Bias/variance analysis is a useful tool for investigating the performance of machine learning algorithms. Conventional analysis decomposes loss into errors due to aspects of the le...
In this work, we propose a new robust and edge-preserving superresolution algorithm to simultaneously estimate all frames of a sequence. The new algorithm is based on the regulari...
We address optimal model estimation for model-based vector quantization for both the constrained resolution (CR) and constrained entropy (CE) cases. To this purpose we derive unde...
We present a novel pedestrian detection system based on probabilistic component assembly. A part-based model is proposed which uses three parts consisting of head-shoulder, torso a...
Martin Rapus, Stefan Munder, Gregory Baratoff, Joa...
A novel no-reference blockiness metric that can automatically and perceptually quantify blocking artifacts of DCT coding is presented. The proposed metric is built upon the specif...