Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Luo, Yunpeng"'
Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing sev
Externí odkaz:
http://arxiv.org/abs/2409.09860
We consider the anisotropic Finsler $N$-Laplacian Liouville equation \[-\Delta ^{H}_{N}u=e^u \qquad {\rm{in}}\,\, \mathcal{C},\] where $N\geq2$, $\mathcal{C}\subseteq\mathbb{R}^{N}$ is an open convex cone including $\mathbb{R}^{N}$, the half space $\
Externí odkaz:
http://arxiv.org/abs/2407.04987
The evolution of Diffusion Models has dramatically improved image generation quality, making it increasingly difficult to differentiate between real and generated images. This development, while impressive, also raises significant privacy and securit
Externí odkaz:
http://arxiv.org/abs/2403.17465
In autonomous driving (AD), accurate perception is indispensable to achieving safe and secure driving. Due to its safety-criticality, the security of AD perception has been widely studied. Among different attacks on AD perception, the physical advers
Externí odkaz:
http://arxiv.org/abs/2308.11894
Localization in high-level Autonomous Driving (AD) systems is highly security critical. While the popular Multi-Sensor Fusion (MSF) based design can be more robust against single-source sensor spoofing attacks, it is found recently that state-of-the-
Externí odkaz:
http://arxiv.org/abs/2307.14540
Autor:
Shen, Junjie, Wang, Ningfei, Wan, Ziwen, Luo, Yunpeng, Sato, Takami, Hu, Zhisheng, Zhang, Xinyang, Guo, Shengjian, Zhong, Zhenyu, Li, Kang, Zhao, Ziming, Qiao, Chunming, Chen, Qi Alfred
Autonomous Driving (AD) systems rely on AI components to make safety and correct driving decisions. Unfortunately, today's AI algorithms are known to be generally vulnerable to adversarial attacks. However, for such AI component-level vulnerabilities
Externí odkaz:
http://arxiv.org/abs/2203.05314
Publikováno v:
In Pattern Recognition February 2025 158
Autor:
Zhao, Yang, Chen, Yuanyuan, Liu, Ziru, Zhou, Lei, Huang, Jiao, Luo, Xi, Luo, Yunpeng, Li, Jia, Lin, Yunan, Lai, Jian, Liu, Jingchen
Publikováno v:
In Free Radical Biology and Medicine July 2024 219:1-16
Autor:
Luo, Yunpeng, Ji, Jiayi, Sun, Xiaoshuai, Cao, Liujuan, Wu, Yongjian, Huang, Feiyue, Lin, Chia-Wen, Ji, Rongrong
Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning. However, they are still criticized for the lack of contextual information and fine-grained details, which
Externí odkaz:
http://arxiv.org/abs/2101.06462
Autor:
Ji, Jiayi, Luo, Yunpeng, Sun, Xiaoshuai, Chen, Fuhai, Luo, Gen, Wu, Yongjian, Gao, Yue, Ji, Rongrong
Transformer-based architectures have shown great success in image captioning, where object regions are encoded and then attended into the vectorial representations to guide the caption decoding. However, such vectorial representations only contain re
Externí odkaz:
http://arxiv.org/abs/2012.07061