Zobrazeno 1 - 10
of 334
pro vyhledávání: '"Hu, Xiyuan"'
Autor:
Hu, Xiyuan1 (AUTHOR), Liu, Hongdou1,2 (AUTHOR), Luo, Tiao3 (AUTHOR), Chen, Ling1 (AUTHOR), Peng, Ting1 (AUTHOR), Wen, Min1,2 (AUTHOR), Luo, Wensong1 (AUTHOR), Xu, Qunfang2 (AUTHOR), Xie, Yuanzhu1 (AUTHOR), Li, Mo1,4 (AUTHOR), Liu, Mingquan1 (AUTHOR), Liu, Xiaohe1 (AUTHOR), Liu, Suyou5 (AUTHOR), Zhu, Shuaiwen5 (AUTHOR), Zou, Zizheng1,2 (AUTHOR) zizhengzou@hotmail.com, Luo, Zhiyong1 (AUTHOR) luozhiyong@csu.edu.cn
Publikováno v:
Scientific Reports. 11/19/2024, Vol. 14 Issue 1, p1-11. 11p.
Publikováno v:
In Image and Vision Computing November 2024 151
Autor:
Chen, Xiaoxia, Li, Xin, Fan, Yuqing, Hu, Guocheng, Xie, Hang, Chen, Xiaoyan, Ding, Ping, Dang, Yao, Hu, Xiyuan, Chen, Qinghua
Publikováno v:
In Science of the Total Environment 15 August 2024 938
Publikováno v:
In Information Fusion June 2024 106
Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the performance on he
Externí odkaz:
http://arxiv.org/abs/2104.10510
Publikováno v:
In Atmospheric Pollution Research March 2024 15(3)
Publikováno v:
Transactions on Multimedia 2020
Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric. Owing to visual ambiguities, these content-based methods that determine the pairwise relationship
Externí odkaz:
http://arxiv.org/abs/2009.03098
Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture. To further improve the performance of GAN based models on super
Externí odkaz:
http://arxiv.org/abs/2005.00306
Publikováno v:
In Neurocomputing 28 March 2023 527:36-46
Publikováno v:
In Pattern Recognition January 2023 133