We propose an algorithm to perform causal inference of the state of a dynamical model when the measurements are corrupted by outliers. While the optimal (maximumlikelihood) soluti...
Andrea Vedaldi, Hailin Jin, Paolo Favaro, Stefano ...
We present an approach to 3D scene flow estimation, which exploits that in realistic scenarios image motion is frequently dominated by observer motion and independent, but rigid ...
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...
Sorting hierarchical data in external memory is necessary for a wide variety of applications including archiving scientific data and dealing with large XML datasets. The topic of ...
In this paper we explore database segmentation in the context of a column-store DBMS targeted at a scientific database. We present a novel hardware- and scheme-oblivious segmentati...