4 papers
FaceQSORT: a Multi-Face Tracking Method based on Biometric and Appearance Features
Robert Jöchl, Andreas Uhl
In this work, a novel multi-face tracking method named FaceQSORT is proposed. To mitigate multi-face tracking challenges (e.g., partially occluded or lateral faces), FaceQSORT comb…
Temporal Image Forensics: A Review and Critical Evaluation
Robert Jöchl, Andreas Uhl
Temporal image forensics is the science of estimating the age of a digital image. Usually, time-dependent traces (age traces) introduced by the image acquisition pipeline are explo…
Content Bias in Deep Learning Image Age Approximation: A new Approach Towards better Explainability
Robert Jöchl, Andreas Uhl
In the context of temporal image forensics, it is not evident that a neural network, trained on images from different time-slots (classes), exploits solely image age related featur…
Device (In)Dependence of Deep Learning-based Image Age Approximation
Robert Jöchl, Andreas Uhl
The goal of temporal image forensic is to approximate the age of a digital image relative to images from the same device. Usually, this is based on traces left during the image acq…