Media forensics and deepfakes: an overview

L Verdoliva - IEEE Journal of Selected Topics in Signal …, 2020 - ieeexplore.ieee.org
With the rapid progress in recent years, techniques that generate and manipulate multimedia
content can now provide a very advanced level of realism. The boundary between real and …

Novel ligands for the affinity-chromatographic purification of antibodies

G Fassina, M Ruvo, G Palombo, A Verdoliva… - Journal of biochemical …, 2001 - Elsevier
Affinity chromatography represents one of the most powerful fractionation techniques for the
large-scale purification of biotechnological products. Despite its potential, the use of this …

[HTML][HTML] Zeolites as acid/basic solid catalysts: recent synthetic developments

V Verdoliva, M Saviano, S De Luca - Catalysts, 2019 - mdpi.com
The zeolites are porous solid structures characterized by a particular framework of aluminosilicates,
in which the incorporation of the Al +3 ions generates an excess of negative charge …

Faceforensics++: Learning to detect manipulated facial images

A Rossler, D Cozzolino, L Verdoliva… - Proceedings of the …, 2019 - openaccess.thecvf.com
The rapid progress in synthetic image generation and manipulation has now come to a point
where it raises significant concerns for the implications towards society. At best, this leads …

[HTML][HTML] Pansharpening by convolutional neural networks

G Masi, D Cozzolino, L Verdoliva, G Scarpa - Remote Sensing, 2016 - mdpi.com
A new pansharpening method is proposed, based on convolutional neural networks. We
adapt a simple and effective three-layer architecture recently proposed for super-resolution to …

Land use classification in remote sensing images by convolutional neural networks

…, G Poggi, C Sansone, L Verdoliva - arXiv preprint arXiv …, 2015 - arxiv.org
We explore the use of convolutional neural networks for the semantic classification of
remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are …

A nonlocal SAR image denoising algorithm based on LLMMSE wavelet shrinkage

…, CV Angelino, L Verdoliva - IEEE Transactions on …, 2011 - ieeexplore.ieee.org
We propose a novel despeckling algorithm for synthetic aperture radar (SAR) images based
on the concepts of nonlocal filtering and wavelet-domain shrinkage. It follows the structure …

Efficient dense-field copy–move forgery detection

…, G Poggi, L Verdoliva - IEEE Transactions on …, 2015 - ieeexplore.ieee.org
We propose a new algorithm for the accurate detection and localization of copy-move
forgeries, based on rotation-invariant features computed densely on the image. Dense-field …

Faceforensics: A large-scale video dataset for forgery detection in human faces

A Rössler, D Cozzolino, L Verdoliva, C Riess… - arXiv preprint arXiv …, 2018 - arxiv.org
With recent advances in computer vision and graphics, it is now possible to generate videos
with extremely realistic synthetic faces, even in real time. Countless applications are …

Noiseprint: A CNN-based camera model fingerprint

D Cozzolino, L Verdoliva - IEEE Transactions on Information …, 2019 - ieeexplore.ieee.org
Forensic analyses of digital images rely heavily on the traces of in-camera and out-camera
processes left on the acquired images. Such traces represent a sort of camera fingerprint. If …