检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Wan, Junwei Chen, Yaojie Zheng, Xuecong Wuhan University of Science and Technology Department of Computer Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350330717

In addressing the challenges of limited semantic labeling data and imprecise segmentation regions prevalent in the semantic segmentation of ship flame images, this study introduces a semi-supervised semantic segmentation method tailored for ship flame images. This approach is grounded in the principles of pairwise similarity with strong-weak perturbations. Adopting a pseudo-label self-learning strategy, the method employs weak-strong perturbation pairwise similarity, ensuring the propagation of high-confidence predictions during label generation, and thereby enhancing performance. Additionally, to tackle the inherent difficulties presented by smoke enveloping and obscuring flame regions in ship images, we have conceived a Vertical Continuity Feature Enhancement module. This module empowers the model to discern more explicit inter-class boundaries. Empirical evaluations on our proprietary dataset substantiate the superiority of our method, registering an improvement of 4.12 percentage points in mIoU over other semi-supervised approaches. Such results attest to the efficacy of the proposed pairwise similarity approach and the Vertical Continuity Feature Enhancement module in flame semantic segmentation. © 2023 IEEE.

关键词： Feature enhancemen Pairwise similarity Semantic segmentation Semi-Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Image Quality Assessment Method Based on Cross-Modal 20th

Image Quality Assessment Method Based on Cross-Modal

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Long, Teng Chen, Li Wang, Yubo School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430065 China

ISBN: (纸本)9789819970247

Deep learning methods have achieved remarkable results in the direction of image quality assessment tasks. However, most of the related studies focus only on image unimodal, ignoring the potential advantages that come with the development of cross-modal techniques. Cross-modal models have implied a wealth of information, which provides new research directions and possibilities in the field of image quality assessment. In this paper, the feasibility of cross-modal models in image quality assessment is first explored for the image quality binary classification task. Subsequently, the optimization prompting method is combined with the tuning of the image encoder in the cross-modal model so that the cross-modal model can be used for image quality assessment scoring. To verify the feasibility of the cross-modal model on the image quality assessment task, an empirical analysis was conducted on the binary image quality dataset PQD, and it was found that the F1 score improved by 18% over the baseline model. Further, we propose an adaptive cross-modal image quality assessment method AC-IQA. On the image quality scoring dataset, compared with the previous optimal methods, AC-IQA improves the PLCC and SROCC metrics on the TID2013 dataset by 5.5% and 9.5%, respectively, and on the KADID dataset by 6.2% and 5.2%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Application of improved sparrow search algorithm in wave compensation

Application of improved sparrow search algorithm in wave com...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Hu, Ao Lin, Yunhan Chen, Yaojie School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real Time Industrial System Wuhan University of Science and Technology Hubei Wuhan430065 China

ISBN: (纸本)9781510680425

To solve the problem of ship heave motion in harsh marine environments, which affects the positioning accuracy and safety of its robotic arm, this paper adopts a PID parameter optimization method based on Tent cold light source improved sparrow search ***, utilizing Tent chaotic mapping to enhance the diversity of sparrow populations, and inspired by the fluorescence attraction effect in the firefly algorithm, this paper perturbs sparrows with a cold light source strategy to obtain better positions and improve their search ***, simulation experiments were conducted to optimize the PID control system using improved *** results showed that compared with the three population intelligent optimization algorithm, the improved algorithm had better convergence accuracy, system response speed, and ***, the improved algorithm was applied to the actual experiment of compensating for the heave direction at the end of a shipborne robotic *** comparison of the four algorithms in compensating for the height difference in the heave direction showed that the improved algorithm had the best heave compensation effect, reflecting the effectiveness of the algorithm in engineering *** provides a certain reference for the active compensation of swarm intelligence optimization algorithms in the heave direction of ships. © 2024 SPIE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stage Method for Texture Defect Detection 4

A Novel Two-Stage Method for Texture Defect Detection

引用

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

Energy-efficient computation offloading via deep reinforcement learning in mobility-aware multi-access edge computing systems with diverse users

引用

Expert systems with Applications 2025年 286卷

作者： Wu, Haixing Jin, Shunfu School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Multi-access Edge Computing (MEC) has been a promising solution that enables Internet of Things (IoT) devices to support computation-intensive applications by offloading some tasks to the network edge. However, most existing offloading methods in MEC systems are based on the premise of scenarios with either single-type or stable users, which is not aligned with the practical situations of users’ diversity and mobility. In addition, these methods always ignore energy saving strategies in MEC systems, which inevitably degrades Utility Energy Efficiency (UEE). To tackle these issues, considering personalized requirements from diverse users and idle energy consumption in MEC servers, we propose a novel computation offloading architecture with adaptive sleeping mechanism and heterogeneous MEC servers. Based on the architecture, we investigate energy-efficient computation offloading in mobility-aware MEC systems with diverse users. Under the Deep Reinforcement Learning (DRL) framework, we propose a Twin Delayed Deep Deterministic Policy Gradient Algorithm with Bursty Traffic (TD3-BT), in which the inherent correlation of task arrivals is taken into account to capture the behavior of correlated traffic and provide rational metrics estimation within one time slot. A long-term system cost minimization problem is formulated to optimize computation offloading for the trade-off between system delay and UEE. Assisted by TD3-BT, the formulated problem is effectively solved and the decision making in each time slot is provided for diverse users. Experimental results demonstrate that our TD3-BT algorithm achieves superior performance under various offloading scenarios compared to some benchmarks. © 2025 Elsevier Ltd

关键词： Energy efficiency

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

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

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

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：