Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
Statistical learning methods are emerging as a valuable tool for decoding information from neural imaging data. The noisy signal and the limited number of training patterns that ar...
Background modeling and subtraction to detect new or moving objects in a scene is an important component of many intelligent video applications. Compared to a single camera, the u...
Ser-Nam Lim, Anurag Mittal, Larry S. Davis, Nikos ...
This paper introduces a method of enhancing an unattended ground sensor (UGS) system’s classification capability of humans via seismic signatures while subsequently discriminati...
In this paper, we present several enhanced network techniques which are appropriate for VLSI implementation and have reduced complexity, high throughput, and simple routing algori...