Abstract. AND/OR search spaces are a unifying paradigm for advanced algorithmic schemes for graphical models. The main virtue of this representation is its sensitivity to the struc...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
As Global Positioning System (GPS) receivers become a common feature in cell phones, personal digital assistants, and automobiles, there is a growing interest in tracking larger us...
In this paper, we focus on methodology of finding a classifier with a minimal cost in presence of additional performance constraints. ROCCH analysis, where accuracy and cost are i...
In a pattern classification setup, image segmentation is achieved by assigning each pixel to one of two classes: object or background. The special case of vessel segmentation is c...