11 citations · 42 across the 9 of their papers we have counts for
7 papers · 1 filter
Faces of Fairness: Examining Bias in Facial Expression Recognition Datasets and Models
Mohammad Mehdi Hosseini, Ali Pourramezan Fard, Mohammad H. Mahoor
Automated Facial Expression Recognition (FER), involves two critical aspects: data and model design. Both significantly influence bias and fairness in FER tasks. However, issues re…
AffectNet+: A Database for Enhancing Facial Expression Recognition with Soft-Labels
Ali Pourramezan Fard, Mohammad Mehdi Hosseini, Timothy D. Sweeny +1
Automated Facial Expression Recognition (FER) is challenging due to intra-class variations and inter-class similarities. FER can be especially difficult when facial expressions ref…
GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis
Ali Pourramezan Fard, Mohammad H. Mahoor, Sarah Ariel Lamer +1
Generative Adversarial Networks (GANs) are capable of synthesizing high-quality facial images. Despite their success, GANs do not provide any information about the relationship bet…
ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment
Ali Pourramezan Fard, Mohammad H. Mahoor
Although deep neural networks have achieved reasonable accuracy in solving face alignment, it is still a challenging task, specifically when we deal with facial images, under occlu…
Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks
Ali Pourramezan Fard, Mohammad H. Mahoor
Facial landmark detection is a vital step for numerous facial image analysis applications. Although some deep learning-based methods have achieved good performances in this task, t…
XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks
Jian Sun, Ali Pourramezan Fard, Mohammad H. Mahoor
Capsule Network is powerful at defining the positional relationship between features in deep neural networks for visual recognition tasks, but it is computationally expensive and n…
ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation
Ali Pourramezan Fard, Hojjat Abdollahi, Mohammad Mahoor
Active Shape Model (ASM) is a statistical model of object shapes that represents a target structure. ASM can guide machine learning algorithms to fit a set of points representing a…