检索结果-内蒙古大学图书馆

G²Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

IEEE Transactions on information Forensics and security 2024年 19卷 8773-8785页

作者： Haoxin Yang Xuemiao Xu Cheng Xu Huaidong Zhang Jing Qin Yi Wang Pheng-Ann Heng Shengfeng He School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology State Key Laboratory of Subtropical Building and Urban Science Guangzhou China Centre for Smart Health The Hong Kong Polytechnic University Hong Kong China School of Future Technology South China University of Technology Guangzhou China School of Computer Science and Network Security Dongguan University of Technology Dongguan China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR China School of Computing and Information Systems Singapore Management University Victoria St Singapore

Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent manipulation in pre-trained GANs can lead to changes in ID-irrelevant attributes, adversely affecting data utility due to GAN inversion inaccuracies. This paper introduces G2Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility. We utilize a 3D face model to extract geometric information from the input face, integrating it with a pre-trained GAN-based decoder. This synergy of generative and geometric priors allows the decoder to produce realistic anonymized faces with consistent geometry. Moreover, multi-scale facial features are extracted from the original face and combined with the decoder using our novel identity-aware feature fusion blocks (IFF). This integration enables precise blending of the generated facial patterns with the original ID-irrelevant features, resulting in accurate identity manipulation. Extensive experiments demonstrate that our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility. Code is available at https://***/Harxis/G2Face .

关键词： Faces Data privacy information integrity information filtering Face recognition Generative adversarial networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Double JPEG Compression Detection Based on Markov Model 18th

Double JPEG Compression Detection Based on Markov Model

引用

18th International Workshop on Digital Forensics and Watermarking, IWDW 2019

作者： Wang, Jinwei Huang, Wei Luo, Xiangyang Shi, Yung-Qing Nanjing University of Information Science and Technology Nanjing210044 China Department of Computer and Software Nanjing University of Information Science and Technology NanjingJiangsu210044 China Shanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China State Key Laboratory of Information Security Institute Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Electrical Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

ISBN: (纸本)9783030435745

In this paper, a feature based on the Markov model in quaternion discrete cosine transform (QDCT) domain is proposed for double JPEG compression detection. Firstly, a given JPEG image is extracted from blocked images to obtain amplitude and three angles (ψ, φ, and θ). Secondly, when extracting the Markov features, we process the transition probability matrix with the corresponding refinement. Our proposed refinement method not only reduces redundant features, but also makes the acquired features more efficient for detection. Finally, a support vector machine (SVM) is employed for NA-DJPEG compression detection. It is well known that detecting NA-DJPEG compressed images with (Formula Presented) is a challenging task, and when the images with small size (i.e., 64 × 64), the detection will be more difficult. The experimental result indicates that our method can still achieve a high classification accuracy in this case. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Research on the damage class prediction method in typhoon disaster for power system 3

Research on the damage class prediction method in typhoon di...

引用

3rd IEEE International Conference on information Systems and Computer Aided Education, ICISCAE 2020

作者： Tang, Shiyang Xu, Xiyuan Yang, Yang Yu, Zhen Liu, Zhuguang Guan, Cheng State Grid Key Laboratory of Information Network Security Global Energy Interconnection Research Institute Co. Ltd Beijing China State Grid Zhejiang Electric Power Co. Ltd Hangzhou China State Grid Wenzhou Electric Power Company Wenzhou China

ISBN: (数字)9781728183046

ISBN: (纸本)9781728183039

power system is one of the most fundamental infrastructure systems for human society. The stability of power system greatly affects the economy and security of the city. Therefore, recovering the power system in cities after a severe disaster is the high priority work in a disaster emergency process. Among several kinds of huge disasters, typhoon is a highly valuable research target. Different from the earthquake or tsunami, typhoons often last several days before landing after their generation, so there is much more time for people to prepare and cope with the damage to power system. In this paper, a damage class prediction method for determining the command institution is researched. Based on the actual power system damage data in China from 2004 to 2019, this research proposed the prediction method with machine learning algorithm. The result shows SVM model can reach 77.4 % accuracy in this task, and it is accurate enough to support the emergency decision. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

LBBESA: An efficient software-defined networking load-balancing scheme based on elevator scheduling algorithm

LBBESA: An efficient software-defined networking load-balanc...

引用

作者： Li, Qiliang Cui, Jie Zhong, Hong Du, Yichao Luo, Yonglong Liu, Lu School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Network and Information Security Wuhu China School of Electronics Computing and Mathematics University of Derby DerbyDE22 1GB United Kingdom

Elevator scheduling algorithms generally denote methods used to calculate how to use the elevator. These algorithms can distribute elevators to various floors of a building, thereby achieving efficient transportation. From the perspective of the elevator scheduling problem, we address the load-balancing problem for software-defined networking (SDN) architecture and propose a load-balancing method based on the elevator scheduling algorithm, LBBESA. We take advantage of the flexibility of the SDN architecture, obtain the real-time load of the server through real-time statistical analyses of the SDN switch port traffic by the controller, and combine this with the idea of regional elevator allocation to coordinate the connection of the client's requests and realize the load balancing of each server in the cluster. Simulation experiments show that, compared with the round-robin algorithm, LBBESA is more effective in the load balancing of the server pool and can improve the throughput of the server pool to a certain extent. In addition, our scheme is easy to implement and has high scalability. © 2019 John Wiley & Sons, Ltd.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Scene Dynamic Scanning Modeling Technology of Substation Based on Depth Vision 1

引用

Annual International Conference on 3D Imaging Technology, IC3DIT 2019

作者： Hai, Yu Min, Xu Lin, Peng Wei, Liu Rong, Sun Jian, Shao Gang, Wang Global Energy Interconnection Research Institute Co. Ltd Nanjing Jiangsu210003 China State Grid Key Laboratory of Information and Network Security Nanjing210003 China Electric Power Research Institute of State Grid Jiangsu Electric Power Company Nanjing Jiangsu210003 China

ISBN: (数字)9789811538674

ISBN: (纸本)9789811538667

State Grid’s intelligent transportation inspection system has taken "self and environmental awareness" as one of its core functions. Among them, environmental modeling and intelligent reconfiguration are the basis for panoramic information collection and organization of field operations, using multiple sensing technologies and high efficiency. The intelligent image processing algorithm eliminates the need to additionally deploy base stations or sensors at the job site, and can directly form 3D model by scanning the environment directly at the job site through the portable terminal. Furthermore, the various types of information on the site are mainly spatial dimensions, and the time dimension and logical relationship are supplemented by reorganization. This technology will provide new automation and intelligent solutions for grid field operations, improve operation modes, improve work efficiency, and achieve active safety protection. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

A BCS-GDE Multi-objective Optimization Algorithm for Combined Cooling, Heating and power Model with Decision Strategies

arXiv

引用

arXiv 2022年

作者： Sun, Jiaze Deng, Jiahui Li, Yang Han, Nan School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi’an710127 China School of Information Science and Technology Northwest University Xi’an710127 China School of Electrical Engineering Northeast Electric Power University Jilin132012 China

District energy systems can not only reduce energy consumption but also set energy supply dispatching schemes according to demand. In addition to economic cost, energy consumption and pollutant are more worthy of attention when evaluating combined cooling, heating and power (CCHP) models. In this paper, the CCHP model is established with the objective of economic cost, primary energy consumption, and pollutant emissions. The mathematical expression of the CCHP system is proposed, and a multi-objective optimization model with constraints is established. According to different usage requirements, two decision-making strategies are designed, which can adapt to different scenarios. Besides, a generalized differential evolution with the best compromise solution processing mechanism (BCS-GDE) algorithm is proposed to optimize the CCHP model for the first time. The algorithm provides the optimal energy scheduling scheme by optimizing the production capacity of different capacity equipment. The simulation is conducted in three application scenarios: hotels, offices, and residential buildings. The simulation results show that the model established in this paper can reduce economic cost by 72%, primary energy consumption by 73%, and pollutant emission by 88%. Concurrently, the Wilcoxon signed-rank test shows that BCS-GDE is significantly better than OMOPSO, NSGA-II, and SPEA2 with greater than 95% confidence. Copyright © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Computational strategy of dynamic nanorod networks for dielectric elastomer nanocomposites towards the balance of high permittivity, low modulus, and high breakdown strength

引用

Polymer 2025年

作者： Han Qin Yancong Feng Tao Liu Baofeng Gao Ying Guo Jingshan Pan Ming Tian Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250000 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan 250000 China Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University Guangzhou 510006 China State Key Laboratory of Organic-Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing 100029 China

Dielectric elastomers exhibit immense potential in emerging fields such as soft robotics, flexible sensors, wearable electronic devices, and energy harvesting, but their widespread application is limited by the intricate paradoxes among the high permittivity, low modulus, and high breakdown strength. By regulating the aspect ratio, concentration, interaction strength, and crosslinking density, a dynamic nanorod network structure is constructed to harmonize comprehensive properties. The construction of the nanorod network significantly enhances permittivity due to the coupling effect of nanorods. Meanwhile, the low percolation threshold avoids high modulus, enabling large electro-induced strain. Under high strain, nanorod orientation shifts, leading to the destruction of the network, thereby avoiding the electric field concentration and achieving the enhancement of electromechanical stability. After the external field is withdrawn, entropic elasticity drives the recovery of elastomers, while the network reconstructs to restore the high dielectric constant. This strategy offers new insights into balancing high permittivity, low modulus, and high breakdown strength in practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition

arXiv

引用

arXiv 2025年

作者： Wang, Changwei Chen, Shunpeng Song, Yukun Xu, Rongtao Zhang, Zherui Zhang, Jiguang Yang, Haoran Zhang, Yu Fu, Kexue Du, Shide Xu, Zhiwei Gao, Longxiang Guo, Li Xu, Shibiao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China MAIS Institute of Automation Chinese Academy of Sciences China Tongji University China College of Computer and Data Science Fuzhou University China Shandong University China

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Non-aligned double JPEG compression detection based on refined Markov features in QDCT domain

Non-aligned double JPEG compression detection based on refin...

引用

作者： Wang, Jinwei Huang, Wei Luo, Xiangyang Shi, Yun-Qing Jha, Sunil Kr. School of Computer and Software Nanjing University of Information Science and Technology NanjingJiangsu China Nanjing University of Information Science and Technology Nanjing China Shanxi Key Laboratory of Network and System Security Xidian University Shanxi China State Key Laboratory of Mathematical Engineering and Advanced Computing ZhengzhouHenan China New Jersey Institute of Technology NewarkNJ United States

Due to the widespread use of the JPEG format, non-aligned double JPEG (NA-DJPEG) compression is very common in image tampering. Therefore, non-aligned double JPEG compression detection has attracted significant attention in digital forensics in recent years. In most of the previous detection algorithms, grayscale images are used directly, or color images are first converted into grayscale images and then processed. However, it is worth noting that most tampered images are color images. To make full use of the color information in images, a detection algorithm, which uses color images directly, is put forward in this paper. The algorithm based on refined Markov in quaternion discrete cosine transform (QDCT) domain is proposed for NA-DJPEG compression detection. Firstly, color information of a given JPEG image is extracted from blocked images to construct quaternion, and then block image QDCT coefficient matrices, including amplitude and three angles (ψ, , and θ) can be obtained. Secondly, the refined Markov features are generated from the transition probability matrix in the corresponding refinement process. Our proposed refinement method not only reduces redundant features but also makes the acquired features more efficient in detection. Therefore, the refined Markov features can not only capture the intra-block correlation between block QDCT coefficients but also improve computing efficiency in real-time. Finally, support vector machine (SVM) method is employed for NA-DJPEG compression detection. The experiment results demonstrate that the proposed algorithm not only make use of color information of images, but also can achieve better detection performance with small size images (i.e., 64 × 64) outperforming state-of-the-art detection methods tested on the same dataset. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Univariate Forecasting of time series data Based on Seq2Seq Model 4

Univariate Forecasting of time series data Based on Seq2Seq ...

引用

4th International Conference on Electronic information Technology and Computer Engineering, EITCE 2020

作者： Guo, Yanwen Wu, Tao Liu, Yanbing Jiang, Yixin Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China School of Cybersecurity and Information Law Chongqing University of Posts and Telecommunications Chongqing China Chongqing Engineering Laboratory of Internet and Information Sccurity Chongqing University of Posts and Telecommunications Chongqing China Electric Power Research Institute Csg Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China

ISBN: (纸本)9781450387811

With the release of country's 2020 new infrastructure projects, the increasing demand for electricity in various projects has further promoted the intelligent upgrade of the power grid. The processing of grid data at the edge has become one of the future trends of next generation grid. In the field of power grid edge time series data prediction, the inability to obtain the variable characteristics of other systems and the uncertainty of the length of various edge input data, this paper proposes a Seq2seq prediction model based on a Bi-directional Long Short Term Memory (Bi-LSTM). Bi-LSTM can make full use of contextual information to achieve a more accurate prediction effect. The Seq2Seq model can process variable-length sequence data. In this paper, Seq2Seq model and BI-LSTM model are combined to solve the problem of uncertain edge length and univariate prediction. At the same time, in order to solve the information loss caused by Seq2Seq in the encoding stage, the Attention mechanism is introduced, it can compute the allocation of resources to more important tasks while addressing the problem of information overload. Through experimental research, it is found that the proposed ABSeq2Seq model is superior to other classic models in univariate prediction, and it has the better generalization for various types of data. We have proved its effectiveness in the single variable power prediction. © 2020 ACM.

关键词： Time series

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：