In this work, we are interested in technologies that will allow users to actively browse and navigate large image databases and to retrieve images through interactive fast browsin...
We introduce the first visual dataset of fast foods with a total of 4,545 still images, 606 stereo pairs, 303 3600 videos for structure from motion, and 27 privacy-preserving vide...
— We describe a framework for finding and tracking “trails” for autonomous outdoor robot navigation. Through a combination of visual cues and ladar-derived structural inform...
Background: In the fly Drosophila melanogaster, new genetic, physiological, molecular and behavioral techniques for the functional analysis of the brain are rapidly accumulating. ...
Arnim Jenett, Johannes E. Schindelin, Martin Heise...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...