In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
We propose a system for the automatic segmentation of novelties from the background in scenarios where multiple images of the same environment are available e.g. obtained by weara...
Omid Aghazadeh, Josephine Sullivan, Stefan Carlsso...
Recovering 3D geometry from a single 2D line drawing is an important and challenging problem in computer vision. It has wide applications in interactive 3D modeling from images, c...
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured v...
Leonid Pishchulin, Arjun Jain, Mykhaylo Andriluka,...
Abstract This paper explores the impact that landmark parametrization has in the performance of monocular, EKFbased, 6-DOF simultaneous localization and mapping (SLAM) in the conte...