Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
A scheme, named tower of knowledge (ToK), is proposed for interpreting 3D scenes. The ToK encapsulates causal dependencies between object appearance and functionality. We demonstr...
We consider the problem of visual categorization with minimal supervision during training. We propose a partbased model that loosely captures structural information. We represent ...
This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously ...
Aswin C. Sankaranarayanan, Rama Chellappa, Qinfen ...
Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supp...