We present a probabilistic framework for recognizing objects in images of cluttered scenes. Hundreds of objects may be considered and searched in parallel. Each object is learned f...
This paper proposes an approach to 2D gesture recognition that models each gesture as a Finite State Machine (FSM) in spatial-temporal space. The model construction works in a sem...
We use 2-Dimensional language to construct 2-Dimensional computer graphics model, use MSO or other logics to specify some graph property, and use automata model checking technique ...
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
Abstract. Class hierarchies are commonly used to reduce the complexity of the classification problem. This is crucial when dealing with a large number of categories. In this work, ...