Zobrazeno 1 - 10
of 248
pro vyhledávání: '"Che-Rung Lee"'
Autor:
Oscar Lijen Hsu, Che-Rung Lee
Publikováno v:
IEEE Access, Vol 8, Pp 23369-23377 (2020)
Conventional sub-trajectory clustering is used to identify similarities among multiple trajectories. Existing methods tend to overlook many of the relevant sub-trajectories; others require a road network as input; all are significantly slowed down co
Externí odkaz:
https://doaj.org/article/5b111cbbc9e54e6380c4f9f9c97b3fe2
Autor:
Guann-Ling Shen, Che-Rung Lee
Publikováno v:
2022 IEEE International Conference on Cloud Computing Technology and Science (CloudCom).
Autor:
Wei-Cheng Hung, Che-Rung Lee
Publikováno v:
2022 IEEE International Conference on Cloud Computing Technology and Science (CloudCom).
Publikováno v:
2022 IEEE International Conference on Cloud Computing Technology and Science (CloudCom).
Publikováno v:
Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion.
Publikováno v:
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI).
Autor:
Chi-Hsi Kung, Che-Rung Lee
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Autor:
Chia-Chun Liang, Che-Rung Lee
Publikováno v:
IPDPS Workshops
Tensor decomposition is one of the model reduction techniques for compressing deep neural networks. Existing methods use either Tucker decomposition (TD) or Canonical Polyadic decomposition (CPD) for model compression, but none of them tried to combi
Autor:
Erh-Chung Chen, Che-Rung Lee
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695347
ACCV (3)
ACCV (3)
The adversarial training, which augments the training data with adversarial examples, is one of the most effective methods to defend adversarial attacks. However, its robustness degrades for complex models, and the producing of strong adversarial exa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::81777c1f23f81133a7abc09c19ab5662
https://doi.org/10.1007/978-3-030-69535-4_35
https://doi.org/10.1007/978-3-030-69535-4_35
Publikováno v:
TAAI
Style transfer of the polyphonic music recordings has always been a challenging task due to the difficulty of learning representations for both domain invariant (i.e. content) and domain-variant (i.e. style) features of the music. Although there exis