We propose novel gaze control algorithms for active perception in mobile autonomous agents with directable, foveated vision sensors. Our agents are realistic artificial animals, o...
The apparent motion reveals what in an image that human vision detects first. Chen's assumption that early stage vision can percept global topology is proved incorrect in the...
Abstract. We investigate the extent to which eye movements in natural dynamic scenes can be predicted with a simple model of bottom-up saliency, which learns on different visual re...
Eleonora Vig, Michael Dorr, Thomas Martinetz, Erha...
Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in...
VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and student...