We present an accurate, interactive silhouette extraction mechanism for texture-based volume rendering. Compared to previous approaches, our system guarantees silhouettes of a use...
We present a 3D face reconstruction system that takes as input either one single view or several different views. Given a facial image, we first classify the facial pose into one...
We present a method to identify and localize people by leveraging existing CCTV camera infrastructure along with inertial sensors (accelerometer and magnetometer) within each pers...
Although facial features are considered to be essential for humans to understand sign language, no prior research work has yet examined their significance for automatic sign langu...
Ulrich von Agris, Moritz Knorr, Karl-Friedrich Kra...
Social media are constructed from the collective contributions of potentially millions of individuals and present an increasingly common and large scale form of database. As these...