We introduce a method to accelerate the evaluation of object detection cascades with the help of a divide-andconquer procedure in the space of candidate regions. Compared to the e...
Here we present a new approach to automatically detect and count breeding Greater Flamingos (Phoenicopterus Roseus) on aerial photographsof their colonies. We consider a stochasti...
Object recognition has made great strides recently. However, the best methods, such as those based on kernelSVMs are highly computationally intensive. The problem of how to accele...
Most tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework called Hidden Markov Model, where the distribution of the object state a...
In this paper we propose a method for continuous learning of simple visual concepts. The method continuously associates words describing observed scenes with automatically extracte...