Abstract. This paper presents an approach to object discovery in a given unlabeled image set, based on mining repetitive spatial configurations of image contours. Contours that si...
One of the bottlenecks of current recognition (and graph matching) systems is their assumption of one-to-one feature (node) correspondence. This assumption breaks down in the gener...
Ali Shokoufandeh, Yakov Keselman, M. Fatih Demirci...
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
A key goal of far-field activity analysis is to learn the usual pattern of activity in a scene and to detect statistically anomalous behavior. We propose a method for unsupervised...
A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently...