Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Fariborz Taherkhani"'
Publikováno v:
IET Biometrics, Vol 11, Iss 3, Pp 260-276 (2022)
Abstract In recent years, with the advent of deep‐learning, face recognition (FR) has achieved exceptional success. However, many of these deep FR models perform much better in handling frontal faces compared to profile faces. The major reason for
Externí odkaz:
https://doaj.org/article/bc784d1fa9524904839aa2831eb01734
Publikováno v:
IEEE Sensors Letters. 7:1-4
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6edd9b129649c29b646940683ae8379a
https://doi.org/10.1109/lsens.2023.3264998
https://doi.org/10.1109/lsens.2023.3264998
Autor:
Fariborz Taherkhani, Aashish Rai, Quankai Gao, Shaunak Srivastava, Xuanbai Chen, Fernando de la Torre, Steven Song, Aayush Prakash, Daeil Kim
3D face modeling has been an active area of research in computer vision and computer graphics, fueling applications ranging from facial expression transfer in virtual avatars to synthetic data generation. Existing 3D deep learning generative models (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22c8ca46ae380e31c31209210ea4db69
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200649
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de833bb93f73bc3f70d9893465ceb894
https://doi.org/10.1007/978-3-031-20065-6_15
https://doi.org/10.1007/978-3-031-20065-6_15
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed4501d29cca30c6a3a36d65202a318b
https://doi.org/10.2139/ssrn.4310666
https://doi.org/10.2139/ssrn.4310666
Autor:
Sobhan Soleymani, Nasser M. Nasrabadi, Jeremy Dawson, Seyed Mehdi Iranmanesh, Fariborz Taherkhani, Ali Dabouei
We present a quality-aware multimodal recognition framework that combines representations from multiple biometric traits with varying quality and number of samples to achieve increased recognition accuracy by extracting complimentary identification i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95ba1bea65e118d910e622207a9e181f
http://arxiv.org/abs/2112.05827
http://arxiv.org/abs/2112.05827
Publikováno v:
CVPR
The goal is to use Wasserstein metric to provide pseudo labels for the unlabeled images to train a Convolutional Neural Networks (CNN) in a Semi-Supervised Learning (SSL) manner for the classification task. The basic premise in our method is that the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b655cc113207d58921c4731cf169527c
https://doi.org/10.1109/cvpr46437.2021.01209
https://doi.org/10.1109/cvpr46437.2021.01209
Publikováno v:
AAAI
Convolutional Neural Networks (CNNs) have provided promising achievements for image classification problems. However, training a CNN model relies on a large number of labeled data. Considering the vast amount of unlabeled data available on the web, i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1babc3a3a160417df08f42329615ffb
https://doi.org/10.1609/aaai.v33i01.33015058
https://doi.org/10.1609/aaai.v33i01.33015058
Publikováno v:
WACV
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 embedding domain using two disentangled but complementary representati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3125aa859f35c6550dbff7f20c258b50
http://arxiv.org/abs/2012.01542
http://arxiv.org/abs/2012.01542