We propose a new unsupervised learning method to obtain a layered pictorial structure (LPS) representation of an articulated object from video sequences. It will be seen that this...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
There are numerous rectangular signboards indoors and outdoors. The information contained in them, such as signs and text, is useful for robot navigation. In this paper, a system ...
Abstract. We apply independent component analysis (ICA) for learning an efficient color image representation of natural scenes. In the spectra of single pixels, the algorithm was a...
Te-Won Lee, Thomas Wachtler, Terrence J. Sejnowski
—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately i...
To reduce the cost of correcting design errors, assemblies of mechanical parts are modeled using CAD systems and verified electronically before the designs are sent to manufacturi...