In this paper, we develop a novel method for view-based recognition of human action/activity from videos. By observing just a few frames, we can identify the activity that takes pl...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Feature selection methods are often used to determine a small set of informative features that guarantee good classification results. Such procedures usually consist of two compon...
Artsiom Harol, Carmen Lai, Elzbieta Pekalska, Robe...
In this paper we present a two-level generative model for representing the images and surface depth maps of drapery and clothes. The upper level consists of a number of folds whic...
—This paper presents a novel method for 3D surface reconstruction that uses polarization and shading information from two views. The method relies on the polarization data acquir...