Object detection is challenging partly due to the limited discriminative power of local feature descriptors. We amend this limitation by incorporating spatial constraints among ne...
In this paper we propose extensions to the match propagation algorithm which is a technique for computing quasidense point correspondences between two views. The extensions make t...
This paper presents a novel framework of hybrid camera pose tracking system for outdoor navigation system. Traditional vision based or inertial sensor based solutions are mostly d...
Francisco Lamosa, Hanqing Lu, Keiichi Uchimura, Zh...
This paper presents a complete framework for creating a speechenabled avatar from a single image of a person. Our approach uses a generic facial motion model which represents defo...
The paper is concerned with two-class active learning. While the common approach for collecting data in active learning is to select samples close to the classification boundary,...