Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Heidari, Negar"'
Autor:
Heidari, Negar, Iosifidis, Alexandros
Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design (CAD), and have the potential to revolutionize how designers and engineers approach and enhance the design process. By harnessing the power of
Externí odkaz:
http://arxiv.org/abs/2402.17695
Autor:
Heidari, Negar, Iosifidis, Alexandros
Diversity of the features extracted by deep neural networks is important for enhancing the model generalization ability and accordingly its performance in different learning tasks. Facial expression recognition in the wild has attracted interest in r
Externí odkaz:
http://arxiv.org/abs/2210.09381
Publikováno v:
Pattern Recognition 140 (2023) 109528
Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of on
Externí odkaz:
http://arxiv.org/abs/2203.11009
Autor:
Abedi, Samira, Behmanesh, Ali, Mazhar, Farid Najd, Bagherifard, Abolfazl, Sami, Sam Hajialiloo, Heidari, Negar, Hossein-Khannazer, Nikoo, Namazifard, Saina, Kazem Arki, Mandana, Shams, Roshanak, Zarrabi, Ali, Vosough, Massoud
Publikováno v:
In BBA - Molecular Basis of Disease October 2024 1870(7)
Autor:
Heidari, Negar, Vosough, Massoud, Bagherifard, Abolfazl, Sami, Sam Hajialilo, Sarabi, Pedram Asadi, Behmanesh, Ali, Shams, Roshanak
Publikováno v:
In Pathology - Research and Practice November 2024 263
Autor:
Heidari, Negar, Iosifidis, Alexandros
Deep neural networks have been widely used for feature learning in facial expression recognition systems. However, small datasets and large intra-class variability can lead to overfitting. In this paper, we propose a method which learns an optimized
Externí odkaz:
http://arxiv.org/abs/2106.04332
Autor:
Rezaei, Zahra S., Ebrahimi, Mehrnaz, Tabaei, Omid, Ghajari, Yasaman, Shahangian, S. Shirin, Heidari, Negar, Norouzi, Parviz, Sajedi, Reza H.
Publikováno v:
In Microchemical Journal February 2024 197
Autor:
Heidari, Negar, Iosifidis, Alexandros
Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph. However, most of the GCN-based methods in this area train a deep feed-forward network with
Externí odkaz:
http://arxiv.org/abs/2011.05668
Autor:
Heidari, Negar, Iosifidis, Alexandros
Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based methods improve the performance by l
Externí odkaz:
http://arxiv.org/abs/2011.03833
Autor:
Heidari, Negar, Iosifidis, Alexandros
Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forwa
Externí odkaz:
http://arxiv.org/abs/2010.12221