Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Jong-Hwan Ko"'
Autor:
Jong-Hwan Ko, Werner Pascha
Publikováno v:
East Asian Economic Review, Vol 18, Iss 1, Pp 55-81 (2014)
This study aims to answer two questions using input-output decomposition analysis: 1) Have emerging Asian economies decoupled? 2) What are the sources of structural changes in gross outputs and value-added of emerging Asian economies related to the f
Externí odkaz:
https://doaj.org/article/099f27e3a29f40a894970ea59ee5d796
Autor:
Changrok So, Jong Uk Kim, Haiwen Luan, Sang Uk Park, Hyochan Kim, Seungyong Han, Doyoung Kim, Changhwan Shin, Tae-il Kim, Wi Hyoung Lee, Yoonseok Park, Keun Heo, Hyoung Won Baac, Jong Hwan Ko, Sang Min Won
Publikováno v:
npj Flexible Electronics, Vol 6, Iss 1, Pp 1-9 (2022)
Abstract Continued research on the epidermal electronic sensor aims to develop sophisticated platforms that reproduce key multimodal responses in human skin, with the ability to sense various external stimuli, such as pressure, shear, torsion, and to
Externí odkaz:
https://doaj.org/article/f9a8bcf9e9bd40d490d23b08f00e5811
Autor:
Cheng Wencan, Jong Hwan Ko
Publikováno v:
IEEE Access, Vol 9, Pp 52977-52986 (2021)
Recognizing and predicting future three-dimensional (3D) scenes are crucial steps for real-time vision-based control systems, as these steps enable them to react appropriately in advance. In this study, a method for predicting the position of a 3D po
Externí odkaz:
https://doaj.org/article/59e0bfdf2dbf4f6fb0ceedd8792f63cb
Publikováno v:
IEEE Access, Vol 9, Pp 119418-119429 (2021)
Conventional human-centric image compression techniques are optimized for human visual perception, and are generally evaluated by metrics such as MSSSIM and PSNR. On the other hand, task-centric image compression techniques that target deep neural ne
Externí odkaz:
https://doaj.org/article/918d1eeef0c440aaaef78dd016c247fa
Autor:
Teerath Kumar, Jinbae Park, Muhammad Salman Ali, A. F. M. Shahab Uddin, Jong Hwan Ko, Sung-Ho Bae
Publikováno v:
IEEE Access, Vol 9, Pp 167663-167673 (2021)
A typical semi-supervised learning-based scheme is based on training a single model for labeled data. For unlabeled data, it uses the pseudo-labeling method to obtain labels. However, the samples during pseudo-labeling are often filtered using a prob
Externí odkaz:
https://doaj.org/article/10dd5cc5be314b2995a840f67b44ee76
Publikováno v:
Electronics Letters, Vol 57, Iss 16, Pp 611-613 (2021)
Abstract Aerial images obtained from autonomous aerial vehicles have lots of small and densely distributed objects because of the capture distance. This paper proposes a deep neural network architecture and training/inference techniques for robust de
Externí odkaz:
https://doaj.org/article/d16e8e60ca3b47a58ec65d9a3f2d3e73
Publikováno v:
Carbon. 208:443-451
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::671908e39097dda474b52db158a092f9
https://doi.org/10.1016/j.carbon.2023.03.069
https://doi.org/10.1016/j.carbon.2023.03.069
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 19:1-18
Conventional image compression techniques targeted for the perceptual quality are not generally optimized for classification tasks using deep neural networks (DNNs). To compress images for DNN inference tasks, recent studies have proposed task-centri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::285d9e0068e205e41de48094a3b011bf
https://doi.org/10.1145/3551389
https://doi.org/10.1145/3551389
Publikováno v:
Fibers and Polymers. 24:741-747
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::310de28e51dacdecd2f5ccf43419eede
https://doi.org/10.1007/s12221-023-00127-6
https://doi.org/10.1007/s12221-023-00127-6
Publikováno v:
Pattern Recognition Letters. 165:1-8
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a62826ad31ad5b5b74afbe6b43a60d9c
https://doi.org/10.1016/j.patrec.2022.11.020
https://doi.org/10.1016/j.patrec.2022.11.020