Deep Residual Networks have recently been shown to significantly improve the
performance of neural networks trained on ImageNet, with results beating all previous …

In the last few years, the deep learning (DL) computing paradigm has been deemed the
Gold Standard in the machine learning (ML) community. Moreover, it has gradually become …

Steganography is the art of concealing information in a cover media in such a way that the
presence of the information is unknown. Digital image steganography accomplishes the …

Abstract Analysis of skin lesion images via visual inspection and manual examination to
diagnose skin cancer has always been cumbersome. This manual examination of skin …

Computer vision techniques, in conjunction with acquisition through remote cameras and
unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure …

Transfer-learning methods aim to improve performance in a data-scarce target domain using
a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing …

Digital steganography has a long history, starting to be developed in the 90s until now. The
main aspects of early steganography are security, imperceptibility, and payload. Security is …

Purpose To build a deep learning model to diagnose glaucoma using fundus photography.
Design Cross sectional case study Subjects, Participants and Controls: A total of 1,542 …

Smart grid and microgrid technology based on energy storage systems (ESS) and
renewable energy are attracting significant attention in addressing the challenges …

Understanding urban scenes is a fundamental capability required of intelligent vehicles.
Depth cues provide useful geometric information for semantic segmentation, thus …