In this paper a novel method for view independent human movement representation and recognition, exploiting the rich information contained in multi-view videos, is proposed. The bi...
Nikolaos Gkalelis, Nikos Nikolaidis, Ioannis Pitas
Background: Most genomic data have ultra-high dimensions with more than 10,000 genes (probes). Regularization methods with L1 and Lp penalty have been extensively studied in survi...
Zhenqiu Liu, Dechang Chen, Ming Tan, Feng Jiang, R...
Abstract--1D or linear barcodes are the black-and-whitestriped codes that can be found on most consumer products. This work evaluates existing 1D barcode scanners for mobile phones...
Felix von Reischach, Stephan Karpischek, Florian M...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The us...