Abstract. A tracking-by-detection framework is proposed that combines nearest-neighbor classification of bags of features, efficient subwindow search, and a novel feature selection...
This paper presents a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is t...
In this paper, we applied online neuroevolution to evolve nonplayer characters for The Open Racing Car Simulator (TORCS). While previous approaches allowed online learning with per...
Luigi Cardamone, Daniele Loiacono, Pier Luca Lanzi
We propose a novel system for associating multi-target tracks across multiple non-overlapping cameras by an on-line learned discriminative appearance affinity model. Collecting rel...
A vision-based automatic tracking system for ocean animals in the midwater has been demonstrated in Monterey Bay, CA. Currently, the input to this system is a measurement of relati...