We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. To this end we combine three ingredients: (i...
A common design of an object recognition system has
two steps, a detection step followed by a foreground withinclass
classification step. For example, consider face detection
by...
Constraint satisfaction problems (CSPs) are ubiquitous in many real-world contexts. However, modeling a problem as a CSP can be very challenging, usually requiring considerable ex...
Abstract. This paper addresses the problem of recovering the generating curve of a surface of revolution from a single uncalibrated perspective view, based solely on the object’s...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...