Graphical models are a framework for representing and exploiting prior conditional independence structures within distributions using graphs. In the Gaussian case, these models are...
Recently, in generic object recognition research, a classification technique based on integration of image features is garnering much attention. However, with a classifying techn...
We define a probe to be a single action sequence computed greedily from a given state that either terminates in the goal or fails. We show that by designing these probes carefull...
— Common human actions are instantly recognizable by people and increasingly machines need to understand this language if they are to engage smoothly with people. Here we introdu...
Texture classification is mainly used for segmentation of texture regions and content-based access to image databases. Lately these texture classification patterns have been appl...