Illumination inconsistencies cause serious problems for classical computer vision applications such as tracking and stereo matching. We present a new approach to model illuminatio...
We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach...
Recently, a novel Log-Euclidean Riemannian metric [28] is proposed for statistics on symmetric positive definite (SPD) matrices. Under this metric, distances and Riemannian means ...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, ...
Most existing subspace analysis-based tracking algorithms utilize a flattened vector to represent a target, resulting in a high dimensional data learning problem. Recently, subspa...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, ...
We present an approach for illumination and affineinvariant point matching using ordinal features. Ordinal measures for matching only consider the order between pixels and not the...