Search

Your search keyword '"Liu Na"' showing total 16,234 results
Start Over Author "Liu Na"
16,234 results on '"Liu Na"'

202. A Survey on Hyperspectral Image Restoration: From the View of Low-Rank Tensor Approximation

Author

Liu, Na, Li, Wei, Wang, Yinjian, Tao, Rao, Du, Qian, and Chanussot, Jocelyn

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

The ability of capturing fine spectral discriminative information enables hyperspectral images (HSIs) to observe, detect and identify objects with subtle spectral discrepancy. However, the captured HSIs may not represent true distribution of ground objects and the received reflectance at imaging instruments may be degraded, owing to environmental disturbances, atmospheric effects and sensors' hardware limitations. These degradations include but are not limited to: complex noise (i.e., Gaussian noise, impulse noise, sparse stripes, and their mixtures), heavy stripes, deadlines, cloud and shadow occlusion, blurring and spatial-resolution degradation and spectral absorption, etc. These degradations dramatically reduce the quality and usefulness of HSIs. Low-rank tensor approximation (LRTA) is such an emerging technique, having gained much attention in HSI restoration community, with ever-growing theoretical foundation and pivotal technological innovation. Compared to low-rank matrix approximation (LRMA), LRTA is capable of characterizing more complex intrinsic structure of high-order data and owns more efficient learning abilities, being established to address convex and non-convex inverse optimization problems induced by HSI restoration. This survey mainly attempts to present a sophisticated, cutting-edge, and comprehensive technical survey of LRTA toward HSI restoration, specifically focusing on the following six topics: Denoising, Destriping, Inpainting, Deblurring, Super--resolution and Fusion. The theoretical development and variants of LRTA techniques are also elaborated. For each topic, the state-of-the-art restoration methods are compared by assessing their performance both quantitatively and visually. Open issues and challenges are also presented, including model formulation, algorithm design, prior exploration and application concerning the interpretation requirements., Comment: Under review in Science China Information Siences

Published
2022

203. Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations

Author

Liu, Na, Dras, Mark, and Zhang, Wei Emma

Subjects
Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly expressive deep classifiers into incorrect predictions. Approaches to adversarial attacks in natural language tasks have boomed in the last five years using character-level, word-level, phrase-level, or sentence-level textual perturbations. While there is some work in NLP on defending against such attacks through proactive methods, like adversarial training, there is to our knowledge no effective general reactive approaches to defence via detection of textual adversarial examples such as is found in the image processing literature. In this paper, we propose two new reactive methods for NLP to fill this gap, which unlike the few limited application baselines from NLP are based entirely on distribution characteristics of learned representations: we adapt one from the image processing literature (Local Intrinsic Dimensionality (LID)), and propose a novel one (MultiDistance Representation Ensemble Method (MDRE)). Adapted LID and MDRE obtain state-of-the-art results on character-level, word-level, and phrase-level attacks on the IMDB dataset as well as on the later two with respect to the MultiNLI dataset. For future research, we publish our code., Comment: 13 pages, RepL4NLP 2022

Published
2022

204. The $(n+1)$-centered operator on a Hilbert $C^*$-module

Author

Liu, Na, Xu, Qingxiang, and Zhang, Xiaofeng

Subjects
Mathematics - Operator Algebras, 46L08, 47A05
Abstract

Let $T$ be an adjointable operator on a Hilbert $C^*$-module such that $T$ has the polar decomposition $T=UT|$. For each natural number $n$, $T$ is called an $(n+1)$-centered operator if $T^k=U^k|T^k|$ is the polar decomposition for $1\le k\le n+1$. This paper initiates the study of the $(n+1)$-centered operator via the generalized Aluthge transform and the generalized iterative Aluthge transform. Some new characterizations of the $(n+1)$-centered operator are provided., Comment: 18 pages

Published
2022
Full Text
View/download PDF

205. Identifying psychiatric and neurological comorbidities associated with hoarding disorder through network analysis.

Author

Sordo Vieira, Luis, Guastello, Andrea, Nguyen, Binh, Nutley, Sara, Ordway, Ashley, Simpson, Heather, Archer, Christian, Liu, Na, Jean Gilles, Marie, Nosheny, Rachel, Mackin, R, Mathews, Carol, Weiner, Michael, and Zakrzewski, Jessica

Subjects
Humans, Hoarding Disorder, Depressive Disorder, Major, Nervous System Diseases
Abstract

BACKGROUND: The relationships between hoarding disorder (HD) and other neurological and psychiatric disorders remain largely unknown. Although psychiatric burden in those with HD is high, less is known about neurological disorders. Furthermore, which disorders are primarily associated with HD vs which can be better explained via a relationship with another disorder has not been determined. To address these questions, we examined comorbidity patterns of psychiatric and neurological disorders in a large online registry of adults using network analyses. METHODS: We first examined psychiatric comorbidity among 252 participants completing clinician administered psychiatric assessments. Using the Brain Health Registry (BHR) (N = 15,978), we next analyzed prevalence of self-reported neurological and psychiatric disorders among participants with no/minimal hoarding, subclinical hoarding, and clinically significant hoarding and used network analyses to identify direct and indirect relationships between HD and the assessed psychiatric and neurological disorders. RESULTS: The most prevalent comorbidity in clinically assessed participants with HD was major depressive disorder (MDD, 62%), followed by generalized anxiety disorder (GAD, 32%). Network analyses in the BHR indicated that the strongest direct relationships with HD were attention-deficit hyperactivity disorder (ADHD), major depressive disorder (MDD), and obsessive-compulsive disorder (OCD). The relationships between HD and neurological disorders, including mild cognitive impairment, were weak or non-existent after controlling for other disorders. CONCLUSIONS: ADHD, MDD, and OCD form a triad of psychiatric disorders directly associated with HD. Despite their high comorbidity rates, the associations among anxiety disorders and HD were weak or indirect.

Published
2022

245. Transplantation of chemically induced pluripotent stem-cell-derived islets under abdominal anterior rectus sheath in a type 1 diabetes patient

Author

Wang, Shusen, Du, Yuanyuan, Zhang, Boya, Meng, Gaofan, Liu, Zewen, Liew, Soon Yi, Liang, Rui, Zhang, Zhengyuan, Cai, Xiangheng, Wu, Shuangshuang, Gao, Wei, Zhuang, Dewei, Zou, Jiaqi, Huang, Hui, Wang, Mingyang, Wang, Xiaofeng, Wang, Xuelian, Liang, Ting, Liu, Tengli, Gu, Jiabin, Liu, Na, Wei, Yanling, Ding, Xuejie, Pu, Yue, Zhan, Yixiang, Luo, Yu, Sun, Peng, Xie, Shuangshuang, Yang, Jiuxia, Weng, Yiqi, Zhou, Chunlei, Wang, Zhenglu, Wang, Shuang, Deng, Hongkui, and Shen, Zhongyang

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results