Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Jeong-Sik Lee"'
Autor:
Jeong-Sik Lee, Hyun-Chul Choi
Publikováno v:
Journal of King Saud University: Computer and Information Sciences, Vol 36, Iss 4, Pp 102028- (2024)
Compositional scripts like Hangeul (Korean characters) and Chinese characters involve numerous characters, making manual font design labor-intensive and cost-ineffective work. Although many few-shot font generation methods have been introduced, they
Externí odkaz:
https://doaj.org/article/a443b0790e354d7782a2454f9b22f647
Autor:
Kyeongrae Cho, Jeong-Sik Lee, Chanyang Park, Hyeok Yun, Hyundong Jang, Seungjoon Eom, Min Sang Park, Hyun-Chul Choi, Rock-Hyun Baek
Publikováno v:
Advanced Intelligent Systems, Vol 5, Iss 12, Pp n/a-n/a (2023)
Herein, the impact of cross‐temperature on 3D NAND flash memory is modeled by considering adjacent cells using machine learning. The cells comprising NAND flash memory exhibit diverse states and connectivity patterns. To effectively capture this co
Externí odkaz:
https://doaj.org/article/a94ec992d5914f90a1f025fa622e6dd5
Autor:
Jeong-Sik Lee, Hyun-Chul Choi
Publikováno v:
Journal of King Saud University: Computer and Information Sciences, Vol 35, Iss 10, Pp 101850- (2023)
Early feed-forward neural methods of arbitrary image style transfer utilized the encoded feature map up to its second-order statistics, i.e., mean and variance (or covariance) of the encoded feature map. Recent methods have begun to utilize feature s
Externí odkaz:
https://doaj.org/article/a11e17d9a4b94b36a64ccf0ea46f4d9a
Autor:
Hyeok Yun, Chang-Hyeon An, Hyundong Jang, Kyeongrae Cho, Jeong-Sik Lee, Seungjoon Eom, Choong-Ki Kim, Min-Soo Yoo, Hyun-Chul Choi, Rock-Hyun Baek
Publikováno v:
Advanced Intelligent Systems, Vol 5, Iss 9, Pp n/a-n/a (2023)
Herein, novel neural network (NN) methods that improve prediction accuracy and reduce output variance of the optimized input in the gradient method for cross‐sectional data are proposed, and the variability evaluation approach of optimized inputs i
Externí odkaz:
https://doaj.org/article/ab5cb2a7ed1c40f0b5d17fbb27fbd5d2
Publikováno v:
IEEE Access, Vol 9, Pp 166579-166587 (2021)
Non-maximum suppression (NMS) is an unavoidable post-processing step in the object detection pipeline. NMS selects the bounding boxes with a locally maximum confidence score and eliminates its neighboring candidates which have a large overlap with th
Externí odkaz:
https://doaj.org/article/7184871134544852ae0f19943567b555
Publikováno v:
Sensors, Vol 22, Iss 22, p 8628 (2022)
With the prevalence of degenerative diseases due to the increase in the aging population, we have encountered many spine-related disorders. Since the spine is a crucial part of the body, fast and accurate diagnosis is critically important. Generally,
Externí odkaz:
https://doaj.org/article/1b30039afd094993a79e5cbe9f2e80c0
Autor:
Ubaid Ullah, Jeong-Sik Lee, Chang-Hyeon An, Hyeonjin Lee, Su-Yeong Park, Rock-Hyun Baek, Hyun-Chul Choi
Publikováno v:
Sensors, Vol 22, Iss 18, p 6816 (2022)
For decades, co-relating different data domains to attain the maximum potential of machines has driven research, especially in neural networks. Similarly, text and visual data (images and videos) are two distinct data domains with extensive research
Externí odkaz:
https://doaj.org/article/47717b234abb4790b27686785fea75f6
Publikováno v:
Sensors, Vol 22, Iss 6, p 2374 (2022)
Making a new font requires graphical designs for all base characters, and this designing process consumes lots of time and human resources. Especially for languages including a large number of combinations of consonants and vowels, it is a heavy burd
Externí odkaz:
https://doaj.org/article/e858e2956717442f96b07ef48ac397b8
Publikováno v:
The Institute of Management and Economy Research. 12:135-151
Publikováno v:
Journal of the Korean Society of Fisheries Technology. 57:390-400