no code implementations • 20 Nov 2023 • Biying Fu, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises.
1 code implementation • 29 Aug 2022 • Biying Fu, Naser Damer
To improve the trustfulness of such ML decision systems, it is crucial to be aware of the inherent biases in these solutions and to make them more transparent to the public and developers.
no code implementations • 11 Aug 2022 • Biying Fu, Naser Damer
A morphed image can be successfully verified to multiple identities.
1 code implementation • CVPR 2023 • Fadi Boutros, Meiling Fang, Marcel Klemt, Biying Fu, Naser Damer
Based on that, our proposed CR-FIQA uses this paradigm to estimate the face image quality of a sample by predicting its relative classifiability.
1 code implementation • 9 Dec 2021 • Biying Fu, Naser Damer
To avoid the low discrimination between the general spatial activation mapping of low and high-quality images in FR models, we build our explainability tools in a higher derivative space by analyzing the variation of the FR activation maps of image sets with different quality decisions.
no code implementations • 21 Oct 2021 • Biying Fu, Florian Kirchbuchner, Naser Damer
This work studies, for the first time, the effect of wearing a face mask on face image quality by utilising state-of-the-art face image quality assessment methods of different natures.
no code implementations • 21 Oct 2021 • Biying Fu, Cong Chen, Olaf Henniger, Naser Damer
This paper focuses on face images and the measurement of face image utility with general and face-specific image quality metrics.