Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Ashraf Siddique"'
Publikováno v:
The Astrophysical Journal Supplement Series, Vol 271, Iss 1, p 14 (2024)
For the first time, we generate solar coronal parameters (density, magnetic field, radial velocity, and temperature) on a near-real-time basis by deep learning. For this, we apply the Pix2PixCC deep-learning model to three-dimensional (3D) distributi
Externí odkaz:
https://doaj.org/article/ea1c8d8da6794d71b8d85d8d11a7f65c
Publikováno v:
IEEE Access, Vol 8, Pp 206427-206444 (2020)
Deep learning-based action recognition in videos has obtained much attention because of achieving remarkable performance in diverse applications. However, due to the heterogeneous background and noisy spatio-temporal cues, extracting highly discrimin
Externí odkaz:
https://doaj.org/article/05f28599217a418a90993811d342e405
Autor:
Sumiaya Rahman, Seungheon Shin, Hyun-Jin Jeong, Ashraf Siddique, Yong-Jae Moon, Eunsu Park, Jihye Kang, Sung-Ho Bae
Publikováno v:
The Astrophysical Journal, Vol 948, Iss 1, p 21 (2023)
This study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider
Externí odkaz:
https://doaj.org/article/a21885a2e382407d9893b07256f0217d
Autor:
Ashraf Siddique, Seungkyu Lee
Publikováno v:
Sensors, Vol 22, Iss 2, p 518 (2022)
The three-dimensional (3D) symmetry shape plays a critical role in the reconstruction and recognition of 3D objects under occlusion or partial viewpoint observation. Symmetry structure prior is particularly useful in recovering missing or unseen part
Externí odkaz:
https://doaj.org/article/62b52d897ec147478738cf110cdcb4f8
Autor:
Ashraf Siddique, Seungkyu Lee
Publikováno v:
Applied Sciences, Vol 11, Iss 2, p 671 (2021)
Beyond time frame editing in video data, object level video editing is a challenging task; such as object removal in a video or viewpoint changes. These tasks involve dynamic object segmentation, novel view video synthesis and background inpainting.
Externí odkaz:
https://doaj.org/article/84620ddfb31c4e5ba42d1180c526d0dd
Publikováno v:
IEEE Access, Vol 8, Pp 206427-206444 (2020)
Deep learning-based action recognition in videos has obtained much attention because of achieving remarkable performance in diverse applications. However, due to the heterogeneous background and noisy spatio-temporal cues, extracting highly discrimin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e54a507a9a6e80e5805759d46d7271ab
https://ieeexplore.ieee.org/document/9256204/
https://ieeexplore.ieee.org/document/9256204/
Publikováno v:
The Astrophysical Journal. 897:L32
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82f3cfa36cca8459832270a384a7098e
https://doi.org/10.3847/2041-8213/ab9d79
https://doi.org/10.3847/2041-8213/ab9d79
Autor:
Seungkyu Lee, Ashraf Siddique
Publikováno v:
WACV
In this paper, we propose a robust video inpainting method under challenging background conditions such as occlusion, complex visual pattern, overlaid object clutter and depth variation observed in a moving camera. We propose a confidence score based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09d8bca4d7306b33fdff199f4f58b8d2
https://doi.org/10.1109/wacv.2018.00195
https://doi.org/10.1109/wacv.2018.00195