Global shape information is an effective top-down complement
to bottom-up figure-ground segmentation as well
as a useful constraint to avoid drift during adaptive tracking.
We p...
Abstract. In this paper we present an efficient technique to obtain accurate semantic classification on the pixel level capable of integrating various modalities, such as color, ed...
Stefan Kluckner, Thomas Mauthner, Peter M. Roth, H...
Weathering phenomena represent a topic of growing interest in computer graphics, and corrosion reactions are of great importance since they affect a large number of different fiel...
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
Abstract. This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned ...
Jamie Shotton, John M. Winn, Carsten Rother, Anton...