Hotelling’s Canonical Correlation Analysis (CCA) works with two sets of related variables, also called views, and its goal is to find their linear projections with maximal mutual...
Empirical evidence shows that in favorable situations semi-supervised learning (SSL) algorithms can capitalize on the abundance of unlabeled training data to improve the performan...
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao...
We propose an approach to improving the detection results of a generic offline trained detector on a specific video. Our method does not leverage visual tracking as most detecti...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...