Zobrazeno 1 - 10
of 248
pro vyhledávání: '"Suha Kwak"'
Autor:
Se Woo Kim, Jung Hoon Kim, Suha Kwak, Minkyo Seo, Changhyun Ryoo, Cheong-Il Shin, Siwon Jang, Jungheum Cho, Young-Hoon Kim, Kyutae Jeon
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
Abstract Our objective was to investigate the feasibility of deep learning-based synthetic contrast-enhanced CT (DL-SCE-CT) from nonenhanced CT (NECT) in patients who visited the emergency department (ED) with acute abdominal pain (AAP). We trained a
Externí odkaz:
https://doaj.org/article/824434b2b6b54f469f72a0b6f50e3125
Publikováno v:
Computer Vision – ACCV 2022 ISBN: 9783031263477
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b52f3c0555f873af88775eda362ffbd6
https://doi.org/10.1007/978-3-031-26348-4_4
https://doi.org/10.1007/978-3-031-26348-4_4
This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object classes through attentions drawn by an image classification network. Sinc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7880ae47a83808551f275712329ee70
http://arxiv.org/abs/2212.07579
http://arxiv.org/abs/2212.07579
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9359724fa23dc5c4aeea40d56c321c17
https://doi.org/10.1109/cvpr52688.2022.00699
https://doi.org/10.1109/cvpr52688.2022.00699
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0eb888e46041a6a49ae93949b0ff6c32
https://doi.org/10.1007/978-3-031-19806-9_1
https://doi.org/10.1007/978-3-031-19806-9_1
Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which however ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d430e1509b801b880111598cf428847
The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::358154eafaba49a9a14c02499cdc3562
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::763497f2c73149498fe8ef87ef3f9342
https://doi.org/10.1007/978-3-031-19827-4_32
https://doi.org/10.1007/978-3-031-19827-4_32
Publikováno v:
CVPR
This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge, and transfe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34baa4a06187e988bbfb5e40c830e724
http://arxiv.org/abs/2103.14908
http://arxiv.org/abs/2103.14908
Spatio-temporal convolution often fails to learn motion dynamics in videos and thus an effective motion representation is required for video understanding in the wild. In this paper, we propose a rich and robust motion representation based on spatio-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87b27716a553c992fe5b2d068d5db6a8
http://arxiv.org/abs/2102.07092
http://arxiv.org/abs/2102.07092