Zobrazeno 1 - 10
of 2 623
pro vyhledávání: '"LIU Shijie"'
Publikováno v:
Gong-kuang zidonghua, Vol 49, Iss 8, Pp 70-80 (2023)
Unmanned driving technology has enormous advantages in improving efficiency, saving costs and reducing safety hazards. In the current implementation of localization and navigation solutions in underground environments, there are problems of implement
Externí odkaz:
https://doaj.org/article/0432867ae1cb4759b2421a5120437587
Autor:
Ye, Rui, Li, Guangzhen, Wan, Shuai, Xue, Xiaotian, Wang, Piyu, Qiao, Xin, Li, Hao, Liu, Shijie, Wang, Jiayu, Ma, Rui, Bo, Fang, Zheng, Yuanlin, Dong, Chunhua, Yuan, Luqi, Chen, Xianfeng
Integrated photonics provides an important platform for simulating physical models with high-performance chip-scale devices, where the lattice size and the time-dependence of a model are key ingredients for further enriching the functionality of a ph
Externí odkaz:
http://arxiv.org/abs/2408.00287
Autor:
Li, Zengya, Hu, Zhuoran, Ye, Xiaona, Mao, Zhengyang, Feng, Juan, Li, Hao, Liu, Shijie, Wang, Bo, Zheng, Yuanlin, Chen, Xianfeng
Second-order nonlinearity gives rise to many distinctive physical phenomena, e.g., second-harmonic generation, which plays an important role in fundamental science and various applications. Lithium niobate, one of the most widely used nonlinear cryst
Externí odkaz:
http://arxiv.org/abs/2407.02214
Autor:
Liu, Shijie, Yan, Kang, Qin, Feiwei, Wang, Changmiao, Ge, Ruiquan, Zhang, Kai, Huang, Jie, Peng, Yong, Cao, Jin
Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low-resolution counterpart. Despite the notable advancements achieved by leveraging deep neural networks fo
Externí odkaz:
http://arxiv.org/abs/2405.10561
Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calculated size. While there is value in these certifications, the technique
Externí odkaz:
http://arxiv.org/abs/2309.11005
Publikováno v:
Proceedings of the 2023 AAAI Conference on Artificial Intelligence, 37(7), 8861-8869
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them potentially cou
Externí odkaz:
http://arxiv.org/abs/2308.07553
Autor:
Cai, Hongjie, Song, Nan, Wang, Zengzhi, Xie, Qiming, Zhao, Qiankun, Li, Ke, Wu, Siwei, Liu, Shijie, Yu, Jianfei, Xia, Rui
Aspect-based sentiment analysis is a long-standing research interest in the field of opinion mining, and in recent years, researchers have gradually shifted their focus from simple ABSA subtasks to end-to-end multi-element ABSA tasks. However, the da
Externí odkaz:
http://arxiv.org/abs/2306.16956
In image denoising, deep convolutional neural networks (CNNs) can obtain favorable performance on removing spatially invariant noise. However, many of these networks cannot perform well on removing the real noise (i.e. spatially variant noise) genera
Externí odkaz:
http://arxiv.org/abs/2305.04269