if the appearence and the dynamics of the object varies over successive frames. It becomes important to include elements of nonlinearity and non-Gaussianity in order to model accurately the underlying dynamics of a ...

This paper describes a novel importance sampling method with applications in multimodal optimization. Based on initial results, the method seems suitable for real-time computer vision, and enables an efficient frame-by-frame global search with no initialization step. The method is based on importance sampling with adaptive subdivision, developed by Kajiya, Painter, and Sloan in the context of s...

The paper describes a simple, generic and yet highly accurate Efficient Importance Sampling (EIS) Monte Carlo (MC) procedure for the evaluation of high-dimensional numerical integrals. EIS is based upon a sequence of auxiliary weighted regressions which actually are linear under appropriate conditions. It can be used to evaluate likelihood functions and byproducts thereof, such as ML estimators...

We present an alternative approach to the problem of estimating probabilities of rare events and for optimization problems using the class of Rényi divergences of order α > 1. The general procedure we describe does not involve any specific family of distributions, the only restriction is that the search space consists of product form probability density functions. We discuss an algorithm for es...

Computing the exact likelihood of data in large Bayesian networks consisting of thousands of vertices is often a difficult task. When these models contain many deterministic conditional probability tables and when the observed values are extremely unlikely even alternative algorithms such as variational methods and stochastic sampling often perform poorly. We present a new importance sampling a...

An appearance-based EigenTracker can track objects which simultaneously undergo image motions as well as changes in view. This paper enhances the framework in two ways. First, we incorporate a novel CONDENSATION-based predictive framework to speed up the EigenTracker. Next, our scheme is on-line: we use efficient eigenspace updates to track unknown objects. We use Importance Sampling for enhanc...

Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one single batch. In the adversarial learning of N real training samples and M generated samples, the target of discriminator training is to distribute all the probability mass to th...

A framework for real-time tracking of complex non-rigid objects is presented. The object shape is approximated by an ellipse and its appearance by histogram based features derived from local image properties. An efficient search procedure is used to find the image region with a histogram most similar to the histogram of the tracked object. The procedure is a natural extension of the mean-shift ...

Additional author information --J.R.G.: Also Ph.D. Candidate at the Electrical Engineering Department, School of Engineering and Applied Science, The George Washington University, Ashburn, VA, USA 20147. ABSTRACT A brief introduction to the widely spread theory of Importance Sampling is given. Several approaches to the optimization of the twisted density function are described, such as: i) usin...

Monte Carlo rendering algorithms generally rely on some form of importance sampling to evaluate the measurement equation. Most of these importance sampling methods only take local information into account, however, so the actual importance function used may not closely resemble the light distribution in the scene. In this paper, we present Table-driven Adaptive Importance Sampling (TAIS), a sam...