检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qu, Qiang Shen, Yiran Chen, Xiaoming Chung, Yuk Ying Liu, Tongliang School of Computer Science The University of Sydney Australia School of Software Shandong University China School of Computer Science and Engineering Beijing Technology and Business University China

The bio-inspired event cameras or dynamic vision sensors are capable of asynchronously capturing per-pixel brightness changes (called event-streams) in high temporal resolution and high dynamic range. However, the non-structural spatial-temporal event-streams make it challenging for providing intuitive visualization with rich semantic information for human vision. It calls for events-to-video (E2V) solutions which take event-streams as input and generate high quality video frames for intuitive visualization. However, current solutions are predominantly data-driven without considering the prior knowledge of the underlying statistics relating event-streams and video frames. It highly relies on the non-linearity and generalization capability of the deep neural networks, thus, is struggling on reconstructing detailed textures when the scenes are complex. In this work, we propose E2HQV, a novel E2V paradigm designed to produce high-quality video frames from events. This approach leverages a model-aided deep learning framework, underpinned by a theory-inspired E2V model, which is meticulously derived from the fundamental imaging principles of event cameras. To deal with the issue of state-reset in the recurrent components of E2HQV, we also design a temporal shift embedding module to further improve the quality of the video frames. Comprehensive evaluations on the real world event camera datasets validate our approach, with E2HQV, notably outperforming state-of-the-art approaches, e.g., surpassing the second best by over 40% for some evaluation metrics. © 2024, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Federated Flowchart: Overview of State-of-the-Arts based on Federated Learning Process 13

Federated Flowchart: Overview of State-of-the-Arts based on ...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Oh, Junsuk Lee, Donghyun Ha, Taeyun Jeon, Yongin Noh, Woniong Cho, Sungrae School of Computer Science and Engineering Chung-Ang University Seoul Korea Republic of School of Software Hallym University Chuncheon Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

Federated learning centrally trains global statistical models by aggregating the local models trained on each device with localized data. Accordingly, federated learning protects the privacy of each device by eliminating the need to transmit distributed data generated in real-time on each device to a central data center. However, unlike other machine learning paradigms, this new paradigm raises new problems in large-scale and high-density networks composed of various devices, such as privacy protection due to the numerous devices, and distributed optimization due to the different resources of each device. In this paper, we describe the characteristics, challenges, and process of federated learning, and provide an overview of state-of-the-arts according to each phase of the process. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Difficulty-Aware Data Augmentor for Scene Text Recognition 48

Difficulty-Aware Data Augmentor for Scene Text Recognition

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Meng, Guanghao Dai, Tao Chen, Bin Li, Naiqi Jiang, Yong Xia, Shu-Tao Tsinghua University Tsinghua Shenzhen International Graduate School China Peng Cheng Laboratory Shenzhen China Shenzhen University College of Computer Science and Software Engineering China Harbin Institute of Technology Department of Computer Science and Technology Shenzhen China

ISBN: (纸本)9781728163277

Deep neural network (DNN) based scene text recognition (STR) methods usually require a large amount of annotated data for training, which is time-consuming and cost-expensive in practice. To address this issue, many data augmentation methods have been developed to train recognizers by improving the diversity of training samples. However, most existing methods neglect the difficulty inherent in samples, and easily suffer from the problem of over-diversity, i.e., the distribution of the augmented data significantly deviates from that of clean data. In this paper, we propose a novel difficulty-aware data augmentation framework for scene text recognition, which jointly considers the difficulty of samples and the strength of augmentations. Specifically, our framework first predicts the sample difficulty, followed by an adaptive data augmentation strategy. Furthermore, we build a more diverse set of augmentation methods for STR and integrate it into our augmentation framework. Extensive experiments on scene text recognition benchmarks show that our augmentation framework significantly improves the performance of recognizers. © 2023 IEEE.

关键词： data augmentation deep neural network difficulty-aware Scene text recognition

来源：评论

学校读者我要写书评

暂无评论

Correlation Fusion with Instance-level Auto-weighted for Multi-view Graph Clustering 25

Correlation Fusion with Instance-level Auto-weighted for Mul...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Chen, Xuan Chen, Zhikui Yao, Liang Ma, Shubin Li, Peng Yu, Shuo School of Software Dalian University of Technology Da'lian China School of Electrical Engineering Anhui Polytechnic University Wu'hu China School of Computer Science and Technology Dalian University of Technology Da'lian China

ISBN: (纸本)9798350330014

Multi-view graph clustering (MGC) has emerged as a hot research topic due to its effectiveness. Previous works mainly focus on the fusion of similarity graphs to exploit the complementary and consistent. However, these approaches suffer from three shortcomings: 1) The distance similarity estimate by the linear Euclidean metric may be incorrect in revealing the association relationship of heterogeneous multi-view samples. 2) Most of them often weight the whole view to balance the effect of different views, which ignores the importance of local samples. 3) They fail to preserve the inherent manifold structure between views via directly applying similarity matrix fusion to obtain a consistent graph. To fill these gaps, this paper proposed a novel framework called correlation fusion with instance-level auto-weighted for MGC (CFIMGC). In particular, the Spearman distance is leveraged to effectively characterize the versatile correlation matrix. The sample-level auto-weighted fusion mechanism is presented for flexible assigning weight values to different sample-wise relations in intra-view and inter-view, through which the complementary of numerous correlation matrices is appropri-ately explored to produce a consistent correlation matrix. What's more, a probability graph is adaptively learned based on the fusion correlation matrix for constructing a clustering-friendly similarity graph. Meanwhile, an alternating iteration algorithm is devised to address the non-convex joint optimization problem. Comprehensive experiment results on seven widely used but challenging multi-view datasets demonstrate that the proposed method yields superiority in clustering performance against six state-of-the-art counterparts. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning

引用

IEEE Access 2025年 13卷 108798-108814页

作者： Minghong Fan Jinghua Lan Yiyi Zhou Mengshuang Pan Junrong Li Daqiang Zhang School of Computer Engineering Jimei University Xiamen China Department of Computer Science and Engineering Shaoxing University Shaoxing China College of Letters and Science University of California at Berkeley Berkeley CA USA School of Data Science Lingnan University Tuen Mun Hong Kong School of Software Engineering Tongji University Shanghai China

software-defined networking (SDN)-assisted federated learning (FL) is an emerging network computing environment. It can not only shorten the training time of federated learning while maintaining high learning performance, but also enhance the security of the FL network. However, compared with traditional FL networks, SDN-assisted FL technology introduces new security threats. Distributed denial of service(DDoS) attacks are an important security threat for the SDN service in FL. In the SDN-assisted FL environment, the FL network requires the interaction of model parameters among multiple participants. During this process, DDoS attacks may target the SDN control plane, disrupt its normal operation, and thus affect the transmission of model parameters in FL. Hence, this paper proposes a novel approach to detecting and identifying DDoS attacks based on contrastive learning (CL), an adversarial learning framework based on two-layer deep neural networks. The framework features a two-layer classification structure. In the first layer, we integrate Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to identify DDoS attacks. In the second layer, we enhance the classifier structure by combining Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (BiGRU). This layer can be optimized based on the contrastive classification loss from the LSTM-SVM classifier in the first layer. We conducted experiments on a specific SDN dataset generated by the Mininet emulator. The results show that for the LSTM-SVM model, the detection accuracy reaches 99.75%, and the recall rate is 99.80%. For the CNN-BiGRU model, the detection accuracy rate is 99.36%, and the recall rate is 99.55%. Overall, the proposed CL model can effectively identify DDoS attack traffic in SDN-assisted FL environments, demonstrating high detection performance. However, the model may face challenges such as high computational resource requirements and insufficient adaptability to complex ne

关键词： Denial-of-service attack Servers Contrastive learning Federated learning Data models Accuracy Support vector machines Training Long short term memory computer crime

来源：评论

学校读者我要写书评

暂无评论

SWPFOPLD: A Profiling and Optimizing Loader for SW26010Pro Processors 8

SWPFOPLD: A Profiling and Optimizing Loader for SW26010Pro P...

引用

8th International Conference on computer and Communication Systems, ICCCS 2023

作者： Qian, Hong Wu, Wei Zhu, Qi Wang, Fei Zhao, Jinwei Zheng, Yan School of Computer Science and Technology University of Science and Technology of China Hefei China Jiangnan Institute of Computing Technology System Software Research Department Wuxi China Tsinghua University Department of Computer Science and Technology Beijing China National Research Center of Parallel Computer Engineering and Technology Beijing China

ISBN: (纸本)9781665456128

The Sunway family supercomputers have achieved a series of remarkable achievements. However, the toolchains provided by them are not perfect, which has brought great challenges to the development of high-performance application software. In this paper, a profiling and optimizing tool is proposed to assist people to analyze and optimize the performance of their programs. SWPFOPLD is independent of the application program and gathers the runtime performance data through the PMUs, an automatically hot functions rearrange optimization based on the performance data is furtherly accomplished. The evaluation shows that SWPFOPLD can be easily and effectively used to analyze and optimize the performance of the application programs. © 2023 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Cohesive Subgraph Awareness 24

Graph Contrastive Learning with Cohesive Subgraph Awareness

引用

33rd ACM Web Conference, WWW 2024

作者： Wu, Yucheng Wang, Leye Han, Xiao Ye, Han-Jia Key Lab of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai China National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University Nanjing China

ISBN: (纸本)9798400701719

Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses stochastic graph topology augmentation, such as uniform node dropping, to generate augmented graphs. However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process. We argue that incorporating an awareness of cohesive subgraphs during the graph augmentation and learning processes has the potential to enhance GCL performance. To this end, we propose a novel unified framework called CTAug, to seamlessly integrate cohesion awareness into various existing GCL mechanisms. In particular, CTAug comprises two specialized modules: topology augmentation enhancement and graph learning enhancement. The former module generates augmented graphs that carefully preserve cohesion properties, while the latter module bolsters the graph encoder's ability to discern subgraph patterns. Theoretical analysis shows that CTAug can strictly improve existing GCL mechanisms. Empirical experiments verify that CTAug can achieve state-of-the-art performance for graph representation learning, especially for graphs with high degrees. The code is available at https://***/10.5281/zenodo.10594093, or https://***/wuyucheng2002/CTAug. © 2024 ACM.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A-REA: Relation-Aware Graph Convolutional Network Entity Alignment Via a Differential Adjacency Matrix

A-REA: Relation-Aware Graph Convolutional Network Entity Ali...

引用

2023 Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2023

作者： Dang, Yuemei Qiu, Chen Gao, Feng Gu, Jinguang Zhang, Lihua Arman, Ghazaleh School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Software College East China Jiaotong University Jiangxi Nanchang China Urmia University of Technology Faculty of Information Technology and Computer Engineering Urmia Iran

ISBN: (纸本)9781665457033

Entity Alignment is the task of seeking entities with the same semantics from distinct knowledge graphs (KGs). Researchers have recently proposed Graph Convolutional Network (GCN) based approaches to achieve this task. Most existing GCN-based methods embed all the relations into an identical value, making the underlying loss on the diversity of the relationship. Relation semantics of entities and relation structure have benefitted the entity alignment task in the monolingual scenarios. This paper proposes a Relation-Aware Graph Convolutional Network with a Differential Adjacency Matrix (A-REA), which exploits the relation-specific semantics and structural information of entities in the KGs to promote the entity representations. The experiments on DBP-15K and DWY-100K datasets, including three cross-lingual subsets and two cross-knowledge graph sub-datasets, reveal that our approach leads to advance in entity alignment task in both the cross-lingual and cross-knowledge KGs. Discriminating the relation shows the effective signal for entity alignment, especially for the schema heterogeneity of different KGs. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SyntaxLineDP: a Line-level software Defect Prediction Model based on Extended Syntax Information 23

SyntaxLineDP: a Line-level Software Defect Prediction Model ...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Zhu, Jianzhong Huang, Yuan Chen, Xiangping Wang, Ruomei Zheng, Zibin Sun Yat-sen University School of Computer Science and Engineering Guangdong Guangzhou China Sun Yat-sen University School of Software Engineering Guangdong Zhuhai China Sun Yat-sen University School of Journalism and Communication Guangdong Guangzhou China

ISBN: (纸本)9798350319583

The existence of software defects greatly restricts the application of software and may bring great economic losses. Defect prediction techniques based on file level or module level can help code reviewers quickly locate defects and fix them. In recent years, researchers have used natural language techniques to explore the defectiveness of code lines by analyzing the semantic information of the code lines. However, the appearance of defects is often associated with the syntactic information of the code. To fully use the syntax information associated with code lines, we propose a code line-level representation considering the coverage of the syntax node. Specifically, we add the syntax node to its corresponding coverage lines. Combining with the BiLSTM model, we propose a new line-level defect prediction model, SyntaxLineDP, which shows good performance achieving 0.72 and 0.62 for AUC and Balanced Accuracy respectively. SyntaxLineDP outperforms the state-of-the-art model and the popular static tools (e.g., ErrorProne, PMD). Specifically, In the within-project evaluation, the SyntaxLineDP model outperforms the start-of-the-art model by 15% and 27% on the Recall@Top20% LOC metric and the Effort@Top20% Recall metric respectively. In the cross-project evaluation, the SyntaxLineDP outperforms the start-of-the-art model by 7% and 42% on the Recall@Top20% LOC metric and the Effort@Top20% Recall metric respectively. Through ablation experiments, we studied how the selection of extended syntax information contributes to the detection and found out some key features that are helpful for the defect prediction task: number of infix expressions of code line, number of blocks of code line, and number of method invocation of the code line. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Search Method of Technology Video based on Adversarial Learning and Feature Fusion 8

Cross-modal Search Method of Technology Video based on Adver...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Liu, Xiangbin Du, Junping Liang, Meiyu Li, Ang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing100876 China

ISBN: (纸本)9781665477352

Technology videos contain rich multi-modal information. In cross-modal information search, the data features of different modalities cannot be compared directly, so the semantic gap between different modalities is a key problem that needs to be solved. To address the above problems, this paper proposes a novel Feature Fusion based Adversarial Cross-modal Retrieval method (FFACR) to achieve text-to-video matching, ranking and searching. The proposed method uses the framework of adversarial learning to construct a video multimodal feature fusion network and a feature mapping network as generator, a modality discrimination network as discriminator. Generator and discriminator are trained alternately based on adversarial learning, so that the data obtained by the feature mapping network is semantically consistent with the original data and the modal features are eliminated. Experimental results demonstrate that the proposed method performs better in text-to-video search on the self-built datasets of technology videos. © 2022 IEEE.

关键词： Semantics

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：