We present a method to learn visual attributes (eg.“red”,
“metal”, “spotted”) and object classes (eg. “car”,
“dress”, “umbrella”) together. We assume imag...
The visual hull relates the shape of an object to its silhouettes. This paper develops the theory of the visual hull of piecewise smooth objects, as those used in CAD applications...
Objects of interest are represented in the brain simultaneously in different frames of reference. Knowing the positions of one’s head and eyes, for example, one can compute the...
Cornelius Weber, David Muse, Mark Elshaw, Stefan W...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...