In this paper, we present an efficient and robust subspace learning based object tracking algorithm with special illumination handling. Illumination variances pose a great challen...
Decision trees have been widely used for online learning classification. Many approaches usually need large data stream to finish decision trees induction, as show notable limitat...
Abstract. Automatic delineation of the prostate boundary in transrectal ultrasound (TRUS) can play a key role in image-guided prostate intervention. However, it is a very challengi...
In real life, visual learning is supposed to be a continuous process. Humans have an innate facility to recognize objects even under less-than-ideal conditions and to build robust ...
We present a category learning vector quantization (cLVQ) approach for incremental and life-long learning of multiple visual categories where we focus on approaching the stability-...
Stephan Kirstein, Heiko Wersing, Horst-Michael Gro...