The problem of simultaneous feature extraction and selection, for classifier design, is considered. A new framework is proposed, based on boosting algorithms that can either 1) s...
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. First, we address this issue as ...
This paper investigates how to parse (segment) facial components from face images which may be partially occluded. We propose a novel face parser, which recasts segmentation of fa...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Metric learning is a fundamental problem in computer vision. Different features and algorithms may tackle a problem from different angles, and thus often provide complementary inf...
Bo Wang, Jiayan Jiang, Wei Wang 0028, Zhi-Hua Zhou...