Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Junseok Kwon"'
Autor:
Taeeun Kwon, Junseok Kwon
Publikováno v:
Electronics Letters, Vol 60, Iss 17, Pp n/a-n/a (2024)
Abstract As generative models become more advanced and essential, interest in using these models for image editing is growing. Nevertheless, conventional image editing methods still have many problems and can alter the intrinsic properties (e.g. geom
Externí odkaz:
https://doaj.org/article/b33efe90f64b41aa8233c2d028c14b22
Publikováno v:
IEEE Access, Vol 12, Pp 177028-177037 (2024)
In this study, we introduce a probabilistic visual tracking method tailored for wild scenarios, where tracking environments experience abrupt changes over time. In probabilistic visual tracking, particularly when utilizing sequential Monte Carlo (MC)
Externí odkaz:
https://doaj.org/article/e2e5ef5b67de4c5db79c2543723469ad
Autor:
Youjin Kim, Junseok Kwon
Publikováno v:
BMC Bioinformatics, Vol 24, Iss 1, Pp 1-16 (2023)
Abstract Background Protein secondary structures that link simple 1D sequences to complex 3D structures can be used as good features for describing the local properties of protein, but also can serve as key features for predicting the complex 3D stru
Externí odkaz:
https://doaj.org/article/9bd705bb6ce94557a1bb7aa2748e122a
Publikováno v:
IEEE Access, Vol 11, Pp 26086-26098 (2023)
In this paper, we propose a novel dual gradient-based desnowing algorithm that can accurately remove snow from a scene by characterizing snow particles. To localize snow in an image, we present a gradient-based snow activation map that can be estimat
Externí odkaz:
https://doaj.org/article/d111f16c329f444eb3cbf065938d0872
Publikováno v:
IEEE Access, Vol 10, Pp 116141-116151 (2022)
Learning deep neural networks from noisy labels is challenging, because high-capacity networks attempt to describe data even with noisy class labels. In this study, we propose a self-augmentation method without additional parameters, which handles no
Externí odkaz:
https://doaj.org/article/fa61df39eb6f47c3af6f046b65f9490e
Publikováno v:
IEEE Access, Vol 10, Pp 9022-9035 (2022)
We formulate the visual tracking problem as a semi-supervised continual learning problem, where only an initial frame is labeled. In contrast to conventional meta-learning based approaches that regard visual tracking as an instance detection problem
Externí odkaz:
https://doaj.org/article/3063a4ad6a5040f7bfd5bb72f956a3d9
Autor:
Youjin Kim, Junseok Kwon
Publikováno v:
IEEE Access, Vol 10, Pp 33527-33536 (2022)
In this study, we propose a novel Wasserstein distributional tracking method that can balance approximation with accuracy in terms of Monte Carlo estimation. To achieve this goal, we present three different systems: sliced Wasserstein-based (SWT), pr
Externí odkaz:
https://doaj.org/article/96d0396fdd074f1a89dd10d75328a95b
Autor:
Jiaying Liu, Wen-Huang Cheng, Jenq-Neng Hwang, lvan V. Bajic, Shiqi Wang, Junseok Kwon, Ngai-Man Cheung, Rei Kawakami
Publikováno v:
APSIPA Transactions on Signal and Information Processing, Vol 12, Iss 4 (2023)
Externí odkaz:
https://doaj.org/article/591e8cf90dd34dc2b490fe8f4abe6a08
Autor:
Jin Wook Paeng, Junseok Kwon
Publikováno v:
IET Signal Processing, Vol 15, Iss 6, Pp 365-374 (2021)
Abstract The authors present a novel tracking algorithm based on a factorial hidden Markov model (FHMM) that can utilise the structured information of a target. An FHMM consists of multiple hidden Markov models (HMMs), wherein each HMM aims to repres
Externí odkaz:
https://doaj.org/article/d7d2498827ae4e78a85bba1dffcec1f7
Publikováno v:
IEEE Access, Vol 9, Pp 144699-144712 (2021)
In this paper, we tackle the well-known problem of dataset construction from the point of its generation using generative adversarial networks (GAN). As semantic information of the dataset should have a proper alignment with images, controlling the i
Externí odkaz:
https://doaj.org/article/78a98bdcd9b54ed0a9f64108b16fa9c4