Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors

no code implementations • 7 Oct 2022 • Federico Baldassarre, Quentin Debard, Gonzalo Fiz Pontiveros, Tri Kurniawan Wijaya

The proliferation of DeepFake technology is a rising challenge in today's society, owing to more powerful and accessible generation methods.

Attribute Face Swapping +1

Towards Self-Supervised Learning of Global and Object-Centric Representations

1 code implementation • 11 Mar 2022 • Federico Baldassarre, Hossein Azizpour

Self-supervision allows learning meaningful representations of natural images, which usually contain one central object.

Data Augmentation Object +2

Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks

1 code implementation • ECCV 2020 • Federico Baldassarre, Kevin Smith, Josephine Sullivan, Hossein Azizpour

Visual relationship detection is fundamental for holistic image understanding.

Human-Object Interaction Detection Inductive Bias +4

GraphQA: Protein Model Quality Assessment using Graph Convolutional Network

1 code implementation • 25 Sep 2019 • Federico Baldassarre, David Menéndez Hurtado, Arne Elofsson, Hossein Azizpour

Proteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure.

Computational Efficiency Protein Folding +1

Explainability Techniques for Graph Convolutional Networks

2 code implementations • 31 May 2019 • Federico Baldassarre, Hossein Azizpour

Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them.

Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2

16 code implementations • 9 Dec 2017 • Federico Baldassarre, Diego González Morín, Lucas Rodés-Guirao

We review some of the most recent approaches to colorize gray-scale images using deep learning methods.

Colorization Image Colorization