Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Seunghoon Hong"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198021
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb901cd0c2ecbee56fdd0c2573bf6b69
https://doi.org/10.1007/978-3-031-19803-8_6
https://doi.org/10.1007/978-3-031-19803-8_6
Autor:
Jung Hoon Kim, Kyungmoon Lee, Dongkeun Kim, Suha Kwak, Jae Seok Bae, Minkyo Seo, Seunghoon Hong
Publikováno v:
WACV
Contrast materials are often injected into body to contrast specific tissues in Computed Tomography (CT) images. Contrast Enhanced CT (CECT) images obtained in this way are more useful than Non-Enhanced CT (NECT) images for medical diagnosis, but not
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76f498ed757f39706c69ab70e82313fc
https://doi.org/10.1109/wacv48630.2021.00402
https://doi.org/10.1109/wacv48630.2021.00402
Publikováno v:
CVPR
Generative modeling of set-structured data, such as point clouds, requires reasoning over local and global structures at various scales. However, adopting multi-scale frameworks for ordinary sequential data to a set-structured data is nontrivial as i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06b891a11e26832d28554f76fcf0c7d0
Publikováno v:
CVPR
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an innovative mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01e01e51ea32eceae004d956b312be7a
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585730
ECCV (26)
ECCV (26)
Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often suffer from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e84c3418121d915b71e4ecf7fc849955
https://doi.org/10.1007/978-3-030-58574-7_10
https://doi.org/10.1007/978-3-030-58574-7_10
Publikováno v:
ICCV
With the remarkable success of deep learning, Deep Neural Networks (DNNs) have been applied as dominant tools to various machine learning domains. Despite this success, however, it has been found that DNNs are surprisingly vulnerable to malicious att
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3363c7672e655dd462ec6ac988420074
https://doi.org/10.1109/iccv.2019.00283
https://doi.org/10.1109/iccv.2019.00283
Publikováno v:
Journal of Hydraulic Engineering. 145
The method of large eddy simulation (LES) was employed to investigate the flow and turbulence structure around bridge abutments of different lengths placed in a compound, asymmetric channel. The simulations were faithful representations of large-scal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::109dc90c8ef89141123131c0119819b1
https://doi.org/10.1061/(asce)hy.1943-7900.0001591
https://doi.org/10.1061/(asce)hy.1943-7900.0001591
Publikováno v:
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning ISBN: 9783030289539
Explainable AI
Explainable AI
Generating images from natural language description has drawn a lot of attention in the research community for its practical usefulness and for understanding the method in which the model relates text with visual concepts by synthesizing them. Deep g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5fecfbcf9d6701bb5123727c6cb0261
https://doi.org/10.1007/978-3-030-28954-6_5
https://doi.org/10.1007/978-3-030-28954-6_5
Publikováno v:
CVPR
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout. Instead of learning a direct mapping from text to image, our algorithm decomposes the generation process into multiple steps, in which it first constru
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a9b328cf137599211be7e03d829940d
https://doi.org/10.1109/cvpr.2018.00833
https://doi.org/10.1109/cvpr.2018.00833
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 31
We propose a weakly supervised semantic segmentation algorithm based on deep neural networks, which relies on image-level class labels only. The proposed algorithm alternates between generating segmentation annotations and learning a semantic segment
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33a921c66707a7ae49ebe462ff71e97d
https://doi.org/10.1609/aaai.v31i1.11213
https://doi.org/10.1609/aaai.v31i1.11213