检索结果-内蒙古大学图书馆

4th International Conference on Consumer Electronics and computer Engineering, ICCECE 2024

作者： Liu, Lu Jiang, Min Xu, Lifa School of Computer Science and Technology Wuhan University of Science and Technology Hubei WuHan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China

ISBN: (纸本)9798350384062

Texture defect detection has wide applications in both textiles and industry, where traditional defect detection methods focus on costly manual labeling and defect samples are complex to collect in real-world industrial scenarios. Furthermore, labeling errors are common in datasets from industrial scenarios, and the problem still needs to be explored. Therefore, we propose a novel texture defect detection method. It has two stages;the defective samples are synthesized in the first stage. In the second stage, we represent normal samples using a self-supervised learning method. Then, we construct a single classifier based on this learned representation. Subsequently, the model is trained to distinguish between normal and defective samples within the embedding space. To increase the robustness of our method, we adopt a novel strategy to construct defective samples and compute the feature similarity through a similarity-weighted aggregation method to achieve defect detection, which is more robust to noise. Experimental results on the DAGM2007 dataset show that our method performs comparably to the leading texture defect detection methods without label noise. In contrast, in the presence of noise, our method can effectively minimize the impact of noise on model performance. © 2024 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Towards Practical Facial Video-based Remote Heart Rate Estimation via Cross Domain rPPG Adaptation 23

Towards Practical Facial Video-based Remote Heart Rate Estim...

引用

Proceedings of the 2023 10th International Conference on Biomedical and Bioinformatics Engineering

作者： Ze Yang Haofei Wang Feng Lu Qinping Zhao the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China Peng Cheng Laboratory China the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China and Peng Cheng Laboratory China

ISBN: (纸本)9798400708343

Remote photoplethysmography (rPPG) is a non-contact technology that can estimate heart rate using facial video and holds significant potential for health monitoring. Despite the latest deep learning-based rPPG approaches can predict high-quality rPPG signal under similar scenarios, these methods often suffer from degraded performance when encountering variations in subjects, environments, or illumination conditions in target domains. To address this challenge, we propose an uncertainty-guided self-training approach that leverages model uncertainty and periodic priors to enhance generalization across different domains without requiring labels in the target domain. We iteratively update the model using pseudo-labels generated from its own predictions on unlabelled data in the target domain, with varying confidence levels informed by the model’s uncertainty estimation. To achieve this, we modify a standard Convolutional Neural Network (CNN) into a Bayesian Neural Network (BNN) for uncertainty estimation, which guides the assignment of pseudo-labels with varying confidence levels. By employing the adversarially learned periodic priors of rPPG signals shared across domains as regularization terms, we further stabilize the model adaptation process. We evaluate the proposed method on two public datasets (PURE and UBFC-rPPG) across five cross-domain tasks. Experimental results demonstrate improved performance over the baselines, with gains ranging from 60.5% to 97.2%, outperforming existing methods in generalization performance for rPPG-based heart rate measurement.

关键词： heart rate estimation remote photoplethysmography unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

GraphFed: A Personalized Subgraph Federated Learning Framework for Non-IID Graphs 20

GraphFed: A Personalized Subgraph Federated Learning Framewo...

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart systems, MASS 2023

作者： Deng, Pan Liu, Xuefeng Niu, Jianwei Hu, Chunming Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798350324334

Recently, federated graph learning has attracted significant attention, as subgraphs of a global graph may often distribute across different institutions and are subject to privacy restrictions. However, inevitable data heterogeneity among sub-graphs can lead to poor performance of Graph Neural Networks (GNNs) trained by vanilla federated learning algorithm, which has been neglected before. To address this problem we look at subgraphs and find that there are usually overlapping nodes among them. Inspired by the common overlapping nodes among subgraphs, we propose GraphFed, a subgraph federated learning framework which solve the challenge in terms of both data augmentation and personalized federated learning. GraphFed uses common overlapping nodes among subgraphs to locate lost node information and applies data augmentation by retrieving lost nodes and forming common node sets that mitigates data distribution difference. Furthermore, GraphFed treats the overlapping nodes as bridges to calculate the distance among different subgraphs, which implies the similarity of the graph data distribution. Then, we use the distance to perform personalized federated learning. Empirical results and analysis on three real-world graph datasets with graph federated learning settings demonstrate the effectiveness of our proposed framework. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Super-resolution of Solar Magnetograms Using Deep Learning

引用

Research in Astronomy and Astrophysics 2022年第8期22卷 218-229页

作者： Fengping Dou Long Xu Zhixiang Ren Dong Zhao Xinze Zhang State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng National Laboratory Shenzhen 518000China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Currently,data-driven models of solar activity forecast are investigated extensively by using machine *** model training,it is highly demanded to establish a large database which may contain observations coming from different instruments with different spatio-temporal *** this paper,we employ deep learning models for super-resolution(SR)of magnetogram of Michelson Doppler Imager(MDI)in order to achieve the same spatial resolution of Helioseismic and Magnetic Imager(HMI).First,a generative adversarial network(GAN)is designed to transfer characteristics of MDI onto downscaled HMI,getting low-resolution HMI magnetogram in the same domain as ***,with the paired low-resolution and high-resolution HMI magnetograms,another GAN is trained in a supervised learning way,which consists of two streams,one is for generating high-fidelity image content,the other is explicitly optimized for generating elaborate image ***,these two streams work together to guarantee both high-fidelity and photorealistic super-resolved *** results demonstrate that the proposed method can generate super-resolved magnetograms with perceptual-pleasant visual ***,the best PSNR,LPIPS,RMSE,comparable SSIM and CC are obtained by the proposed *** source code and data set can be accessed via https://***/filterbank/SPSR.

关键词： techniques:image processing Sun:magnetic fields Sun:atmosphere

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Verifiable Secure Aggregation Protocol Under Federated Learning 1st

Verifiable Secure Aggregation Protocol Under Federated Learn...

引用

1st International Conference on Artificial Intelligence Security and Privacy, AIS and P 2023

作者： Xu, Peiming Zheng, Meiling Xu, Lingling Guangdong Provincial Key Laboratory of Power System Network Security Electric Power Research Institute CSG Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9789819997848

Federated learning is a new machine learning paradigm used for collaborative training models among multiple devices. In federated learning, multiple clients participate in model training locally and use decentralized learning methods to ensure the privacy of client data. However, although federated learning protects the privacy of client data, the update gradients uploaded by clients may still contain sensitive information. To solve this problem, this paper proposes a secure aggregation protocol which can verify the aggregation results under federated learning and protect gradient privacy. The core idea of this aggregation protocol is to use encryption technology to achieve secure computation between clients, ensuring the privacy of gradients during the aggregation process. At the same time, bilinear pairing technology is used to achieve the verifiability of aggregation results, ensuring the correctness and usability of the model after aggregation. In order to evaluate the security of the protocol, this paper conducts a detailed security analysis. The results show that this protocol has higher security properties compared to the existing related protocols. In addition, the computation and communication costs of the protocol are analyzed, which show that the protocol has good credibility and applicability in practical federated learning scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios Engineering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

来源：评论

学校读者我要写书评

暂无评论

Variable-order fractional derivative rutting depth prediction of asphalt pavement based on the RIOHTrack full-scale track

引用

Science China(Information Sciences) 2023年第5期66卷 196-214页

作者： Yu WANG Jiaojiao YAN Wei HUANG Leszek RUTKOWSKI Jinde CAO School of Mathematics Southeast University Jiangsu Provincial Key Laboratory of Networked Collective Intelligence Southeast University Intelligent Transportation System Research Center Southeast University Systems Research Institute of the Polish Academy of Sciences Institute of Computer Science AGH University of Science and Technology Information Technology Institute University of Social Sciences Yonsei Frontier Lab Yonsei University

Rutting deformation is typical damage to asphalt pavement and can be quantitatively described as the time-varying mechanical deformation feature of the asphalt mixture during the creep process. First,a nonlinear viscoelastic creep model is established based on the Caputo variable-order fractional *** fractional order in this model is not fixed and is defined as a time-varying function. The time-dependent mechanical properties of asphalt mixtures are efectively reflected. Based on the modified Burgers model, the variable-order function is revised to a linear form. Second, the variable-order fractional Burgers rutting model is obtained by fitting the test data of the RIOHTrack full-scale track. The Levenberg-Marquardt optimization algorithm is used to analyze the test data and the corresponding parameters to obtain more accurate and applicable variable-order fractional rutting mechanics and empirical models for diferent asphalt pavement structures. Finally, according to the classification of the pavement structure, structures III and VI are taken as examples. The rutting prediction and comparison results of several representative pavement structures are obtained to verify that the proposed rutting prediction model can also accurately predict all road sections of RIOHTrack. The new model is also compared with the rutting model of the mechanistic-empirical pavement design guide, the fractional-order Burgers rutting model, and the modified Burgers rutting model. The fitting results are evaluated using the determination coefficient R2. The results show that the variable-order fractional Burgers rutting model proposed in this study exhibits a better fit and is more applicable to describe the rutting deformation of asphalt pavement.

关键词： RIOHTrack full-scale track Caputo fractional derivative variable-order fractional modified Burgers model rutting prediction

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Latency and Energy Consumption for Mobile Edge Computing Based Proximity Detection in Road Networks

引用

China Communications 2022年第4期19卷 274-290页

作者： Tongyu Zhao Yaqiong Liu Guochu Shou Xinwei Yao School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and ConvergenceBeijing 100876China School of Computer Science and Technology Zhejiang University of TechnologyChina

In recent years, artificial intelligence and automotive industry have developed rapidly, and autonomous driving has gradually become the focus of the industry. In road networks, the problem of proximity detection refers to detecting whether two moving objects are close to each other or not in real time. However, the battery life and computing capability of mobile devices are limited in the actual scene,which results in high latency and energy consumption. Therefore, it is a tough problem to determine the proximity relationship between mobile users with low latency and energy consumption. In this article, we aim at finding a tradeoff between latency and energy consumption. We formalize the computation offloading problem base on mobile edge computing(MEC)into a constrained multiobjective optimization problem(CMOP) and utilize NSGA-II to solve it. The simulation results demonstrate that NSGA-II can find the Pareto set, which reduces the latency and energy consumption effectively. In addition, a large number of solutions provided by the Pareto set give us more choices of the offloading decision according to the actual situation.

关键词： proximity detection mobile edge computing road networks constrained multiobjective optimization

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：