Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Gee-Sern Hsu"'
Publikováno v:
IEEE Access, Vol 9, Pp 39695-39706 (2021)
We propose the Wasserstein Divergence GAN with an identity expert and an attribute retainer for facial age transformation. The Wasserstein Divergence GAN (WGAN-div) can better stabilize the training and lead to better target image generation. The ide
Externí odkaz:
https://doaj.org/article/612d506ef1ba4ab3ad6aafe499f4b653
Publikováno v:
IEEE Access, Vol 9, Pp 71418-71421 (2021)
Recent discourse in security domains points to the emergence of intelligent biometric systems as some of the most potent authentication systems for government agencies, border surveillance, anomaly detection, and medical data protection. New and emer
Externí odkaz:
https://doaj.org/article/d4c7222c9d8a4f4485221394da6713f6
Autor:
Gee-Sern Hsu, Chia-Hao Tang
Publikováno v:
IEEE Access, Vol 8, Pp 147765-147775 (2020)
Face normalization refers to a family of approaches that rotate a non-frontal face to the frontal pose for better handling of face recognition. While a great majority of face normalization methods focus on frontal pose only, we proposed a framework f
Externí odkaz:
https://doaj.org/article/95c731e3da72481d8b2dc63c5e32c28d
Publikováno v:
IEEE Access, Vol 8, Pp 6032-6044 (2020)
We propose the Edge-Embedded Multi-Dropout (EEMD) framework for real-time face alignment. The EEMD framework extracts facial edge features and explores multiple dropout architecture for locating facial landmarks. It consists of two major component ne
Externí odkaz:
https://doaj.org/article/234a0c3c6cd5423b970326ac265a292f
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Publikováno v:
IEEE Access, Vol 9, Pp 39695-39706 (2021)
We propose the Wasserstein Divergence GAN with an identity expert and an attribute retainer for facial age transformation. The Wasserstein Divergence GAN (WGAN-div) can better stabilize the training and lead to better target image generation. The ide
Autor:
Chia-Hao Tang, Gee-Sern Hsu
Publikováno v:
IEEE Access, Vol 8, Pp 147765-147775 (2020)
Face normalization refers to a family of approaches that rotate a non-frontal face to the frontal pose for better handling of face recognition. While a great majority of face normalization methods focus on frontal pose only, we proposed a framework f
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197741
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d2ae9f46c38adedc8cc3e17021315e2
https://doi.org/10.1007/978-3-031-19775-8_34
https://doi.org/10.1007/978-3-031-19775-8_34
Publikováno v:
2021 25th International Computer Science and Engineering Conference (ICSEC).
Publikováno v:
WACV
Facial image inpainting is a problem that is widely studied, and in recent years the introduction of Generative Adversarial Networks, has led to improvements in the field. Unfortunately some issues persists, in particular when blending the missing pi