检索结果-内蒙古大学图书馆

End-to-end Optimized Lossy Compression for Neural-morphic Spiking Camera Captured Data

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Feng, Kexiang Jia, Chuanmin Pan, Jingshan Ma, Siwei Gao, Wen Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Peking University National Engineering Research Center of Visual Technology Beijing100871 China Peking University Wangxuan Institute of Computer Technology Beijing100080 China Shandong Computer Science Center National Supercomputer in Jinan Jinan250014 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we propose a novel Reconstruction-based Contextual Spike Compression (RCSC) framework, which contains scene reconstruction, contextual image compression and spike generation. To our knowledge, it is the first learning-based model for efficient and robust spike stream compression with informative fidelity. Extensive experimental results show that our model outperforms the state-of-the-art conventional codec VVC intra by 6.14% and surpasses the state-of-the-art learned codec by 2.53% in BD-rate reduction, establishing a strong baseline for spike compression. © 1991-2012 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

783-MHz fundamental repetition rate CNT mode-locked all Er-doped fiber ring laser

783-MHz fundamental repetition rate CNT mode-locked all Er-d...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Dai, Maolin Liu, Bowen Ma, Yifan Shirahata, Takuma Yang, Ruoao Zhang, Zhigang Set, Sze Yun Yamashita, Shinji Department of Electrical Engineering and Information Systems The University of Tokyo Bunkyo-ku Tokyo113-8656 Japan Research Center for Advanced Science and Technology The University of Tokyo Meguro-ku Tokyo153-8904 Japan State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Center for Quantum Information Technology Peking University Beijing100871 China

We realize 783-MHz fundamental repetition rate in a carbon-nanotubes (CNT) modelocked Er-doped fiber ring laser with all active fibers. The proposed laser self-starts mode-locking at 108-mW pump power and delivers 623... 详细信息

ISBN: (纸本)9781957171395

关键词： Laser excitation

来源：评论

学校读者我要写书评

暂无评论

Power Allocation Strategy for Secret Key Generation Method in Wireless communications

引用

computers, Materials & Continua 2021年第8期68卷 2179-2188页

作者： Bin Zhang Muhammad Waqas Shanshan Tu Syed Mudassir Hussain Sadaqat Ur Rehman School of Electronics and Information Engineering Hunan University of Science and EngineeringYongzhou425199China Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information TechnologyBeijing University of TechnologyBeijing100124China Faculty of Computer Science and Engineering Ghulam Ishaq Khan(GIK)Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Electronics Engineering FICTBalochistan University of Information TechnologyEngineering and Management SciencesQuetta87300Pakistan Department of Computer Science Namal InstituteMianwali42200Pakistan

Secret key generation(SKG)is an emerging technology to secure wireless communication from ***,the SKG at the physical layer is an alternate solution over traditional cryptographic methods due to wireless channels’***,the physical layer secret key generation(PHY-SKG)depends on two fundamental parameters,i.e.,coherence time and power *** coherence time for PHY-SKG is not applicable to secure wireless *** is because coherence time is for a certain period of ***,legitimate users generate the secret keys(SKs)with a shorter key length in ***,an attacker can quickly get information about the ***,the attacker can easily get valuable information from authentic ***,we considered the scheme of power allocation to enhance the secret key generation rate(SKGR)between legitimate ***,we propose an alternative method,i.e.,a power allocation,to improve the *** results show 72%higher SKGR in bits/sec by increasing power *** addition,the power transmission is based on two important parameters,i.e.,epsilon and power loss factor,as given in power transmission *** found out that a higher value of epsilon impacts power transmission and subsequently impacts the *** SKGR is approximately 40.7%greater at 250 from 50 mW at epsilon=*** value of SKGR is reduced to 18.5%at 250 mW when epsilonis ***,the transmission power is also measured against the different power loss factor values,i.e.,3.5,3,and 2.5,respectively,at epsilon=***,it is concluded that the value of epsilon and power loss factor impacts power transmission and,consequently,impacts the SKGR.

关键词： Secret key generation rate power allocation physical layer wireless communication

来源：评论

学校读者我要写书评

暂无评论

PCNET: PARALLELLY CONQUER THE LARGE VARIANCE OF PERSON RE-IDENTIFICATION

PCNET: PARALLELLY CONQUER THE LARGE VARIANCE OF PERSON RE-ID...

引用

28th IEEE International Conference on Image Processing, ICIP 2021

作者： Wang, Jianyuan You, Meiyue Leng, Biao Jiang, Ming Song, Guanglu School of Automation Science and Electrical Engineering Beihang University Beijing100191 China School of Information Science and Technology Beijing University of Chemical Technology Beijing100029 China School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9781665441155

Person re-identification has a wide range of applications, and many state-of-the-art methods are proposed to solve the problem under specific scenarios. However, it is still a challenging issue because of the large variance in practical applications, such as pose variations, misalignment, and image noises. In this paper, Parallelly Conquer Net (PCNet) is proposed to deal with large variance in a parallel manner. PCNet consists of three module: Pose Adaptation Module (PAM), Global Alignment Module (GAM), and Pixel-Wised Attention Module (PWAM). Each module is designed to deal with a sub-variance independently. Furthermore, the generated features are aggregated by parallel branches to utilize complementary information among them. Extensive experiments on three benchmarks (Market-1501, DukeMTMC-reID, and CUHK03) demonstrate the effectiveness of the method. The results show that PCNet can significantly improve the performance of person re-identification. © 2021 IEEE

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spectrum Access in Cognitive Radio Networks: A Game-Theoretic Approach 15

Dynamic Spectrum Access in Cognitive Radio Networks: A Game-...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Dhabliya, Dharmesh Vigenesh, M. Minhas, Deepak Shalini, M. Das, Sidhant Renukajyothi, S. Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore641021 India Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research for Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Sciences Department of Biotechnology and Genetics Karnataka Bangalore India

ISBN: (纸本)9798350370249

Cognitive radio networks (CRNs) are a promising technology which could offer better spectrum efficiency and utilization via permitting dynamic spectrum get right of entry to (DSA). Game idea has been an increasing number of hired as a tool for analyzing and addressing optimization problems in CRNs. This abstract discusses the utility of sport theory to the evaluation and optimization of DSA in CRNs. the main consciousness is to broaden a widespread recreation-theoretic approach for DSA that can model numerous styles of interactions among cognitive customers. Specifically, we speak 8 exceptional styles of games that may be used to model the DSA problem, including static, dynamic, and multi-attribute games. Moreover, we speak 3 critical DSA optimization issues: spectrum allocation, spectrum sharing, and energy manipulate. Sooner or later, we speak a few crucial challenges and possibilities for similarly research in this place. Using game principle for DSA in CRNs can assist to enhance the performance of CRNs in terms of throughput, fairness, energy efficiency, and security. © 2024 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Oral Squamous Cell Carcinoma Diagnosis Using Spotted Hyena Optimizer Combined with Transfer Learning Approaches 15th

Oral Squamous Cell Carcinoma Diagnosis Using Spotted Hyena O...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Balakrishnan, Roshni M. Bharanidharan, N. Chakravarthy, S. R. Sannasi Kumar, V. Vinoth Patil, Swetha Rajaguru, Harikumar Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidhyapeetham Bengaluru India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering PES University EC Campus Bengaluru India

ISBN: (纸本)9783031810794

Histopathological oral images are one of the popular methodologies to diagnose oral squamous cell carcinoma. computerized diagnostic systems need to be developed in order to process huge number of histopathological oral images for each subject and helping the clinician in classifying the oral images as either normal class or oral squamous cell carcinoma class. This research work uses deep transfer learning approaches namely MobileNetV3, InceptionV2, and EfficientNetB3 for extracting the features from histopathological oral images. Spotted Hyena Optimizer is used as feature transform for improving classification accuracy. Two dense layers are used for classifying the transformed features. 2784 & 3632 number of histopathological oral images are considered in this study under the two classes as normal and oral squamous cell carcinoma respectively. With the proposed spotted Hyena Optimizer, the maximum accuracy attained is 93% for the features extracted through InceptionV2 model. Relatively, the highest accuracy attained is 89% if the optimizer is not used for the features extracted through MobileNetV3 model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Investigating Vision Transformer Models for Low-Resolution Medical Image Recognition 18

Investigating Vision Transformer Models for Low-Resolution M...

引用

18th International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2021

作者： Adjei-Mensah, Isaac Zhang, Xiaoling Baffour, Adu Asare Agyemang, Isaac Osei Yussif, Sophyani Banaamwini Agbley, Bless Lord Y. Sey, Collins University of Electronic Science and Technology of China School of Information and Communication Engineering China University of Electronic Science and Technology of China School of Information and Software Engineering China University of Electronic Science and Technology of China School of Computer Science and Engineering China

ISBN: (纸本)9781665413640

Vision Transformers use self-attention techniques to learn long-range spatial relations to focus on the relevant parts of an image. They have achieved state-of-the-art results in many computer vision tasks. Recently, some methods have to leverage Vision Transformer-based models to tackle tasks in medical imaging. However, Vision Transformer emphasizes the low-resolution features due to the repetitive downsamplings, which result in a loss or lack of detailed localization information, making it highly unfit for low-level image recognition. In this paper, we investigate the performance of Vision Transformer on low-level medical images and contrast it with convolutional neural networks. The experimental results show that Convolutional Neural Network outperforms the Vision Transformer-based models on all four datasets. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Backstepping-Based Interception Control for an Underactuated ASV with Experimental Validation

Backstepping-Based Interception Control for an Underactuated...

引用

Chinese Automation Congress (CAC)

作者： Bin Lin Zhihuan Hu Kairong Duan Zhijian Sun Wei Xie Weidong Zhang Defeng Wu Shangkun Zhong Department of Automation Shanghai Jiao Tong University Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Department of Automation Shanghai Jiao Tong University Crossocean of Suzhou Technology Co. ITD Shanghai China Department of Automation School of Information and Communication Engineering Hainan University Shanghai Jiao Tong University Haikou China School of Marine Engineering Jimei University Xiamen China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This article puts forward an interception control system designed specifically for an Autonomous Surface Vehicle (ASV). The prime goal of this system is to capture a moving target whose speed may vary, even when there are unknown external disturbances such as waves, wind, and stream currents. By applying the sophisticated backstepping method, it can guarantee that the relative speed between the interceptor ASV and the target globally gets close to a neighborhood of the desired value. The effectiveness of this interception control approach has been thoroughly verified through simulations as well as practical experimental tests.

关键词： Analytical models Backstepping Automation Surface waves Control systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Martian Dust Storm Removal via Disentangled Representation Learning

引用

Research in Astronomy and Astrophysics 2022年第9期22卷 255-266页

作者： Dong Zhao Jia Li Hongyu Li Long Xu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBejing 100191China State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China

Mars exploration has become a hot spot in recent years and is still advancing rapidly. However, Mars has massive dust storms that may cover many areas of the planet and last for weeks or even months. The local/global dust storms are so influential that they can significantly reduce visibility, and thereby the images captured by the cameras on the Mars rover are degraded severely. This work presents an unsupervised Martian dust storm removal network via disentangled representation learning(DRL). The core idea of the DRL framework is to use the content encoder and dust storm encoder to disentangle the degraded images into content features(on domain-invariant space) and dust storm features(on domain-specific space). The dust storm features carry the full dust storm-relevant prior knowledge from the dust storm images. The “cleaned” content features can be effectively decoded to generate more natural, faithful, clear *** primary advantages of this framework are twofold. First, it is among the first to perform unsupervised training in Martian dust storm removal with a single image, avoiding the synthetic data requirements. Second, the model can implicitly learn the dust storm-relevant prior knowledge from the real-world dust storm data sets, avoiding the design of the complicated handcrafted priors. Extensive experiments demonstrate the DRL framework’s effectiveness and show the promising performance of our network for Martian dust storm removal.

关键词： planets and satellites:atmospheres planets and satellites:general planets and satellites:surfaces

来源：评论

学校读者我要写书评

暂无评论

TransferFuzz: Fuzzing with Historical Trace for Verifying Propagated Vulnerability Code

arXiv

引用

arXiv 2024年

作者： Li, Siyuan Li, Yuekang Chen, Zuxin Dong, Chaopeng Wang, Yongpan Li, Hong Chen, Yongle Zhu, Hongsong Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering The University of New South Wales Sydney Australia College of Computer Science and Technology Taiyuan University of Technology Shanxi China

Code reuse in software development frequently facilitates the spread of vulnerabilities, making the scope of affected software in CVE reports imprecise. Traditional methods primarily focus on identifying reused vulnerability code within target software, yet they cannot verify if these vulnerabilities can be triggered in new software contexts. This limitation often results in false positives. In this paper, we introduce TransferFuzz, a novel vulnerability verification framework, to verify whether vulnerabilities propagated through code reuse can be triggered in new software. Innovatively, we collected runtime information during the execution or fuzzing of the basic binary (the vulnerable binary detailed in CVE reports). This process allowed us to extract historical traces, which proved instrumental in guiding the fuzzing process for the target binary (the new binary that reused the vulnerable function). TransferFuzz introduces a unique Key Bytes Guided Mutation strategy and a Nested Simulated Annealing algorithm, which transfers these historical traces to implement trace-guided fuzzing on the target binary, facilitating the accurate and efficient verification of the propagated vulnerability. Our evaluation, conducted on widely recognized datasets, shows that TransferFuzz can quickly validate vulnerabilities previously unverifiable with existing techniques. Its verification speed is 2.5 to 26.2 times faster than existing methods. Moreover, TransferFuzz has proven its effectiveness by expanding the impacted software scope for 15 vulnerabilities listed in CVE reports, increasing the number of affected binaries from 15 to 53. The datasets and source code used in this article are available at https://***/Siyuan-Li201/TransferFuzz. Copyright © 2024, The Authors. All rights reserved.

关键词： computer software reusability

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：