Zobrazeno 1 - 10
of 446
pro vyhledávání: '"Zhu Zijian"'
Autor:
Zhu, Zijian, Zia, Ali, Li, Xuesong, Dan, Bingbing, Ma, Yuebo, Long, Hongfeng, Lu, Kaili, Liu, Enhai, Zhao, Rujin
Stripe-like space target detection (SSTD) is crucial for space situational awareness. Traditional unsupervised methods often fail in low signal-to-noise ratio and variable stripe-like space targets scenarios, leading to weak generalization. Although
Externí odkaz:
http://arxiv.org/abs/2408.05029
Stripe-like space target detection (SSTD) plays a key role in enhancing space situational awareness and assessing spacecraft behaviour. This domain faces three challenges: the lack of publicly available datasets, interference from stray light and sta
Externí odkaz:
http://arxiv.org/abs/2407.18097
Memory is a critical design consideration in current data-intensive DNN accelerators, as it profoundly determines energy consumption, bandwidth requirements, and area costs. As DNN structures become more complex, a larger on-chip memory capacity is r
Externí odkaz:
http://arxiv.org/abs/2402.00629
Autor:
Hu, Feiran, Wang, Peng, Li, Yangyang, Duan, Chenlong, Zhu, Zijian, Wang, Fei, Zhang, Faen, Li, Yong, Wei, Xiu-Shen
The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata. This paper presents a method leveraging utilization of both images and metadata. M
Externí odkaz:
http://arxiv.org/abs/2307.09748
Autor:
Zhu, Zijian, Zhang, Yichi, Chen, Hai, Dong, Yinpeng, Zhao, Shu, Ding, Wenbo, Zhong, Jiachen, Zheng, Shibao
3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks.
Externí odkaz:
http://arxiv.org/abs/2303.17297
Autor:
Dong, Yinpeng, Kang, Caixin, Zhang, Jinlai, Zhu, Zijian, Wang, Yikai, Yang, Xiao, Su, Hang, Wei, Xingxing, Zhu, Jun
3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor noises, etc., p
Externí odkaz:
http://arxiv.org/abs/2303.11040
Publikováno v:
Computer Vision and Image Understanding 230C (2023) 103659
Modern object detectors are vulnerable to adversarial examples, which may bring risks to real-world applications. The sparse attack is an important task which, compared with the popular adversarial perturbation on the whole image, needs to select the
Externí odkaz:
http://arxiv.org/abs/2303.00284
Autor:
Zhou, Haoyu, Yao, Zhiming, Sheng, Liang, Song, Yan, Liu, Zhen, Han, Changcai, Zhu, Zijian, Li, Yang, Duan, Baojun, Ji, Chao, Wu, Jian, Hei, Dongwei, Liu, Yinong
Publikováno v:
In Optics and Lasers in Engineering December 2024 183
Publikováno v:
In Food Bioscience October 2024 61
Publikováno v:
In Pattern Recognition Letters February 2025 188:95-102