We introduce perturbation kernels, a new class of similarity measure for information retrieval that casts word similarity in terms of multi-task learning. Perturbation kernels mode...
Chinese NE (Named Entity) recognition is a difficult problem because of the uncertainty in word segmentation and flexibility in language structure. This paper proposes the use of ...
Abstract. In concrete environments, where uncertainty and dynamism are pervasive and time and resources are limited, reasoning and decision-making processes raise important problem...
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
Prateek Jain (University of Texas at Austin), Ashi...
Abstract. In this paper we propose a new approach for tracking multiple objects in image sequences. The proposed approach differs from existing ones in important aspects of the re...