Despite the importance of pointing-device movement to efficiency in interfaces, little is known on how target shape impacts speed, acceleration, and other kinematic properties of ...
Jaime Ruiz, David Tausky, Andrea Bunt, Edward Lank...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
Abstract. We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation s...
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classificat...
We consider the use of medial surfaces to represent symmetries of cts. This allows for a qualitative abstraction based on a directed acyclic graph of components and also a degree o...
Juan Zhang, Kaleem Siddiqi, Diego Macrini, Ali Sho...