In this paper, we study the problem of nonnegative graph
embedding, originally investigated in [14] for reaping the
benefits from both nonnegative data factorization and the
spe...
Changhu Wang (University of Science and Technology...
Various powerful people detection methods exist. Surprisingly,
most approaches rely on static image features
only despite the obvious potential of motion information for
people ...
Christian Wojek (TU Darmstadt), Stefan Walk (TU Da...
Skeletonization algorithms typically decompose an object’s
silhouette into a set of symmetric parts, offering a
powerful representation for shape categorization. However,
havi...
Alex Levinshtein, Sven Dickinson, Cristian Sminchi...
This article proposes a solution of the Lambertian shape from shading (SFS) problem in the case of a pinhole camera model (performing a perspective projection). Our approach is ba...
This paper presents a complete framework for creating a speechenabled avatar from a single image of a person. Our approach uses a generic facial motion model which represents defo...