Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Seonguk Seo"'
Publikováno v:
2022 IEEE International Conference on Big Data (Big Data).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ec2e66823605feb3c40f2a6f58f6a2d
https://doi.org/10.1109/bigdata55660.2022.10020742
https://doi.org/10.1109/bigdata55660.2022.10020742
We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information. Although
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b524e68c776666fbcc57c4a870d18d10
http://arxiv.org/abs/2201.03121
http://arxiv.org/abs/2201.03121
We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3f0e3eec9a6e34530baa87c8df9b79c1
http://arxiv.org/abs/2112.15399
http://arxiv.org/abs/2112.15399
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585419
ECCV (22)
ECCV (22)
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c955121008d3a57da05a3c4870e2532a
https://doi.org/10.1007/978-3-030-58542-6_5
https://doi.org/10.1007/978-3-030-58542-6_5
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585549
ECCV (15)
ECCV (15)
We propose a unified referring video object segmentation network (URVOS). URVOS takes a video and a referring expression as inputs, and estimates the object masks referred by the given language expression in the whole video frames. Our algorithm addr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a603da6fd7442d8a8247d44e19c56a6f
https://doi.org/10.1007/978-3-030-58555-6_13
https://doi.org/10.1007/978-3-030-58555-6_13
Publikováno v:
Ocean Engineering. 137:309-327
Given that the International Maritime Organization (IMO) recently introduced the Energy Efficiency Design Index (EEDI) for new ships and the Energy Efficiency Operational Indicator (EEOI) for ship operations, accurate prediction of the added resistan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0c90ef536743d68ebde6bcc21816a69
https://doi.org/10.1016/j.oceaneng.2017.04.009
https://doi.org/10.1016/j.oceaneng.2017.04.009
Autor:
Sunho Park, Seonguk Seo
Publikováno v:
Journal of the Society of Naval Architects of Korea. 54:132-142
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c22cb745830b02ff169603690b2fe9b
https://doi.org/10.3744/snak.2017.54.2.132
https://doi.org/10.3744/snak.2017.54.2.132
Publikováno v:
CVPR
We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e3fa10d1c5adf533de67de586a0da52
https://doi.org/10.1109/cvpr.2019.00753
https://doi.org/10.1109/cvpr.2019.00753
Publikováno v:
Journal of the Society of Naval Architects of Korea. 53:329-335
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77d338d66daae66025d4454d7dc3a387
https://doi.org/10.3744/snak.2016.53.4.329
https://doi.org/10.3744/snak.2016.53.4.329
Publikováno v:
CVPR
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive unce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0322f6f33059b9f388b03e714f6b260
http://arxiv.org/abs/1809.10877
http://arxiv.org/abs/1809.10877