We extend the work of Black and Yacoob (1995) on the tracking and recognition of human
facial expressions using parametrized models of optical flow to deal with the articulated …

A neural network theory of three-dimensional (3-D) vision, called FACADE theory, is
described. The theory proposes a solution of the classical figure-ground problem for …

Shimon Edelman bases a comprehensive approach to visual representation on the notion of
correspondence between proximal (internal) and distal similarities in objects. Researchers …

Аннотация Если вы хотите создать интуитивно понятный и привлекательный дизайн
для вебсайта, программы, товара или бренда, вы должны знать, что лежит в основе …

A theoretical framework is proposed to understand binocular visual surface perception
based on the idea of a mobile observer sampling images from random vantage points in …

A method for recognition of superquadrics from image contours is presented. The image
contour considered here is a 2-D occluding contour assuming parallel projection. The …

Image regions corresponding to partially hidden objects are enclosed by two types of
bounding contour: those inherent to the object itself (intrinsic) and those defined by …

In the arts and sciences, as well as in our daily lives, symmetry has made a profound and
lasting impact. Likewise, a computational treatment of symmetry and group theory (the …

" This is a very thorough and complete text that is very well written. I was particularly
impressed that the book incorporated and integrated the literatures on neuroscience and …

A representation of objects by their parts is the dominant strategy for representing complex
3D objects in many disciplines. In computer vision and robotics, superquadrics are among …