Pedro C. Neto

TL;DR: The Masked Face Recognition Competition (MFR) as discussed by the authors was held within the 2021 International Joint Conference on Biometrics (IJCB 2021) and attracted a total of 10 participating teams with valid submissions.

TL;DR: In this article, the authors analyzed some relevant works published on this particular task and highlighted the limitations that hinder the application of these works in clinical practice, and empirically investigated the feasibility of using weakly annotated datasets to support the development of computer-aided diagnosis systems for colorectal cancer from WSI.

TL;DR: In this article, the authors proposed a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode.

TL;DR: FocusFace as discussed by the authors is a multi-task architecture that uses contrastive learning to accurately perform masked face recognition, which is designed to be trained from scratch or to work on top of state-of-the-art face recognition methods without sacrificing the capabilities of existing models in conventional face recognition tasks.

TL;DR: The submitted solutions presented innovations that led to out-performing the considered baseline in many experimental settings and are presented at the 2022 International Joint Conference on Biometrics (IJCB 2022).