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...
Modern approaches to speaker recognition (verification) operate in a space of “supervectors” created via concatenation of the mean vectors of a Gaussian mixture model (GMM) a...
Balaji Vasan Srinivasan, Dmitry N. Zotkin, Ramani ...
We address the problem of multi-person tracking in a complex scene from a single camera. Although trackletassociation methods have shown impressive results in several challenging ...
— We present a computational model of human category learning that learns the essential structures of the categories by forgetting information that is not useful for the given ta...
Abstract. In this paper we introduce a novel approach for learning view-invariant gait representation that does not require synthesizing particular views or any camera calibration....