This paper presents a technique to detect instances of classes (objects) according to their semantic definition in the form of a Description Graph. Classes are defined as combinat...
In this paper we present a probabilistic framework for tracking objects based on local dynamic segmentation. We view the segn to be a Markov labeling process and abstract it as a ...
This paper addresses the problem of matching visual parts of video sequences from within a large collection. The visual content of a video sequence is described by the set of the ...
Rate-Distortion optimization can significantly improve encoder performance in MPEG-like video coding applications especially when it is applied to coding mode selection and motion...
This paper presents an efficient method to integrate various spatial-temporal constraints to regularize the contour tracking. The global shape of the contour is represented in a p...