—We study the problem of approximating a 3D solid with a union of overlapping spheres. In comparison with a stateof-the-art approach, our method offers more than an order of magn...
—Many face recognition algorithms use “distance-based” methods: Feature vectors are extracted from each face and distances in feature space are compared to determine matches....
Simon Prince, Peng Li, Yun Fu, Umar Mohammed, Jame...
Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
—We introduce an efficient maximum likelihood approach for one part of the color constancy problem: removing from an image the color cast caused by the spectral distribution of ...
Abstract—Given the size and confidence of pairwise local orderings, angular embedding (AE) finds a global ordering with a nearglobal optimal eigensolution. As a quadratic crite...
Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a fle...
—In this paper, we present a comprehensive analysis of self-dual and m-idempotent operators. We refer to an operator as m-idempotent if it converges after m iterations. We focus ...
Nidhal Bouaynaya, Mohammed Charif-Chefchaouni, Dan...
—The problem of automatic and optimal design of embedded object detector cascades is considered. Two main challenges are identified: optimization of the cascade configuration and...