Abstract. This paper presents a new framework for the motion segmentation and estimation task on sequences of two grey images without a priori information of the number of moving r...
— In this work, we perform an extensive statistical evaluation for learning and recognition of object manipulation actions. We concentrate on single arm/hand actions but study th...
The paper considers making inferences about the underlying true 2-D motion when only evaluations of a local block-based cost function, the mean of absolute or squared differences,...
In this paper, an efficient method using various histogrambased (high-dimensional) image content descriptors for automatically classifying general color photos into relevant categ...
For software and more illustrations: http://www.psi.utoronto.ca/anitha/fastTCA.htm Dimensionality reduction techniques such as principal component analysis and factor analysis are...