Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Xiaoyang TAN"'
Publikováno v:
Mathematics, Vol 12, Iss 19, p 3068 (2024)
Federated learning facilitates collaborative computation among multiple participants while safeguarding user privacy. However, current federated learning algorithms operate under the assumption that all participants are trustworthy and their systems
Externí odkaz:
https://doaj.org/article/2cc7a68e179f4cd1ab8af167357f5d07
Autor:
Yuan Feng, Kaihua Zhang, Ang Li, Yangyang Zhang, Kun Wang, Nan Guo, Ho Yi Wan, Xiaoyang Tan, Nalin Dong, Xin Xu, Ruizhen He, Bing Wang, Long Fan, Shidong Ge, Peihao Song
Publikováno v:
Land, Vol 13, Iss 9, p 1474 (2024)
Greenscaping, a key sustainable practice, helps cities combat rising temperatures and climate change. Urban parks, a pivotal greenscaping element, mitigate the urban heat island (UHI) effect. In this study, we utilized high-resolution remote sensing
Externí odkaz:
https://doaj.org/article/098bd2338c054eb5917f6be4e4da75ec
Autor:
Ming Chen, Xiaoyang Tan
Publikováno v:
IET Computer Vision, Vol 8, Iss 6, Pp 475-486 (2014)
In this study, the authors propose a new method for part‐based human pose estimation. The key idea of the authors method is to improve the accuracies for leaf parts localisations – an issue that was largely ignored by the previous study – by in
Externí odkaz:
https://doaj.org/article/9ea2ce0b5cfd4c199be4373d54827ab7
Publikováno v:
IEEE transactions on cybernetics, 2018
In the era of Internet, recognizing pornographic images is of great significance for protecting children's physical and mental health. However, this task is very challenging as the key pornographic contents (e.g., breast and private part) in an image
Externí odkaz:
http://arxiv.org/abs/1902.03771
Publikováno v:
Journal of the Japanese Society of Revegetation Technology. 48:476-479
Autor:
Xiaoyang Tan, Shozo Shibata
Publikováno v:
Landscape and Ecological Engineering.
Publikováno v:
2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI).
Autor:
Yuhui Wang, Xiaoyang Tan
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:10236-10244
In many real-world sequential decision-making tasks, especially in continuous control like robotic control, it is rare that the observations are perfect, that is, the sensory data could be incomplete, noisy or even dynamically polluted due to the une
Publikováno v:
Pattern Recognition. 137:109276