Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Viktor Varkarakis"'
Publikováno v:
IEEE Access, Vol 10, Pp 123661-123678 (2022)
Robust authentication for low-power consumer devices without a keyboard remains a challenge. The recent availability of low-power neural accelerator hardware, combined with improvements in neural facial recognition algorithms provides enabling techno
Externí odkaz:
https://doaj.org/article/e22dc03396a24a3bb6df894ffbc4ae49
Publikováno v:
IEEE Access, Vol 9, Pp 38810-38825 (2021)
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. For a successful implementation of conditional generators,
Externí odkaz:
https://doaj.org/article/c7c57e7519be44a0a116e22ec9392508
Publikováno v:
IEEE Access, Vol 8, Pp 152532-152550 (2020)
This work explores the identity attribute of synthetic face samples derived from Generative Adversarial Networks. The goal is to determine if individual samples are unique in terms of identity, firstly with respect to the seed dataset that trains the
Externí odkaz:
https://doaj.org/article/ac3051dd95a84be8b14e597a8132d634
Publikováno v:
24th Irish Machine Vision and Image Processing Conference.
Recent low-power neural accelerator hardware provides a solution for end-to-end privacy and secure facial authentication, such as smart refueling machine locks in shared accommodation, smart speakers, or televisions that respond only to family member
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba20831d27dd2a291ba3423570307b20
https://doi.org/10.56541/fevr2516
https://doi.org/10.56541/fevr2516
Publikováno v:
IEEE Access, Vol 9, Pp 38810-38825 (2021)
IEEE access
IEEE access
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. For a successful implementation of conditional generators,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cbed367b913e41737fc897cce724e79
https://ieeexplore.ieee.org/document/9369348/
https://ieeexplore.ieee.org/document/9369348/
Publikováno v:
IEEE Consumer Electronics Magazine. 9:48-54
A key aspect to developing and successfully deploying neural network (NN)-based solutions is the availability of suitable datasets. In this article some of the challenges to acquire and annotate data are discussed in the context of new consumer devic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b44fb62d7b105c0479911bf90576e72
https://doi.org/10.1109/mce.2019.2959062
https://doi.org/10.1109/mce.2019.2959062
Publikováno v:
IEEE access
This work explores the identity attribute of synthetic face samples derived from Generative Adversarial Networks. The goal is to determine if individual samples are unique in terms of identity, firstly with respect to the seed dataset that trains the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::266d4c6a1a6e77043152f57f146a84dc
https://doi.org/10.1109/access.2020.3016097
https://doi.org/10.1109/access.2020.3016097
Publikováno v:
IEEE Consumer Electronics Magazine. 8:10-19
The recent explosive growth of deep learning is enabling a new generation of intelligent consumer devices. Specialized deep learning inference now provides data analysis capabilities that once required an active cloud connection, while reducing laten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79899b65f04d1425790841246eb6d1d6
https://doi.org/10.1109/mce.2019.2923042
https://doi.org/10.1109/mce.2019.2923042
Publikováno v:
2020 31st Irish Signals and Systems Conference (ISSC).
Recent Advances in Artificial Intelligence (AI), particularly in the field of compute vision, have been driven by the availability of large public datasets. However, as AI begins to move into embedded devices there will be a growing need for tools to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::adff6f58873941715d2043ffab8564bc
https://doi.org/10.1109/issc49989.2020.9180200
https://doi.org/10.1109/issc49989.2020.9180200
Publikováno v:
Signals and Systems Conference (ISSC), Irish
StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper we recap the StyleGAN architecture and training methodology and present our experiences of retra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::081b57a0d1dfe20deb38b3fa41d8912c
http://arxiv.org/abs/2003.10847
http://arxiv.org/abs/2003.10847
