In this article, we extend a local prototype-based learning model by active learning, which gives the learner the capability to select training samples during the model adaptation...
Frank-Michael Schleif, Barbara Hammer, Thomas Vill...
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...
Shape from shading (SfS) has always been difficult for real applications due to its intrinsic ill-posedness. In this paper, we propose an interactive SfS method which efficiently ...
Gang Zeng, Yasuyuki Matsushita, Long Quan, Heung-Y...
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
People re-detection aims at performing re-identification of people who leave the scene and reappear after some time. This is an important problem especially in video surveillance ...