We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new...
Recent research has studied the role of sparsity in high dimensional regression and signal reconstruction, establishing theoretical limits for recovering sparse models from sparse...
Shuheng Zhou, John D. Lafferty, Larry A. Wasserman
Traditional dynamical systems used for motion tracking cannot effectively handle high dimensionality of the motion states and composite dynamics. In this paper, to address both is...
Abstract. We propose an approach for modeling the navigational behavior of Web users based on task-level patterns. The discovered “tasks” are characterized probabilistically as...
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...