Abstract. Supervised classifiers require manually labeled training samples to classify unlabeled objects. Active Learning (AL) can be used to selectively label only “ambiguous...
— Matching images with large geometric and iconic changes (e.g. faces under different poses and facial expressions) is an open research problem in computer vision. There are two ...
Multiple-instance learning (MIL) is a generalization of the supervised learning problem where each training observation is a labeled bag of unlabeled instances. Several supervised ...
As tracking systems become more effective at reliably tracking multiple objects over extended periods of time within single camera views and across overlapping camera views, incre...
In this paper we discuss different views of learning and what it means to follow rules. The activities, the language and context of expertise and knowledge have traditionally ofte...