检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Liu, Xin Yan, Mingyu Deng, Lei Li, Guoqi Ye, Xiaochun Fan, Dongrui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100086 China Department of Precision Instrument Center for Brain Inspired Computing Research Tsinghua University Beijing100084 China School of Computer Science and Technology University of Chinese Academy of Sciences

—Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Talking Face Generation via Learning Semantic and Temporal Synchronous Landmarks

Talking Face Generation via Learning Semantic and Temporal S...

引用

International Conference on Pattern Recognition

作者： Aihua Zheng Feixia Zhu Hao Zhu Mandi Luo Ran He Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Heifei China Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) CASIA Beijing China Center for Excellence in Brain Science and Intelligence Technology CAS Beijing China

ISBN: (纸本)9781728188089;9781728188096

Given a speech clip and facial image, the goal of talking face generation is to synthesize a talking face video with accurate mouth synchronization and natural face motion. Recent progress has proven the effectiveness of the landmarks as the intermediate information during talking face generation. However, the large gap between audio and visual modalities makes the prediction of landmarks challenging and limits generation ability. This paper proposes a semantic and temporal synchronous landmark learning method for talking face generation. First, we propose to introduce a word detector to enforce richer semantic information. Then, we propose to preserve the temporal synchronization and consistency between landmarks and audio via the proposed temporal residual loss. Lastly, we employ a U-Net generation network with adaptive reconstruction loss to generate facial images for the predicted landmarks. Experimental results on two benchmark datasets LRW and GRID demonstrate the effectiveness of our model compared to the state-of-the-art methods of talking face generation.

关键词： Learning systems Visualization Face recognition Semantics Mouth Detectors Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Functional Connection Analysis in Nidupallium Caudolaterale of Pigeons During the Operant Conditioning Learning Process

Functional Connection Analysis in Nidupallium Caudolaterale ...

引用

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： You Liang Mengmeng Li Lifang Yang Zhigang Shang Hong Wan Industrial Technology Research Institute Zhengzhou University Zhengzhou China Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou China

The avian nidupallium caudolaterale (NCL), a key region of cognitive learning process, it is believed that it play an important role in the process of operational conditioned learning. To reveal the changes of neural activity in operant conditioning learning process, the experimental paradigms of operant conditioning are designed in this paper. The behavioral data and local field potential (LFP) signals of three experimental periods (induction, acquisition and extinction) from the NCL of three pigeons are recorded. Then, on the basis of coherence calculation, NCL functional networks in specific frequency bands (30-60 Hz) during three experimental periods are constructed, then we analyze and compare the topology characteristics of the network. The experimental results of behavioral and LFP data analysis indicate that during the period of induction, pigeons do not establish stable operant conditioning relationship, and the connection of the network is sparse, in which the connection strength and information transmission efficiency are at a low level. In the acquisition period, pigeons can establish this relationship through learning, the functional network connection becomes tighter, and the connection strength and information transmission efficiency are significantly improved. In the extinction period in which the operant conditioning relationship is destroyed, the functional connection is weakened. These results show that pigeons can establish stable operant conditioning relationship through learning, and strengthen the functional connection of NCL, making the information transmission more efficient. This paper provides basic electrophysiological experimental evidence for further revealing the dynamic functional connection mechanism in NCL of pigeons.

关键词： Coherence Task analysis Information processing Animals Light emitting diodes Time factors Time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

CT Scan Synthesis for Promoting computer-Aided Diagnosis Capacity of COVID-19 16th

CT Scan Synthesis for Promoting Computer-Aided Diagnosis Cap...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Li, Heng Hu, Yan Li, Sanqian Lin, Wenjun Liu, Peng Higashita, Risa Liu, Jiang School of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China Tomey Corporation Nagoya451-0051 Japan Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen518055 China Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

ISBN: (纸本)9783030608019

Nowadays, with the rapid spread of Corona Virus Disease 2019 (COVID-19), this epidemic has become a threatening risk for global public health. Medical workers and researchers all over the world are struggling against the novel coronavirus in the front line. Because the computed tomography (CT) images from infected patients exposure characteristic abnormalities, automatic CT analyzers based on AI-based algorithms are extensively employed as effective weapons to aid clinicians. However, unbalanced data and lack of annotations obstruct AI-based algorithms applying in aided diagnosis because of their low performance. Therefore, in order to solve the above problems, a general-purpose solution is proposed to synthesize COVID-19 CT scans from non-COVID-19 data for providing high-quality negative-positive paired CT scans. Particularly, we introduce an elastic registration algorithm of CT images to manufacture paired training data. Then, a conditional Generative Adversarial Networks (GANs) based image-to-image translation model is implemented to synthesize COVID-19 CT scans from non-COVID-19 data. The effectiveness of our proposed algorithm used in COVID-19 aided diagnosis is verified in the experiments, and the identification and detection capacities of the classification models have been enhanced with the generated CT scans. Specifically, the precise lesion location is achieved by the generated data with a weakly supervised algorithm of class activation mapping (CAM). The model and code of this paper are publicly available at https://***/lihengbit/Synthesis-of-COVID-19-CT-Scan. © 2020, Springer Nature Switzerland AG.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Combination of NMF and IVA for improving the quality of EOG signals 5

Combination of NMF and IVA for improving the quality of EOG ...

引用

5th IEEE International Conference on Signal and Image Processing, ICSIP 2020

作者： Sun, Wenhui Xue, Bing Xue, Jingyi Zhang, Shengli Lv, Zhao Anhui University School of Computer Science and Technology Hefei230601 China Suzhou Xiaoma E-Commerce Co. Ltd Suzhou234000 China Hangzhou Dianzi University Zhejiang Key Laboratory for Brain-Machine Collaborative Intelligence Hangzhou310018 China

ISBN: (纸本)9781728168968

Eye movements play an important role in the implementation of human computer interface (HCI) system, which could be recorded by the electrooculography (EOG) technique. However, the recorded EOG signals are always contaminated by various latent artifacts. Aiming at obtaining high-quality EOG signals, a blind source separation (BSS) method combined with non-negative matrix factorization (NMF) and independent vector analysis (IVA), is used in the separation problem of EOG signals. The effectiveness of the addition of NMF is validated on the classification tasks, and the corresponding average classification accuracy is higher than that of extended Infomax independent component analysis (ICA) and IVA, with the improvement of 4.42% and 3.26%, respectively. This result indicates that the combination of NMF and IVA can achieve better separation performance, in which the NMF could provide more information close to the source signals in the iteration step. © 2020 IEEE.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

Genetics Blood-brain barrier–penetrating single CRISPR-Cas9 nanocapsules for effective and safe glioblastoma gene therapy

引用

science Advances 2022年第16期8卷

作者： Zou, Yan Sun, Xinhong Yang, Qingshan Zheng, Meng Shimoni, Olga Ruan, Weimin Wang, Yibin Zhang, Dongya Yin, Jinlong Huang, Xiangang Tao, Wei Park, Jong Bae Liang, Xing-Jie Leong, Kam W. Shi, Bingyang Henan-Macquarie Uni Joint Centre for Biomedical Innovation Academy for Advanced Interdisciplinary Studies Henan Key Laboratory of Brain Targeted Bio-nanomedicine School of Life Sciences Henan University Henan Kaifeng475004 China Macquarie Medical School Faculty of Medicine Health and Human Sciences Macquarie University SydneyNSW2109 Australia Faculty of Science University of Technology Sydney 15 Broadway Ultimo SydneyNSW2007 Australia Center for Nanomedicine Department of Anesthesiology Harvard Medical School 25 Shattuck St. BostonMA02115 United States Department of Cancer Biomedical Science Graduate School of Cancer Science and Policy National Cancer Center Goyang10408 Korea Republic of Center for Excellence in Nanoscience CAS Key Laboratory for Biological Effects of Nano-materials and Nanosafety National Center for Nanoscience and Technology Chinese Academy of Sciences Beijing100190 China Department of Biomedical Engineering Columbia University New YorkNY10032 United States

We designed a unique nanocapsule for efficient single CRISPR-Cas9 capsuling, noninvasive brain delivery and tumor cell targeting, demonstrating an effective and safe strategy for glioblastoma gene therapy. Our CRISPR-Cas9 nanocapsules can be simply fabricated by encapsulating the single Cas9/sgRNA complex within a glutathione-sensitive polymer shell incorporating a dual-action ligand that facilitates BBB penetration, tumor cell targeting, and Cas9/sgRNA selective release. Our encapsulating nanocapsules evidenced promising glioblastoma tissue targeting that led to high PLK1 gene editing efficiency in a brain tumor (up to 38.1%) with negligible (less than 0.5%) off-target gene editing in high-risk tissues. Treatment with nanocapsules extended median survival time (68 days versus 24 days in nonfunctional sgRNA-treated mice). Our new CRISPR-Cas9 delivery system thus addresses various delivery challenges to demonstrate safe and tumor-specific delivery of gene editing Cas9 ribonucleoprotein for improved glioblastoma treatment that may potentially be therapeutically useful in other brain diseases. Copyright © 2022 The Authors, some rights reserved.

关键词： Nanocapsules

来源：评论

学校读者我要写书评

暂无评论

Keiki: Towards realistic danmaku generation via sequential GANs

arXiv

引用

arXiv 2021年

作者： Wang, Ziqi Liu, Jialin Yannakakis, Georgios N. Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Institute of Digital Games University of Malta Msida2080 Malta

Search-based procedural content generation methods have recently been introduced for the autonomous creation of bullet hell games. Search-based methods, however, can hardly model patterns of danmakus—the bullet hell shooting entity—explicitly and the resulting levels often look non-realistic. In this paper, we present a novel bullet hell game platform named Keiki, which allows the representation of danmakus as a parametric sequence which, in turn, can model the sequential behaviours of danmakus. We employ three types of generative adversarial networks (GANs) and test Keiki across three metrics designed to quantify the quality of the generated danmakus. The time-series GAN and periodic spatial GAN show different yet competitive performance in terms of the evaluation metrics adopted, their deviation from human-designed danmakus, and the diversity of generated danmakus. The preliminary experimental studies presented here showcase that potential of time-series GANs for sequential content generation in games. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Meta ordinal regression forest for learning with unsure lung nodules

arXiv

引用

arXiv 2020年

作者： Lei, Yiming Zhu, Haiping Zhang, Junping Shan, Hongming Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai201210 China

Deep learning-based methods have achieved promising performance in early detection and classification of lung nodules, most of which discard unsure nodules and simply deal with a binary classification—malignant vs benign. Recently, an unsure data model (UDM) was proposed to incorporate those unsure nodules by formulating this problem as an ordinal regression, showing better performance over traditional binary classification. To further explore the ordinal relationship for lung nodule classification, this paper proposes a meta ordinal regression forest (MORF), which improves upon the state-of-the-art ordinal regression method, deep ordinal regression forest (DORF), in three major ways. First, MORF can alleviate the biases of the predictions by making full use of deep features while DORF needs to fix the composition of decision trees before training. Second, MORF has a novel grouped feature selection (GFS) module to re-sample the split nodes of decision trees. Last, combined with GFS, MORF is equipped with a meta learning-based weighting scheme to map the features selected by GFS to tree-wise weights while DORF assigns equal weights for all trees. Experimental results on LIDC-IDRI dataset demonstrate superior performance over existing methods, including the state-of-the-art DORF. © 2020, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Modeling and experimental verification of the rapid inversion model of the living body based on the fem model

引用

Recent Patents on Engineering 2021年第3期15卷 287-293页

作者： Zhang, Shuang Liu, Yi He Data Recovery Key Laboratory of Sichuan Province College of Computer Science & AI Neijiang Normal University Neijiang Sichuan China School of Life Science and Technology University of Electronic Science and Technology of P.R.China Chengdu Sichuan China High Field Magnetic Resonance Brain Imaging Laboratory of Sichuan Chengdu Sichuan China Key Laboratory for Neuro Information of Ministry of Education Chengdu Sichuan China

Objective: This study aims to verify the practicability and accuracy of a finite element model (FEM) built using digital human model construction and to apply the model to actual explo-sion impact inversion. Methods: We proposed a simplified rapid inversion model using digital human modeling. In mod-eling, cell mesh generation was performed using preprocessing software (ANSYS ICEM CFD), measured organism data were used as the corresponding geometrical parameters of all specified parts, and material characteristics parameters were set according to tissue characteristics. FEM construction was completed in the ANSYS LS-DYNA software and verified by an equivalent experiment. Results: The rapid inversion FEM was built by employing digital human model construction. Through analysis, it was concluded that the calculation result was practically consistent with the experimental result. Conclusion: By creating the digital human model based on a CT dataset, the FEM inversion model of an approximately actual material environment can be rebuilt, and the model can be used to study human thorax injury characteristics. © 2021 Bentham science Publishers.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "brain network communication in remission: a comparative study of bipolar and unipolar depression" [J. Psychiatr. Res. 186 (2025) 1-8]

引用

Journal of psychiatric research 2025年

作者： Haiyan Liu Yi Xia Lingling Hua Hao Sun Rui Yan Zhijian Yao Jiaolong Qin Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Electronic address: zjyao@***. The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China.

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：