no code implementations • 13 Nov 2023 • Soroush Hashemifar, Saeed Parsa, Morteza Zakeri-Nasrabadi
As the capacity of deep neural networks (DNNs) increases, their need for huge amounts of data significantly grows.
no code implementations • 29 Oct 2023 • Soroush Hashemifar, Saeed Parsa, Akram Kalaee
Deep learning has revolutionized various real-world applications, but the quality of Deep Neural Networks (DNNs) remains a concern.
no code implementations • 27 Jan 2023 • Soroush Hashemifar, Abdolreza Marefat, Javad Hassannataj Joloudari, Hamid Hassanpour
To the best of our knowledge, FRA is the first method that shifts its focus towards manipulating the face embeddings generated by any face representation learning algorithm to create new embeddings representing the same identity and facial emotion but with an altered posture.