Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Bassel Zeno"'
Publikováno v:
International Journal of Speech Technology. 24:729-735
Recent studies on the application of generative adversarial networks (GAN) for speech synthesis have shown improvements in the naturalness of synthesized speech, compared to the conventional approaches. In this article, we present a new framework of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b81b5f83d7dc32ec25eeb67981909b14
https://doi.org/10.1007/s10772-021-09840-0
https://doi.org/10.1007/s10772-021-09840-0
Publikováno v:
Informatica. :425-440
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16f4f699fdf611cda11a89131626edcc
https://doi.org/10.15388/21-infor443
https://doi.org/10.15388/21-infor443
Publikováno v:
Pattern Recognition Letters. 138:527-533
In this work, we introduce a novel framework based on Generative Adversarial Networks to control the pose, expression and facial features of a given face image using another face image. It can then be used for data augmentation, pose invariant face i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a8caa242d10321b31108dd26c12ebb1
https://doi.org/10.1016/j.patrec.2020.08.026
https://doi.org/10.1016/j.patrec.2020.08.026
Autor:
Ibrahim Alnafrah, Bassel Zeno
Publikováno v:
Innovation and Development. 10:45-66
This study aims to cluster and classify national innovation systems (NISs) dynamically based on analysing the structural differences among NISs’ dimensions. This study provides a tool that will hel...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5d107bf5698e3b762b72c29e0fa826a
https://doi.org/10.1080/2157930x.2018.1564124
https://doi.org/10.1080/2157930x.2018.1564124
Publikováno v:
Proceedings of the 5th International Conference on Engineering and MIS.
This paper provides a comparative analysis between two recent image-to-image translation models based on Generative Adversarial Networks. The first one is UNIT which consists of coupled GANs and variational autoencoders (VAEs) with shared-latent spac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::169fd50820f8e3b3b37e92fc710a0927
https://doi.org/10.1145/3330431.3330435
https://doi.org/10.1145/3330431.3330435
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions ISBN: 9783030304928
ICANN (Workshop)
ICANN (Workshop)
Synthesizing realistic multi-view face images from a single-view input is an effective and cheap way for data augmentation. In addition it is promising for more efficiently training deep pose-invariant models for large-scale unconstrained face recogn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd3d0bb044900011e8abd4e8e7e53480
https://doi.org/10.1007/978-3-030-30493-5_51
https://doi.org/10.1007/978-3-030-30493-5_51
Autor:
Bassel Zeno, Dmitry Yudin
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319683201
The paper considers usage of fine-tuning of the deep neural network ensemble for recognition of 60 event types in the set of 60,000 images from WIDER database. The applied ensemble consists of two deep convolutional neural networks (CNN) using the Go
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::673eea9f5550279e9e984722b30f2ff9
https://doi.org/10.1007/978-3-319-68321-8_49
https://doi.org/10.1007/978-3-319-68321-8_49
Publikováno v:
Computational Science and Its Applications – ICCSA 2017 ISBN: 9783319624037
ICCSA (5)
ICCSA (5)
Nowadays big volumes of medical data are accumulated. So the problem of analysis of these data and mining linked logical structures, defining internal data semantics is an actual one. Solution of this problem allows solve the problem of optimizing in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::12b501da2fb19043602221a33a999381
https://doi.org/10.1007/978-3-319-62404-4_27
https://doi.org/10.1007/978-3-319-62404-4_27
Publikováno v:
IOP Conference Series: Materials Science and Engineering. 618:012012
This paper provides the comparative analysis between two recent image-to-image translation models that based on Generative Adversarial Networks. The first one is UNIT which consists of coupled GANs and variational autoencoders (VAEs) with shared-late
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::291c1d12e83d9d5eec01a3e92159a61b
https://doi.org/10.1088/1757-899x/618/1/012012
https://doi.org/10.1088/1757-899x/618/1/012012
Publikováno v:
IOP Conference Series: Materials Science and Engineering. 618:012011
In unconstrained facial images, large visual variations concerning pose, scale, the presence of occlusions, expressions and lighting usually cause difficulties in discriminating faces from the background accurately. As a result, some non-face regions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6a5bb0b69bc18f8c7c2e5657d4c93a15
https://doi.org/10.1088/1757-899x/618/1/012011
https://doi.org/10.1088/1757-899x/618/1/012011