Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
Psychological experiments on children's development of spatial knowledge suggest experience at self-locomotion with visual tracking as important factors. Yet, the mechanism u...
We describe a framework for learning an object classifier from a single example. This goal is achieved by emphasizing the relevant dimensions for classification using available ex...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...