检索结果-内蒙古大学图书馆

Workshops held at the 16th European Conference on computer Vision, ECCV 2020

作者： Zhang, Kai Danelljan, Martin Li, Yawei Timofte, Radu Liu, Jie Tang, Jie Wu, Gangshan Zhu, Yu He, Xiangyu Xu, Wenjie Li, Chenghua Leng, Cong Cheng, Jian Wu, Guangyang Wang, Wenyi Liu, Xiaohong Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao Luo, Xiaotong Chen, Liang Zhang, Jiangtao Suin, Maitreya Purohit, Kuldeep Rajagopalan, A.N. Li, Xiaochuan Lang, Zhiqiang Nie, Jiangtao Wei, Wei Zhang, Lei Muqeet, Abdul Hwang, Jiwon Yang, Subin Kang, JungHeum Bae, Sung-Ho Kim, Yongwoo Qu, Yanyun Jeon, Geun-Woo Choi, Jun-Ho Kim, Jun-Hyuk Lee, Jong-Seok Marty, Steven Marty, Eric Xiong, Dongliang Chen, Siang Zha, Lin Jiang, Jiande Gao, Xinbo Lu, Wen Wang, Haicheng Bhaskara, Vineeth Levinshtein, Alex Tsogkas, Stavros Jepson, Allan Kong, Xiangzhen Zhao, Tongtong Zhao, Shanshan Hrishikesh, P.S. Puthussery, Densen Jiji, C.V. Nan, Nan Liu, Shuai Cai, Jie Meng, Zibo Ding, Jiaming Ho, Chiu Man Wang, Xuehui Yan, Qiong Zhao, Yuzhi Chen, Long Sun, Long Wang, Wenhao Liu, Zhenbing Lan, Rushi Umer, Rao Muhammad Micheloni, Christian Computer Vision Lab ETH Zurich Zürich Switzerland State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China MAICRO Nanjing China University of Electronic Science and Technology of China Nanjing China McMaster University Hamilton Canada Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China Xiamen University Xiamen China Indian Institute of Technology Madras Chennai India Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science Northwestern Polytechnical University Xi’an China Kyung Hee University Seoul Korea Republic of Sang Myung University Seoul Korea Republic of Yonsei University Seoul Korea Republic of ETH Zurich Zürich Switzerland Zhejiang University Hangzhou China Shandong China Xidian University Xi’an China Samsung AI Centre Toronto Canada Wuhan China Dalian Maritime University Dalian China China Everbright Bank Co. Ltd. Beijing China College of Engineering Trivandrum India Jinan China InnoPeak Technology Inc. Palo Alto United States SenseTime Research Hong Kong China Sun Yat-sen University Guangzhou China City University of Hong Kong Kowloon Hong Kong Guilin University of Electronic Technology Guilin541004 China University of Udine Udine Italy

ISBN: (纸本)9783030670696

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor × 4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution. © 2020, Springer Nature Switzerland AG.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Erratum: “Enhanced acoustic pressure sensors based on coherent perfect absorber-laser effect” [J. Appl. Phys. 129, 104902 (2021)]

引用

Journal of Applied Physics 2021年第22期129卷

作者： Mohamed Farhat Waqas W. Ahmad Abdelkrim Khelif Khaled N. Salama Ying Wu 1Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia 2Institut FEMTO-ST CNRS Universite de Bourgogne Franche-Comte 25000 Besancon France 3Sensors Lab Advanced Membranes & Porous Materials Center (AMPMC) King Abdullah University of Science and Technology (KAUST) Thuwal 23955 Saudi Arabia

There is a typo in Eq. (2) of the original paper.1 The corrected form of this equation is

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Drain Current Density of E-Mode AlGaN/GaN HEMT with Double-Doped P-Gate

Improved Drain Current Density of E-Mode AlGaN/GaN HEMT with...

引用

International Conference on Solid-State and Integrated Circuit Technology

作者： Wenteng Kuang Hui Sun Meihua Liu Xinnan Lin Dongmin Chen The Shenzhen Key Lab of Advanced Electron Device and Integration School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Academy for Advanced Interdisciplinary Studies Peking University Beijing China

A novel E-mode AlGaN/GaN HEMT with double-doped p-gate (DDP) is proposed to improve output current and verified by TCAD simulation. The heavily p-doped region of the AlGaN gate layer ensures enhancement-mode (E-mode) operation and the lightly p-doped region of the AlGaN gate layer reduces the channel resistance. The simulated results have demonstrated that DDP HEMT delivers a much larger maximum drain current (I MAX = 334 mA/mm) than the conventional p-gate (CP) HEMT (I MAX = 144 mA/mm) while maintaining a high threshold voltage (V TH ~1.5 V). The simulated results also indicate that the DDP gate structure could decrease the peak electric field (E C ) and thus improve the reliability of the device under off-state high-drain-bias (HDBT).

关键词： HEMTs Logic gates Aluminum gallium nitride Wide band gap semiconductors Electric fields Doping Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Sparse weighted naive bayes classifier for efficient classification of categorical data 3

Sparse weighted naive bayes classifier for efficient classif...

引用

3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018

作者： Zheng, Zhuoyuan Cai, Yunpeng Yang, Yujie Li, Ye Guangxi Key Laboratory of Trusted Software Guangxi Colleges and Universities Key Lab. of Intelligent Processing of Computer Images and Graphics Guilin University of Electronic Technology Guilin541004 China Shenzhen Institutes of Advanced Technology Key Laboratory for Biomedical Informatics and Health Engineering Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781538642108

Feature selection has become a key challenge in machine learning with the rapid growth of data size in real-world applications. However, existing feature selection methods mainly focus on numeric data, which will lead to quality loss when handling classification problems involving categorical variables. In this paper, we proposed an improvement of Bayesian Classifier with the sparse regression technology. To the best of our knowledge, this is the first attempt to extend sparse regression for directly process of categorical variables. We implemented the idea for the case of weighted naive Bayes classifier. The introduction of L1 regularized learning ensures the algorithm to retain only a minimal subset of variables for model building, while at the same time achieves a near-optimal decision hyper-plane, which leads to excellent performance in case of high dimensional or small sample size situations. We carried out benchmark test on five UCI benchmark categorical data sets, which proved that the proposed algorithm have competitive performances over the original weighted naive bayes classifier and several state-of-the-art feature selection methods including L1 logistic regression and SVM-RFE. © 2018 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An On-Chip Oscillator with Comparator Offset Cancellation

An On-Chip Oscillator with Comparator Offset Cancellation

引用

IEEE Conference on Electron Devices and Solid-State Circuits

作者： Dewei Zhang Ruijun Zhang Hesheng Lin Qinghua Wang Min Zhang The Shenzhen Key Lab of Advanced Electron Device and Integration School of Electronic and Computer Engineering Peking University Shenzhen China imec-KU Leuven Leuven Belgium

ISBN: (纸本)9781538662359

This work presents an on-chip oscillator with offset cancellation in 0.25 μm process. By automatically choosing the reference voltage in a single comparator, the proposed oscillator can perfectly achieve offset cancellation. In addition, it reduces the comparator count from two to one for area-saving and power-saving. The simulation results exhibit a Temperature Coefficient of 2.3 ppm/°C from -40 to 90 °C while consuming 6.5 μW at 30 kHz.

关键词： Oscillators System-on-chip Clocks Delays Capacitors Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Deep high-order supervised hashing

引用

Optik 2019年 180卷 847-857页

作者： Jing Dong Cheng Qiu Le Sun Jian Xin Zhang Christian Desrosiers Bin Liu Jian Lu Qiang Zhang Key Lab of Advanced Design and Intelligent Computing (Ministry of Education) Dalian University Dalian 116622 China School of Information and Communication Engineering Dalian University of Technology Dalian 116024 China Laboratory for Imagery Vision and Artificial Intelligence (LIVAI) École de technologie supérieure (ETS) Montreal H3C1K3 Canada International School of Information Science and Engineering (DUT-RUISE) Dalian University of Technology Dalian 116622 China School of Computer Science and Technology Dalian University of Technology Dalian 116024 China

Recently, deep hashing has achieved excellent performance in large-scale image retrieval by simultaneously learning deep features and hash function. However, state-of-the-art methods for this task have so far failed to explore feature statistics higher than first-order. To address this problem, we propose two novel deep high-order supervised hashing (DHoSH) architectures based on point-wise labels (DHoSH-PO) and pair-wise labels (DHoSH-PA), respectively. The core of DHoSH is a trainable layer of bilinear features incorporated into existing deep convolutional neural network (CNN) for end-to-end learning. This layer captures the interaction of local features by bilinear pooling, using correlation to model dependencies of features within the same layer or cross-correlation for features across different layers of the CNN. Furthermore, DHoSH systematically employs the high-order statistics of features of multiple layers. Extensive experiments on commonly used image retrieval benchmarks show that our DHoSH-PO and DHoSH-PA models yield improved accuracy over its first-order counterparts and achieve effective performance for these benchmarks.

关键词： High-order statistics Supervised hashing Bilinear pooling CNN Image retrieval

来源：评论

学校读者我要写书评

暂无评论

A High-Efficient, Multi-Phase Charge Pump Scheme

A High-Efficient, Multi-Phase Charge Pump Scheme

引用

IEEE Conference on Electron Devices and Solid-State Circuits

作者： Dewei Zhang Binjie Liu Hesheng Lin Dedong Ding Min Zhang The Shenzhen Key Lab of Advanced Electron Device and Integration School of Electronic and Computer Engineering Peking University Shenzhen China imec-KU Leuven Leuven Belgium

ISBN: (纸本)9781538662359

In this paper, a high-efficiency solution to multi-phase stepup charge pump is proposed. Aiming at traditional multi-phase charge pump with full-coverage integer voltage conversion ratios (VCRs) for good efficiency, we further improve its efficiency at some particular VCRs. By automatically bypassing some unnecessary converter stages, dynamic power loss is reduced. Based on a 0.25 μm process, an example of three-stage charge pump with VCRs of 1~8 is conducted. It shows that converter with proposed control strategy has improved perofrmance at VCR

关键词： Video recording Charge pumps Clocks Solid state circuits Switches Capacitors Transient response

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering

arXiv

引用

arXiv 2018年

作者： Deng, Yang Xie, Yuexiang Li, Yaliang Yang, Min Du, Nan Fan, Wei Lei, Kai Shen, Ying School of Electronics and Computer Engineering Peking University Shenzhen Graduate School Tencent Medical AI Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the rich correlation information between tasks. In this paper, we tackle answer selection and KBQA tasks simultaneously via multi-task learning (MTL), motivated by the following motivations. First, both answer selection and KBQA can be regarded as a ranking problem, with one at text-level while the other at knowledge-level. Second, these two tasks can benefit each other: answer selection can incorporate the external knowledge from knowledge base (KB), while KBQA can be improved by learning contextual information from answer selection. To fulfill the goal of jointly learning these two tasks, we propose a novel multi-task learning scheme that utilizes multi-view attention learned from various perspectives to enable these tasks to interact with each other as well as learn more comprehensive sentence representations. The experiments conducted on several real-world datasets demonstrate the effectiveness of the proposed method, and the performance of answer selection and KBQA is improved. Also, the multi-view attention scheme is proved to be effective in assembling attentive information from different representational perspectives. Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Full-Coverage Voltage-Conversion-Ratio Fibonacci-Like Charge Pump

An Algorithm for Full-Coverage Voltage-Conversion-Ratio Fibo...

引用

IEEE Conference on Electron Devices and Solid-State Circuits

作者： Binjie Liu Hesheng Lin Dedong Ding Dewei Zhang Min Zhang The Shenzhen Key Lab of Advanced Electron Device and Integration School of Electronic and Computer Engineering Peking University Shenzhen China imec-KU Leuven Leuven Belgium

ISBN: (纸本)9781538662359

In this work, an algorithm for full-coverage voltage-conversion-ratio (VCR) Fibonacci-like charge pump is proposed. By shifting the connect node of each flying capacitor's bottom plate, a charge pump topology can achieve arbitrary integer voltage conversion ratios. By the algorithm, we can find the best Fibonacci-like charge pump topology with the least number of capacitors and transistors, for a given VCR.

关键词： Charge pumps Video recording Capacitors Topology Transistors Clocks

来源：评论

学校读者我要写书评

暂无评论

Region-wise generative adversarial image inpainting for large missing areas

arXiv

引用

arXiv 2019年

作者： Ma, Yuqing Liu, Xianglong Bai, Shihao Wang, Lei Liu, Aishan Tao, Dacheng Hancock, Edwin State Key Lab of Software Development Environment Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine UBTECH Sydney Artificial Intelligence Centre School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney DarlingtonNSW2008 Australia Department of Computer Science University of York York United Kingdom

Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless contents, such as color discrepancy, blur and artifacts. Moreover, most inpainting approaches cannot well handle the large contiguous missing area cases. To address these problems, we propose a generic inpainting framework capable of handling with incomplete images on both contiguous and discontiguous large missing areas, in an adversarial manner. From which, region-wise convolution is deployed in both generator and discriminator to separately handle with the different regions, namely existing regions and missing ones. Moreover, a correlation loss is introduced to capture the non-local correlations between different patches, and thus guides the generator to obtain more information during inference. With the help of our proposed framework, we can restore semantically reasonable and visually realistic images. Extensive experiments on three widely-used datasets for image inpainting tasks have been conducted, and both qualitative and quantitative experimental results demonstrate that the proposed model significantly outperforms the state-of-the-art approaches, both on the large contiguous and discontiguous missing areas. Copyright © 2019, 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

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：