This paper proposes a new tracking algorithm which combines object and background information, via building object and background appearance models simultaneously by nonparametric...
Many object-oriented frameworks exhibit a high density of design pattern applications. Usually, there are more instances in a framework than there are abstract classes. Yet, only ...
Dirk Riehle, Roger Brudermann, Thomas R. Gross, Ka...
This paper proposes a computational system of object categorization based on decomposition and adaptive fusion of visual information. A coupled Conditional Random Field is develop...
We consider visual category recognition in the framework of measuring similarities, or equivalently perceptual distances, to prototype examples of categories. This approach is qui...
Alexander C. Berg, Hao Zhang 0003, Jitendra Malik,...
Feature selection is fundamental to knowledge discovery from massive amount of high-dimensional data. In an effort to establish theoretical justification for feature selection al...