检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Yan Zhong Xingyu Wu Li Zhang Chenxi Yang Tingting Jiang School of Mathematical Sciences and National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China Hefei Institute of Physical Science Chinese Academy of Sciences University of Science and Technology of China Hefei China National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science and 5National Biomedical Imaging Center Peking University Beijing China

Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks based Muti-Label Deep Cross-Modal Hashing 13

Graph Convolutional Networks based Muti-Label Deep Cross-Mod...

引用

13th International Conference on Information Science and Technology, ICIST 2023

作者： Peng, Yi Zhang, Nian Jiang, Xin Xiong, Jiang School of Electronic and Information Engineering Chongqing Three Gorges University Chongqing40044 China Department of Electrical and Computer Engineering University of the District of Columbia WashingtonDC20008 United States Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Chongqing40044 China College of Mathematics and Statistics Chongqing Three Gorges University Chongqing40044 China

ISBN: (纸本)9798350313925

Recently, multi-label deep cross-modal hashing (MDCH), which incorporates deep neural networks, hashing and multi-label learning for cross-modal retrieval tasks, has achieved excellent cross-modal retrieval results and thus became a highly popular area of research. Nevertheless, many existing MDCH methods concentrate on extracting information from multi-modal data, while neglecting the abundant semantic information in multiple labels. Few MDCH methods incorporate multi-label information, but they often treat labels as independent entities, ignoring the relationships between categories, which hinders the establishment of semantic connections among multi-modal data. In order to tackle the aforementioned challenges, we propose a graph convolutional networks based multi-label deep cross-modal hashing method (GMCH) in this paper. GMCH leverages two deep neural networks to generate hash representations from the original image-text pairs, during this process, a graph convolutional network is introduced to capture the category correlations of multi-labels and supervise the training of hash mapping. Experimental results on two commonly employed datasets validate the efficacy of the proposed GMCH method. You can find the code for our proposed GCMH at https://***/licher12/***. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Sparse Signal Recovery with Dirichlet Process Priors Based on Expectation Propagation Technique 7

Multi-Task Sparse Signal Recovery with Dirichlet Process Pri...

引用

7th International Conference on Signal and Image processing, ICSIP 2022

作者： Fu, Yin Wu, Qisong Zhang, Yimin D. Amin, Moeness G. Southeast University Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Nanjing210096 China Temple University Department of Electrical and Computer Engineering PhiladelphiaPA19122 United States Villanova University Center for Advanced Communications VillanovaPA19085 United States

ISBN: (数字)9781665495639

ISBN: (纸本)9781665495639

Exploiting the shared information among tasks to significantly improve the sparse reconstruction performance lays the essence of multi-task compressive sensing. In this paper, a novel generative model of multi-task compressive sensing with Dirichlet process (DP) priors is proposed and the sharing mechanisms among tasks are revealed, yielding a principled means of inferring the clusters as well as performing compressive sensing inversion simultaneously. The spike-and-slab priors are first used to model the group sparsity among tasks within the identical cluster, and the DP priors are then introduced to automatically perform clustering for the tasks. The expectation propagation method is finally carried out to take the inference for posterior distribution approximation. The superiority of the proposed method over state-of-the-art algorithms is demonstrated by using experimental results on both numerical data and real data sets. © 2022 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition

arXiv

引用

arXiv 2024年

作者： Chen, Lan Li, Dong Wang, Xiao Shao, Pengpeng Zhang, Wei Wang, Yaowei Tian, Yonghong Tang, Jin The School of Electronic and Information Engineering Anhui University Hefei230601 China The School of Computer Science and Technology Anhui University Hefei230601 China The Department of Automation Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen China Shenzhen China Peng Cheng Laboratory China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

Existing event stream-based pattern recognition models usually represent the event stream as the point cloud, voxel, image, etc., and design various deep neural networks to learn their features. Although considerable results can be achieved in simple cases, however, the model performance may be limited by monotonous modality expressions, sub-optimal fusion, and readout mechanisms. In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. The spatial and three-dimensional stereo information can be learned separately by utilizing Transformer and Graph Neural Network (GNN). We believe the features of each representation still contain both efficient and redundant features and a suboptimal solution may be obtained if we directly fuse them without differentiation. Thus, we divide each feature into three levels and retain high-quality features, blend medium-quality features, and exchange low-quality features. The enhanced dual features will be fed into the fusion Transformer together with bottleneck features. In addition, we introduce a novel hybrid interaction readout mechanism to enhance the diversity of features as final representations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on multiple widely used event stream-based classification datasets. Specifically, we achieve new state-of-the-art performance on the Bullying10k dataset, i.e., 90.51%, which exceeds the second place by +2.21%. The source code of this paper has been released on https://***/Event-AHU/EFV_event_classification/tree/ EFVpp. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Weakly Secure Summation with Colluding Users

引用

IEEE Transactions on Information Theory 2025年

作者： Li, Zhou Zhao, Yizhou Sun, Hua Electronics and Information at Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Nanning530004 China Southwest University College of Electronic and Information Engineering Chongqing400715 China University of North Texas Department of Electrical Engineering DentonTX76203 United States

In secure summation, K users, each holds an input, wish to compute the sum of the inputs at a server without revealing any information about all the inputs even if the server may collude with an arbitrary subset of users. In this work, we relax the security and colluding constraints, where the set of inputs whose information is prohibited from leakage is from a predetermined collection of sets (e.g., any set of up to S inputs) and the set of colluding users is from another predetermined collection of sets (e.g., any set of up to T users). For arbitrary collection of security input sets and colluding user sets, we characterize the optimal randomness assumption, i.e., the minimum number of key bits that need to be held by the users, per input bit, for weakly secure summation to be feasible, which generally involves solving a linear program. © 1963-2012 IEEE.

关键词： Capacity Secure Summation Weak Security

来源：评论

学校读者我要写书评

暂无评论

GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph

arXiv

引用

arXiv 2024年

作者： Liu, Shaonan Chen, Wenting Liu, Jie Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China Department of Electrical Engineering City University of Hong Kong Hong Kong AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Gaze estimation is pivotal in human scene comprehension tasks, particularly in medical diagnostic analysis. Eye-tracking technology facilitates the recording of physicians’ ocular movements during image interpretation, thereby elucidating their visual attention patterns and information-processing strategies. In this paper, we initially define the context-aware gaze estimation problem in medical radiology report settings. To understand the attention allocation and cognitive behavior of radiologists during the medical image interpretation process, we propose a context-aware Gaze EstiMation (GEM) network that utilizes eye gaze data collected from radiologists to simulate their visual search behavior patterns throughout the image interpretation process. It consists of a context-awareness module, visual behavior graph construction, and visual behavior matching. Within the context-awareness module, we achieve intricate multimodal registration by establishing connections between medical reports and images. Subsequently, for a more accurate simulation of genuine visual search behavior patterns, we introduce a visual behavior graph structure, capturing such behavior through high-order relationships (edges) between gaze points (nodes). To maintain the authenticity of visual behavior, we devise a visual behavior-matching approach, adjusting the high-order relationships between them by matching the graph constructed from real and estimated gaze points. Extensive experiments on four publicly available datasets demonstrate the superiority of GEM over existing methods and its strong generalizability, which also provides a new direction for the effective utilization of diverse modalities in medical image interpretation and enhances the interpretability of models in the field of medical imaging. https://***/Tiger-SN/GEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

A robust incomplete large-scale group decision-making model for metaverse metro operations and maintenance

引用

Applied Soft Computing 2024年 156卷

作者： Bai, Wenhui Zhang, Chao Zhai, Yanhui Sangaiah, Arun Kumar School of Computer and Information Technology Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

The metaverse, constructed through digital technology, serves as a virtual realm intertwining with reality. Within this context, the challenge of evaluating data from diverse sources arises, and the application of large-scale group decision-making (LSGDM) methods emerges as a viable solution. Handling incomplete information and reducing dimensionality for large-scale decision-makers (DMs) is crucial in addressing complex decision-making problems. Moreover, addressing missing data is a fundamental and pivotal concern in tackling real-world decision challenges, given the ubiquitous presence of information gaps that cannot be straightforwardly integrated into decision models. Besides, the intricacies of LSGDM amplify this challenge by introducing a wealth of DMs, thereby augmenting the complexity and diversity of decision-related information. This paper proposes an approach to supplement missing data by double-dimensions. This paper explores various facets of similarity relationships within the data to enhance data completeness. Additionally, this paper categorizes DMs into clusters based on their relevance and establishes a two-stage consensus-reaching process (CRP) that takes into account both group sizes and individual consensus contributions. These CRPs play a crucial role in enhancing the overall consistency and consensus within the decision group. Subsequently, this paper applies a robust decision-making method rooted in MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the complete MULTIplicative form) to rank decision objects. Finally, this paper employs this proposed methodology in a practical case study that involves evaluating the operational status of a metaverse's urban construction metro system. Following these considerations, a comprehensive stability analysis of relevant parameters is conducted to guarantee the robustness and reliability of the decision-making process. © 2024 Elsevier B.V.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Automated Controller Placement for Software-Defined Networks to Resist DDoS Attacks

引用

computers, Materials & Continua 2021年第9期68卷 3147-3165页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Lee Ching Kwang Rizaludin Kaspin Bhawani Shankar Chowdhry Rajkumar Buyya Satya Prasad Majumder Manoj Gupta Shuaib Memon Faculty of Computing&Informatics Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation CentreCyberjaya63000SelangorMalaysia National Center of Robotics and Automation Mehran University of Engineering&TechnologyJamshoroPakistan Department of Computer Science and Engineering Hanyang UniversitySeoul04763South Korea School of Electrical and Electronic Engineering Nanyang Technological University639798Singapore Cloud Computing and Distributed Systems Laboratory The University of MelbourneMelbourneVIC 3053Australia Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology(BUET)Dhaka1205Bangladesh Department of Electronics and Communication Engineering JECRC UniversityVidhaniJaipur303905India Auckland Institute of Studies Mt AlbertAucklandNew Zealand

In software-defined networks(SDNs),controller placement is a critical factor in the design and planning for the future Internet of Things(IoT),telecommunication,and satellite communication *** research has concentrated largely on factors such as reliability,latency,controller capacity,propagation delay,and energy ***,SDNs are vulnerable to distributed denial of service(DDoS)attacks that interfere with legitimate use of the *** ever-increasing frequency of DDoS attacks has made it necessary to consider them in network design,especially in critical applications such as military,health care,and financial services networks requiring high *** propose a mathematical model for planning the deployment of SDN smart backup controllers(SBCs)to preserve service in the presence of DDoS *** a number of input parameters,our model has two distinct ***,it determines the optimal number of primary controllers to place at specific locations or nodes under normal operating ***,it recommends an optimal number of smart backup controllers for use with different levels of DDoS *** goal of the model is to improve resistance to DDoS attacks while optimizing the overall cost based on the *** simulated results demonstrate that the model is useful in planning for SDN reliability in the presence of DDoS attacks while managing the overall cost.

关键词： SDN automated controller placement SBC ILP DDoS attack

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable intelligent surfaces for wireless communications:Overview of hardware designs,channel models,and estimation techniques

引用

Intelligent and Converged Networks 2022年第1期3卷 1-32页

作者： Mengnan Jian George C.Alexandropoulos Ertugrul Basar Chongwen Huang Ruiqi Liu Yuanwei Liu Chau Yuen the Wireless Research Institute ZTE CorporationBeijing 100029China the State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518055China Department of Informatics and Telecommunications National and Kapodistrian University of AthensAthens 15784Greece Communications Research and Innovation Laboratory(CoreLab) Department of Electrical and Electronics EngineeringKoçUniversityIstanbul 34450Turkey College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027China School of Electronic Engineering and Computer Science Queen Mary University of LondonLondonE14NSUK. the Engineering Product Development(EPD)Pillar Singapore University of Technology and DesignSingapore 487372Singapore

The demanding objectives for the future sixth generation(6G)of wireless communication networks have spurred recent research efforts on novel materials and radio-frequency front-end architectures for wireless connectivity,as well as revolutionary communication and computing *** the pioneering candidate technologies for 6G belong the reconfigurable intelligent surfaces(RISs),which are artificial planar structures with integrated electronic circuits that can be programmed to manipulate the incoming electromagnetic field in a wide variety of *** RISs in wireless networks have been recently advocated as a revolutionary means to transform any wireless signal propagation environment to a dynamically programmable one,intended for various networking objectives,such as coverage extension and capacity boosting,spatiotemporal focusing with benefits in energy efficiency and secrecy,and low electromagnetic field *** by the recent increasing interests in the field of RISs and the consequent pioneering concept of the RIS-enabled smart wireless environments,in this paper,we overview and taxonomize the latest advances in RIS hardware architectures as well as the most recent developments in the modeling of RIS unit elements and RIS-empowered wireless signal *** also present a thorough overview of the channel estimation approaches for RIS-empowered communications systems,which constitute a prerequisite step for the optimized incorporation of RISs in future wireless ***,we discuss the relevance of the RIS technology in the latest wireless communication standards,and highlight the current and future standardization activities for the RIS technology and the consequent RIS-empowered wireless networking approaches.

关键词： reconfigurable intelligent surfaces beyond 5G 6G channel modeling hardware architecture channel estimation smart wireless environment standardization

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：