Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Dinh Viet Sang"'
Autor:
Ren, Zhiyao, Dinh, Viet Sang, Wong, Pooi-Mun, Chng, Chin-Boon, Too, Joan Jue-Ying, Foong, Theng-Wai, Loh, Will Ne-Hooi, Chui, Chee-Kong
Publikováno v:
In Computers in Biology and Medicine December 2024 183
Publikováno v:
IEEE Access, Vol 10, Pp 101248-101262 (2022)
Domain adaptation methods in machine learning deal with the domain shift issue by aligning source and target data representation. This paper proposes a novel domain adaptation method for semantic segmentation that exploits the Fourier transform on ch
Externí odkaz:
https://doaj.org/article/fcc96f94eaa34ded8a9effea9ac62028
Publikováno v:
Procedia Computer Science. 207:2698-2707
Autor:
Kieu Dang Nam, Thi-Oanh Nguyen, Nguyen Thi Thuy, Dao Viet Hang, Dao Van Long, Tran Quang Trung, Dinh Viet Sang
Publikováno v:
2022 14th International Conference on Knowledge and Systems Engineering (KSE).
Autor:
Nguyen Duy Manh, Dao Viet Hang, Dao Van Long, Le Quang Hung, Pham Cong Khanh, Nguyen Thi Oanh, Nguyen Thi Thuy, Dinh Viet Sang
Publikováno v:
2022 14th International Conference on Knowledge and Systems Engineering (KSE).
Publikováno v:
Advances in Visual Computing ISBN: 9783031207129
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c0a75dc9ef96afebcffb687135ed4b2
https://doi.org/10.1007/978-3-031-20713-6_35
https://doi.org/10.1007/978-3-031-20713-6_35
Publikováno v:
Advances in Visual Computing ISBN: 9783031207150
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::617a85bfee6b6553f9ef7b20afa971a8
https://doi.org/10.1007/978-3-031-20716-7_11
https://doi.org/10.1007/978-3-031-20716-7_11
Publikováno v:
The 5th International Conference on Future Networks & Distributed Systems.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Lam Xuan Thu, Dinh Viet Sang
Publikováno v:
MAPR
Recent state-of-the-art neural text-to-speech synthesis models have significantly improved the quality of synthesized speech. However, the previous methods have remained several problems. While autoregressive models suffer from slow inference speed,