This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
We present a novel discriminative-generative hybrid approach in this paper, with emphasis on application in multiview object detection. Our method includes a novel generative mode...
—We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selectio...