检索结果-内蒙古大学图书馆

Euromicro conference on parallel, distributed and Network-Based processing

作者： Igor Kotenko Igor Saenko Oleg Lauta Nikita Vasiliev Vladimir Sadovnikov Laboratory of Computer Security Problems St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS) Saint-Petersburg Russia Department of Telecommunications and Information Security Admiral Makarov State University of Maritime and Inland Shipping Saint-Petersburg Russia

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

Adversarial attacks are now becoming quite a dangerous means of disrupting image processing systems that use machine learning methods for decision making. Therefore, developing effective countermeasures against adversarial attacks is becoming quite an important area of cybersecurity. The paper proposes a noise-based approach to countering adversarial attacks that is augmented with neural-cleanse and jpeg-compression technologies. The idea of the proposed approach is that adding noise distorts the effect of an adversarial attack, and neural cleaning and jpeg compression eliminate the consequences of such an effect. The paper examines the three most well-known types of adversarial attacks: Fast Gradient Sign Method, Zeroth Order Optimization and One Pixel Attack. These attacks manipulate input data, resulting in misclassification or incorrect predictions by exploiting high-frequency components that are undetectable to humans. The research was carried out on two datasets: MNIST-JPG and PC Parts images. Two types of noise were used: Gaussian and Poisson. During the experiments, optimal parameters for these types of noise were found, ensuring maximum accuracy of image recognition after exposure to adversarial attacks.

关键词： Resistance image recognition image coding image resolution Noise Transform coding Machine learning Distortion Optimization image classification

来源：评论

学校读者我要写书评

暂无评论

An Exhaustive Survey on the methods and Applications of Graph Neural Networks 8th

An Exhaustive Survey on the Methods and Applications of Grap...

引用

8th International conference on Information Science, Communication and Computing

作者： Fan, Dong Cheng, Jieren Tang, Xiangyan Lu, Kai Hainan Univ Sch Comp Sci & Technol Haikou 570228 Hainan Peoples R China Hainan Blockchain Technol Engn Res Ctr Haikou 570228 Hainan Peoples R China Sch Cyberspace Secur Sch Cryptol Haikou 570228 Hainan Peoples R China Hainan Vocat Coll Polit & Law Dept Publ Safety Technol Haikou 571100 Hainan Peoples R China

ISBN: (纸本)9789819617838;9789819617814;9789819617807

The widespread use of deep learning has achieved unprecedented success. Neural networks have achieved remarkable results in natural language processing, image recognition and other application fields. The key to the success of neural networks lies in its efficient processing of Euclidean space data, but the results obtained when traditional neural networks are used in non-Euclidean spaces are often not satisfactory to researchers. Graph neural network has been widely developed as a neural network that can be used in non-Euclidean space. This paper starts with the basic knowledge of graphs, introduces graph neural networks, and makes a new classification of them. Then it illustrates its application from 18 application areas. Finally, I put forward my own views on the future development and challenges of graph neural networks.

关键词： Graph Neural Networks Convolution Recurrent Graph Generation Euclidean non-Euclidean

来源：评论

学校读者我要写书评

暂无评论

Invisible Backdoor Attack with image Contours Triggers 24th

Invisible Backdoor Attack with Image Contours Triggers

引用

24th International conference on Algorithms and Architectures for parallel processing, ICA3PP 2024

作者： Hou, Yangzhi Yang, Ying Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9789819615445

In recent years, backdoor attack techniques on neural networks have been widely studied and researched. In this attack mode, the model implanted with a backdoor behaves normally when processing normal inputs, but once it encounters a special trigger designed by the attacker, its prediction results will be maliciously manipulated. Different backdoor attack strategies have been proposed to improve the stealth and robustness of the triggers. However, most of the existing backdoor attack strategies use fixed triggering patterns or input-independent triggering patterns, and thus are easily detected and blocked by existing defense systems. To address these limitations, we propose a backdoor attack method based on image contours. Specifically, we first use image contours as the target region for backdoor injection and fill them with specific color information to generate trigger patterns. Then, using our designed Generative Network (GN) and the Auxiliary Extraction Network (AE), the trigger patterns are covertly embedded into the images to be contaminated to generate a poisoned dataset, which contaminates the training model for the purpose of malicious attacks. Compared with traditional methods, our trigger patterns are more natural and harder to detect. Experimental results show that our proposed attack method achieves excellent performance in terms of both stealth and robustness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A synchronization-free incomplete LU factorization for GPUs with level-set analysis

A synchronization-free incomplete LU factorization for GPUs ...

引用

Euromicro conference on parallel, distributed and Network-Based processing

作者： Manuel Freire Ernesto Dufrechou Pablo Ezzatti Instituto de Computación Facultad de Ingeniería - UDELAR Montevideo Uruguay

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

Incomplete factorization methods are powerful algebraic preconditioners widely used to accelerate the convergence of linear solvers. The parallelization of ILU methods has been extensively studied, particularly for GPUs, which are ubiquitous parallel computing devices. In recent years, synchronization-free methods have become the mainstream approach for solving sparse triangular linear *** the sparse triangular solver and ILU factorization are closely related, the application of synchronization-free strategies to ILU factorization has not been explored in the literature to the same extent as the triangular solver. In this work, we present synchronization-free implementations of the ILU-0 preconditioner on GPUs. Specifically, we propose three implementations that vary in how row updates are handled after each coefficient elimination, as well as an additional approach that leverages a prior level-set analysis to optimize the execution schedule.

关键词： Linear systems Schedules parallel processing Synchronization Convergence

来源：评论

学校读者我要写书评

暂无评论

AcDWS:Actor Based distributed Web Scraping

AcDWS:Actor Based Distributed Web Scraping

引用

International CSI Computer conference, CSICC

作者： Fatemeh Aliasgharzadeh Reza Azmi Department of Computer Faculty Engineering Alzahra University Tehran Iran

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

This paper examines a new system for web data extraction that utilizes an AcDWS approach. The main goal of this system is to collect information related to user-requested products quickly and at scale. In this system, communication between actors is managed, and the messages exchanged between them are controlled to ensure proper operation. Solr is used for data storage and full-text search, Akka for parallel processing, and Akka Cluster for distributed processing. The results show that this method operates 75% faster than conventional methods using Python and 36.7% faster than data extraction implemented in Java sequentially.

关键词： Java distributed processing Scalability Memory distributed databases Computer architecture parallel processing Service-oriented architecture Data mining Information analysis

来源：评论

学校读者我要写书评

暂无评论

InVideo Search: Scene Description Clustering and Integrating image and Audio Captioning for Enhanced Video Search 21st

InVideo Search: Scene Description Clustering and Integrating...

引用

21st International conference on distributed Computing and Intelligent Technology

作者： Khan, Almira Asif Muhammed Shaji, Asher Mathews Sujith, Devika Nath, Aneesh G. Udmale, Sandeep S. TKM Coll Engn Dept Comp Sci & Engn Kollam Kerala India Veermata Jijabai Technol Inst VJTI Dept Comp Engn & Informat Technol Mumbai 400019 Maharashtra India

ISBN: (纸本)9783031814037;9783031814044

In the digital era, the vast amount of long videos highlights the need for an advanced system to efficiently find specific segments based on text descriptions. The proposed solution aims to develop a video content retrieval system by utilizing established tools in video analysis, image/video captioning, and information retrieval. The work is organized into three modules: Keyframe extraction, Captioning, and Query-based searching. Our primary focus is on effectively identifying key elements within these videos, achieving a semantic understanding of these videos in the form of captions, and establishing precise matches of user queries. In short, users input descriptive text prompts, and the application, equipped with pre-trained models, promptly and accurately identifies and retrieves the video segments. This application carries significant potential across various domains, from enabling efficient scene location in movies to helping extract knowledge from educational lectures. Furthermore, this research fundamentally departs from conventional video search methods that heavily rely on metadata or manually assigned tags, which often fall short of capturing the nuances of video content. This work also focuses on a multimodal captioning strategy to integrate more semantic content. Clustering of captions was also incorporated to improve search performance in the case of long videos. This approach allows us to deliver a robust and efficient solution, taking advantage of the extensive knowledge and research underlying these established technologies. Beyond the immediate applications, this research has broader applications in fields like natural language understanding, multimedia analysis, and information retrieval.

关键词： Clustering Keyframe extraction Natural language processing Video content retrieval system

来源：评论

学校读者我要写书评

暂无评论

A small-sample fault diagnosis approach for RV reducer with RP-SST parallel CNN-SVM model 5

A small-sample fault diagnosis approach for RV reducer with ...

引用

5th International conference on Mechanical Engineering and Materials, ICMEM 2024

作者： Pan, Jiahao Liu, Chuanmeng Jin, Nan Peng, Yulong Qiu, Guangqi School of Mechanical and Electrical Engineering Jiangxi University of Science and Technology 1958 Hakka Avenue Jiangxi Ganzhou China

ISBN: (数字)9781510688971

ISBN: (纸本)9781510688964

For addressing the problem of low accuracy in the available diagnostic methods due to the insufficient fault-sample, this article proposes a small-sample fault diagnosis method with Recurrence plot (RP), Synchrosqueezed transform (SST) and parallel convolutional neural network (CNN) and support vector machine (SVM). This method first utilizes RP and SST techniques to extract the multimodal features into image processing. Then, the parallel CNN is used for multimodal feature fusion, enabling it to utilize more fault information within a limited number of samples. Finally, SVM is used for fault classification. The fault experiments for RV reducer were performed to verify the effectiveness of the proposed fault diagnosis method. The complementarity of RP-SST in multimodal feature extraction was verified for solving the problem of insufficient feature extraction due to sample size limitations effectively. Further, the SOTA fault diagnosis model showed that the proposed method achieved a fault diagnosis accuracy of 96.26% in small sample situations, significantly better than CNN-BIGRU, CNN-LSTM, and Resnet model. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Frequency Decoupled Domain-Irrelevant Feature Learning for Pan-Sharpening

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1237-1250页

作者： Zhang, Jie Cao, Ke Yan, Keyu Lin, Yunlong He, Xuanhua Wang, Yingying Li, Rui Xie, Chengjun Zhang, Jun Zhou, Man Chinese Acad Sci Inst Intelligent Machines Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Grad Sch Sci Isl Branch Hefei 230026 Peoples R China Chinese Acad Sci Inst Intelligent Machines Hefei Inst Phys Sci Hefei 230031 Peoples R China Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Univ Key Lab Multimedia Trusted Percept & Efficient Com Minist Educ China Xiamen 361005 Peoples R China Chinese Acad Sci High Magnet Field Lab Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230026 Peoples R China

Pan-sharpening aims to generate high-detail multi-spectral images (HRMS) through the fusion of panchromatic (PAN) and multi-spectral (MS) images. However, existing pan-sharpening methods often suffer from significant performance degradation when dealing with out-of-distribution data, as they assume the training and test datasets are independent and identically distributed. To overcome this challenge, we propose a novel frequency domain-irrelevant feature learning framework that exhibits exceptional generalization capabilities. Our approach involves parallel extraction and processing of domain-irrelevant information from the amplitude and phase components of the input images. Specifically, we design a frequency information separation module to extract the amplitude and phase components of the paired images. The learnable high-pass filter is then employed to eliminate domain-specific information from the amplitude spectrums. After that, we devised two specialized sub-networks (AFL-Net and PFL-Net) to perform targeted learning of the frequency domain-irrelevant information. This allows our method to effectively capture the complementary domain-irrelevant information contained in the amplitude and phase spectra of the images. Finally, the information fusion and restoration module dynamically adjusts the feature channel weights, enabling the network to output high-quality HRMS images. Through this frequency domain-irrelevant feature learning framework, our method balances generalization capability and network performance on the distribution of training dataset. Extensive experiments conducted on various satellite datasets demonstrate the effectiveness of our method for generalized pan-sharpening. Our proposed network outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality, showcasing its superior ability to handle diverse, out-of-distribution data.

关键词： Representation learning Frequency-domain analysis Feature extraction Data mining Training Spatial resolution Circuits and systems image restoration Fourier transforms Distortion Frequency domain-irrelevant pan-sharpening learnable filter amplitude spectrums

来源：评论

学校读者我要写书评

暂无评论

Frequency-Domain Guided Multiple parallel Kernels Network for Low-Light Remote Sensing image Enhancement

Frequency-Domain Guided Multiple Parallel Kernels Network fo...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jingxuan Zhou Hao Li Jinlong Wang Xiongxin Tang Fanjiang Xu Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Due to dark environments, optical aberrations, etc, the remote sensing images are often submerged under low contrast degradation, which greatly hinders their practical applications for agricultural management and other related tasks. The surface features of remote sensing images are often continuously distributed in space, thus, the sizes of the network’s receptive fields and its ability to learn long-range dependencies are crucial for restoring low-light remote sensing images. Existing methods based on CNN provide limited receptive fields, while Transformer-based methods are constrained by their quadratic computational complexity. To cope with these issues, we propose a novel low-light remote sensing image enhancement network that combines multi-scale receptive fields with frequency-domain attention. Specifically, this network employs multiple parallel kernels of varying sizes to learn multi-scale local features in the spatial domain and complements frequency-domain information to learn global long-range correlations, which achieves local-global feature extraction and further facilitates subsequent degraded images enhancement. We have conducted extensive experiments to demonstrate that our network outperforms existing methods quantitatively and achieves exceptional visual performance, which fully highlights the effectiveness and superiority of our method in enhancing low-light remote sensing images.

关键词： Visualization Frequency-domain analysis Transforms Speech enhancement Feature extraction Transformers image restoration Kernel Remote sensing image enhancement

来源：评论

学校读者我要写书评

暂无评论

Residual Hybrid Attention Enhanced Video Super-Resolution with Cross Convolution 7th

Residual Hybrid Attention Enhanced Video Super-Resolution wi...

引用

7th Chinese conference on Pattern Recognition and Computer Vision

作者： Yuan, Shiqian Li, Boyue Zhao, Xin Lan, Rushi Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Guilin Univ Elect Technol Int Joint Res Lab Spatiotemporal Informat & Intel Guilin 541004 Peoples R China

ISBN: (纸本)9789819785070;9789819785087

In video super-resolution reconstruction, traditional methods often fall short in capturing details, particularly in edges and occluded areas, which affects the realism and clarity of the images. To address this issue, we propose a novel model-the Residual Hybrid Attention-Enhanced Video Super-Resolution Model, augmented by Cross Convolution techniques, denoted as RCVSR. The model ingeniously integrates a residual hybrid attention mechanism, refining the learning of global and local features through parallel channel attention and self-attention mechanisms. Simultaneously, our model introduces overlapping cross-attention blocks to enhance dynamic interactions between frames, thereby boosting the model's performance. Furthermore, the design of the cross-convolution blocks allows for parallel processing of vertical and horizontal gradient information in images, effectively extracting edge details. In multiple benchmark tests, the RCVSR model demonstrated its excellent reconstruction effects and outstanding performance.

关键词： Video super-resolution Hybrid attention Cross convolution

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：