Recognizing object classes and their 3D viewpoints is an
important problem in computer vision. Based on a partbased
probabilistic representation [31], we propose a new
3D object...
This paper presents a method for registering images at different magnifications (scales) by treating the problem not only as one of scaling the image coordinates but also as one i...
We propose a geometric approach to 3-D motion segmentation from point correspondences in three perspective views. We demonstrate that after applying a polynomial embedding to the ...
A good distance metric is crucial for unsupervised learning from high-dimensional data. To learn a metric without any constraint or class label information, most unsupervised metr...
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...