Abstract: Feature extraction and selection in the presence of nonlinear dependencies among the data is a fundamental challenge in unsupervised learning. We propose using a Gram-Schmidt (GS) type ...
Abstract: To address the deficiencies of frequently missed detections of small targets and low accuracy under occlusion scenarios, this paper proposes a feature extraction network based on attention ...
A team led by Rensselaer Polytechnic Institute (RPI) professors Georges Belfort, Ph.D. (PI), and Pankaj Karande, Ph.D. (co-PI ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback