Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Ha‐Eun Ahn"'
Publikováno v:
Electronics Letters, Vol 57, Iss 24, Pp 915-917 (2021)
Abstract This paper proposes a full body virtual try‐on which handles both top and bottom garments and generates realistic try‐on images. For the full body virtual try‐on, this paper addresses lack of suitable training data to align and fit top
Externí odkaz:
https://doaj.org/article/1e9d778467f44d22a26f9f3182cabfcc
Publikováno v:
Symmetry, Vol 11, Iss 10, p 1251 (2019)
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K fram
Externí odkaz:
https://doaj.org/article/e0d9f430b1d74495b3ab9c531133930f
Publikováno v:
Symmetry, Vol 11, Iss 5, p 619 (2019)
Visual quality and algorithm efficiency are two main interests in video frame interpolation. We propose a hybrid task-based convolutional neural network for fast and accurate frame interpolation of 4K videos. The proposed method synthesizes low-resol
Externí odkaz:
https://doaj.org/article/907fdee8638c45d89666103c1034341c
Autor:
Ha Eun Ahn, Jun Yeung Hong
Publikováno v:
Korean Journal of Financial Studies. 51:611-633
This study examines whether Korean pension guidelines that limit the payment of director show practical policy effectiveness by improving corporate management efficiency. Specifically, this study examines stickiness of pay to determine whether opport
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9307ba47ff4b98538c0a974efd02cda2
https://doi.org/10.26845/kjfs.2022.10.51.5.611
https://doi.org/10.26845/kjfs.2022.10.51.5.611
Publikováno v:
Electronics Letters, Vol 57, Iss 24, Pp 915-917 (2021)
This paper proposes a full body virtual try‐on which handles both top and bottom garments and generates realistic try‐on images. For the full body virtual try‐on, this paper addresses lack of suitable training data to align and fit top and bott
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::645a98c42a12268b822cfd8e751307c2
https://doi.org/10.1049/ell2.12307
https://doi.org/10.1049/ell2.12307
Publikováno v:
Symmetry
Volume 11
Issue 10
Symmetry, Vol 11, Iss 10, p 1251 (2019)
Volume 11
Issue 10
Symmetry, Vol 11, Iss 10, p 1251 (2019)
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K fram
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ea2aa9e09981bb031d19e357b963abf
Autor:
Ha-Eun Ahn, Ji-Sang Yoo
Publikováno v:
Journal of the Korea Institute of Information and Communication Engineering. 18:1686-1694
In this paper, a new scheme to recognize a finger shape in the depth image captured by Kinect is proposed. Rigid transformation of an input finger shape is pre-processed for its robustness against the shape angle of input fingers. After extracting co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f473f27953a252d589ee4962d002adf
https://doi.org/10.6109/jkiice.2014.18.7.1686
https://doi.org/10.6109/jkiice.2014.18.7.1686