activity
20172021
most citedTasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction

2 citations · 2 across the 9 of their papers we have counts for

collaborators

18 papers

cs.CV20212 cited

Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction

Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani +2

The great success of Convolutional Neural Networks (CNN) for facial attribute prediction relies on a large amount of labeled images. Facial image datasets are usually annotated by…

cs.CV2021

Attribute Guided Sparse Tensor-Based Model for Person Re-Identification

Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani +2

Visual perception of a person is easily influenced by many factors such as camera parameters, pose and viewpoint variations. These variations make person Re-Identification (ReID) a…

cs.CV2021

Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN

Fariborz Taherkhani, Veeru Talreja, Jeremy Dawson +2

In recent years, with the advent of deep-learning, face recognition has achieved exceptional success. However, many of these deep face recognition models perform much better in han…

cs.CV2020

Mutual Information Maximization on Disentangled Representations for Differential Morph Detection

Sobhan Soleymani, Ali Dabouei, Fariborz Taherkhani +2

In this paper, we present a novel differential morph detection framework, utilizing landmark and appearance disentanglement. In our framework, the face image is represented in the…

cs.CV2020

Matching Distributions via Optimal Transport for Semi-Supervised Learning

Fariborz Taherkhani, Hadi Kazemi, Ali Dabouei +2

Semi-Supervised Learning (SSL) approaches have been an influential framework for the usage of unlabeled data when there is not a sufficient amount of labeled data available over th…

cs.CV2020

Cross-Spectral Iris Matching Using Conditional Coupled GAN

Moktari Mostofa, Fariborz Taherkhani, Jeremy Dawson +1

Cross-spectral iris recognition is emerging as a promising biometric approach to authenticating the identity of individuals. However, matching iris images acquired at different spe…