Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new r...
Abstract—The idea of an online visual vocabulary is proposed. In contrast to the accepted strategy of generating vocabularies offline, using the k-means clustering over all the ...
Abstract—Segmentation of architectural floorplans is a challenging task, mainly because of the large variability in the notation between different plans. In general, traditional...
Human eyes are highly efficient devices for scanning through a large quantity of low-level visual sensory data and delivering selective information to one’s brain for high-level...
This paper describes a safe and efficient combination of the object-based message-driven execution and shared array parallel programming models. In particular, we demonstrate how ...
Phil Miller, Aaron Becker, Laxmikant V. Kalé...