Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Qiu, Yuning"'
Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network decompositi
Externí odkaz:
http://arxiv.org/abs/2204.01732
Anomaly driving detection is an important problem in advanced driver assistance systems (ADAS). It is important to identify potential hazard scenarios as early as possible to avoid potential accidents. This study proposes an unsupervised method to qu
Externí odkaz:
http://arxiv.org/abs/2203.08289
Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to predict missing entries from partial observations. However, existing methods often make the explicit or implicit assumption that the observed entries are noise
Externí odkaz:
http://arxiv.org/abs/2203.08857
Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstrated superiority in solving the RTC problem. However, the existing meth
Externí odkaz:
http://arxiv.org/abs/2202.13321
Tensor robust principal component analysis (TRPCA) is a fundamental model in machine learning and computer vision. Recently, tensor train (TT) decomposition has been verified effective to capture the global low-rank correlation for tensor recovery ta
Externí odkaz:
http://arxiv.org/abs/2112.10771
We make an attempt to understanding convolutional neural network by exploring the relationship between (deep) convolutional neural networks and Volterra convolutions. We propose a novel approach to explain and study the overall characteristics of neu
Externí odkaz:
http://arxiv.org/abs/2110.09902
Publikováno v:
In Neural Networks July 2024 175
Publikováno v:
In Advances in Space Research March 2024
Autor:
Qiu, Yuning1,2 (AUTHOR), Pei, Dongling1 (AUTHOR), Wang, Minkai1 (AUTHOR), Wang, Qimeng2,3 (AUTHOR), Duan, Wenchao1 (AUTHOR), Wang, Li3 (AUTHOR), Liu, Kehan2,3 (AUTHOR), Guo, Yu1 (AUTHOR), Luo, Lin1 (AUTHOR), Guo, Zhixuan1 (AUTHOR), Guan, Fangzhan1 (AUTHOR), Wang, Zilong1 (AUTHOR), Xing, Aoqi1 (AUTHOR), Liu, Zhongyi1 (AUTHOR), Ma, Zeyu1 (AUTHOR), Jiang, Guozhong3 (AUTHOR), Yan, Dongming1 (AUTHOR), Liu, Xianzhi1 (AUTHOR) xzliu06@126.com, Zhang, Zhenyu1 (AUTHOR) fcczhangzy1@zzu.edu.cn, Wang, Weiwei3 (AUTHOR) wangweiwei0086@zzu.edu.cn
Publikováno v:
CNS Neuroscience & Therapeutics. Apr2024, Vol. 30 Issue 4, p1-15. 15p.
In tensor completion, the latent nuclear norm is commonly used to induce low-rank structure, while substantially failing to capture the global information due to the utilization of unbalanced unfolding scheme. To overcome this drawback, a new latent
Externí odkaz:
http://arxiv.org/abs/1910.05986