-- This paper proposes a Wyner-Ziv / H.264 transcoder that enables low cost video applications. The proposed solution supports video encoding on resource constrained devices such a...
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
A variety of flexible models have been proposed to detect
objects in challenging real world scenes. Motivated
by some of the most successful techniques, we propose a
hierarchica...
Paul Schnitzspan (TU Darmstadt), Mario Fritz (Univ...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes a...