Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Tae Hyun Oh"'
Publikováno v:
IEEE Access, Vol 12, Pp 130007-130021 (2024)
Federated Learning (FL) is a distributed machine learning paradigm involving multiple clients to train a server model. In practice, clients often possess limited data and are not always available for simultaneous participation in FL, which can lead t
Externí odkaz:
https://doaj.org/article/7cc365f95cc34a9cb3187f3446490cfc
Publikováno v:
IEEE Access, Vol 12, Pp 93580-93592 (2024)
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is expensive in terms of labor, time, and cost. In contrast to manually
Externí odkaz:
https://doaj.org/article/324f333acf4846b98f34291ad88f0d40
Autor:
Jinsoo Choi, Tae-Hyun Oh
Publikováno v:
Sensors, Vol 23, Iss 5, p 2529 (2023)
We propose a joint super resolution (SR) and frame interpolation framework that can perform both spatial and temporal super resolution. We identify performance variation according to permutation of inputs in video super-resolution and video frame int
Externí odkaz:
https://doaj.org/article/597a5f63acf146ce9c3c0a26508b7ac3
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. :1-13
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d5c144c230ddfe9c23eb659a157d6d8
https://doi.org/10.1109/tnnls.2023.3267028
https://doi.org/10.1109/tnnls.2023.3267028
Publikováno v:
IEEE Transactions on Microwave Theory and Techniques. 70:4726-4739
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b02a19521e80ea69102239e082538f5
https://doi.org/10.1109/tmtt.2022.3199756
https://doi.org/10.1109/tmtt.2022.3199756
Publikováno v:
IEEE Signal Processing Letters. 29:224-228
This letter proposes a lightweight model for speaker recognition by leveraging a hyperbolic space. The speaker recognition performance heavily depends on the distinctiveness of speaker embeddings induced by metric learning. However, most state-of-the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1e0a23b853fd95faea37c2ab0143873
https://doi.org/10.1109/lsp.2021.3129695
https://doi.org/10.1109/lsp.2021.3129695
Audio captioning aims to generate text descriptions from environmental sounds. One challenge of audio captioning is the difficulty of the generalization due to the lack of audio-text paired training data. In this work, we propose a simple yet effecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2437cd770faed3f2891b9fca2da988f
http://arxiv.org/abs/2303.17489
http://arxiv.org/abs/2303.17489
Publikováno v:
The Visual Computer.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82fd9767a81acb2b0ea682f1cdea76b7
https://doi.org/10.1007/s00371-023-02798-x
https://doi.org/10.1007/s00371-023-02798-x
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f35741ef801f5336a629f6c00f8a33e
https://doi.org/10.1109/wacv56688.2023.00227
https://doi.org/10.1109/wacv56688.2023.00227
EU의 중장기 통상전략과 한-EU 협력 방안 (EU’s Medium- to Long-term Trade Strategies and Korea-EU Cooperation Plans)
Autor:
Young-ook Jang, Dong-Hee Joe, Cheol-Won Lee, Ji Hyun Park, Tae Hyun Oh, Hyun Jean Lee, Chorong Kim
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::274d920fa8786c6e72937c046f765c85
https://doi.org/10.2139/ssrn.4454944
https://doi.org/10.2139/ssrn.4454944