-
[pdf]
[arXiv]
[bibtex]@InProceedings{Melzi_2024_WACV, author = {Melzi, Pietro and Tolosana, Ruben and Vera-Rodriguez, Ruben and Kim, Minchul and Rathgeb, Christian and Liu, Xiaoming and DeAndres-Tame, Ivan and Morales, Aythami and Fierrez, Julian and Ortega-Garcia, Javier and Zhao, Weisong and Zhu, Xiangyu and Yan, Zheyu and Zhang, Xiao-Yu and Wu, Jinlin and Lei, Zhen and Tripathi, Suvidha and Kothari, Mahak and Zama, Md Haider and Deb, Debayan and Biesseck, Bernardo and Vidal, Pedro and Granada, Roger and Fickel, Guilherme and F\"uhr, Gustavo and Menotti, David and Unnervik, Alexander and George, Anjith and Ecabert, Christophe and Shahreza, Hatef Otroshi and Rahimi, Parsa and Marcel, S\'ebastien and Sarridis, Ioannis and Koutlis, Christos and Baltsou, Georgia and Papadopoulos, Symeon and Diou, Christos and Di Domenico, Nicol\`o and Borghi, Guido and Pellegrini, Lorenzo and Mas-Candela, Enrique and S\'anchez-P\'erez, \'Angela and Atzori, Andrea and Boutros, Fadi and Damer, Naser and Fenu, Gianni and Marras, Mirko}, title = {FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {January}, year = {2024}, pages = {892-901} }
FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data
Abstract
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.
Related Material