A State‐of‐the‐Art Computer Vision Adopting Non‐Euclidean Deep‐Learning Models

SH Chowdhury, MR Sany, MH Ahamed… - … Journal of Intelligent …, 2023 - Wiley Online Library
A distance metric known as non‐Euclidean distance deviates from the laws of Euclidean
geometry, which is the geometry that governs most physical spaces. It is utilized when …

Face De-identification: State-of-the-art Methods and Comparative Studies

J Cao, X Chen, B Liu, M Ding, R ** for tinyml
A Ancilotto, F Paissan, E Farella - ACM Transactions on Embedded …, 2024 - dl.acm.org
The unprecedented development of deep learning approaches for video processing has
caused growing privacy concerns. To ensure data analysis while maintaining privacy, it is …

Facial expression translation using landmark guided gans

H Tang, N Sebe - IEEE Transactions on Affective Computing, 2022 - ieeexplore.ieee.org
We propose a simple yet powerful Landmark guided Generative Adversarial Network
(LandmarkGAN) for the facial expression-to-expression translation using a single image …

3PFS: Protecting Pedestrian Privacy Through Face Swap**

Z Zhao, X Zhang, Y Demiris - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
In the era of artificial intelligence, privacy has become a paramount concern, especially
within intelligent transportation systems (ITS) where pedestrians are frequently captured by …

3D Holistic OR Anonymization

TD Wang - ar** to embedded devices
A Ancilotto, F Paissan, E Farella - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Recent years have seen an unprecedented development of deep learning-based
techniques for processing live video from CCTV cameras, causing growing privacy …

PICLAnony: Controlled Anonymization of Face Attributes Based on Parametric Imitation Comparison Learning

H Liu, H Ji, J Liang - 2024 - researchsquare.com
With the ubiquitous use of mobile devices and the widespread sharing of personal photos
and videos on social media, the use of anonymized images to avoid identity disclosure has …