Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
The fast Gauss transform allows for the calculation of the sum of N Gaussians at M points in O(N + M) time. Here, we extend the algorithm to a wider class of kernels, motivated by ...
Marina Spivak, Shravan K. Veerapaneni, Leslie Gree...
This paper presents a complete framework for attention-based video streaming for low bandwidth networks. First, motivated by the fovea-periphery distinction of biological vision s...
Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain const...
Abstract--Sensor networks have been widely used for surveillance, monitoring, and tracking. Camera networks, in particular, provide a large amount of information that has tradition...
Edgar J. Lobaton, Ramanarayan Vasudevan, Ruzena Ba...