This work proposes to learn visual encodings of attention patterns that enables sequential attention for object detection in real world environments. The system embeds a saccadic d...
In this paper we present a new probabilistic feature-based approach to multi-hypothesis global localization and pose tracking. Hypotheses are generated using a constraintbased sea...
Global region-based active contours, like the Chan-Vese model, often make strong assumptions on the intensity distributions of the searched object and background, preventing their ...
Much attention has been given to CONDENSATION methods for mobile robot localization. This has resulted in somewhat of a breakthrough in representing uncertainty for mobile robots....
Patric Jensfelt, David J. Austin, Olle Wijk, Magnu...
Image spam is a new obfuscating method which spammers invented to more effectively bypass conventional text based spam filters. In this paper, we extract local invariant features ...
Haiqiang Zuo, Weiming Hu, Ou Wu, Yunfei Chen, Guan...