We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human b...
Long Zhu, Yuanhao Chen, Yifei Lu, Chenxi Lin, Alan...
The goal of the knowledge discovery and data mining is to extract the useful knowledge from the given data. Visualization enables us to find structures, features, patterns, and re...
In facial image analysis, image resolution is an important factor which has great influence on the performance of face recognition systems. As for lowresolution face recognition p...
Bo Li, Hong Chang, Shiguang Shan, Xilin Chen, Wen ...
With the goal of reducing computational costs without sacrificing accuracy, we describe two algorithms to find sets of prototypes for nearest neighbor classification. Here, the te...
We develop a novel method for fitting high-resolution template meshes to detailed human body range scans with sparse 3D markers. We formulate an optimization problem in which the ...