检索结果-内蒙古大学图书馆

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Lulu Ye Huabin Wang Yufeng Shi Liang Tao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China

At present, the biometric template algorithms with state of the art recognition performance cannot guarantee the security of the system, whereas the security biometric template algorithms usually suffer from inaccurate recognition. In order to improve both the recognition performance and security of feature template for finger vein, a cancelable template algorithm is proposed in this paper. Firstly, a variable curvature Gabor filter is designed for finger vein orientation feature extraction. The maximum and sub-maximum orientation of Gabor filter are combined with differential excitation respectively to generate joint distribution features, which serve as feature vectors of finger vein. Secondly, the extracted feature vectors are reduced dimension by PCA, and the reduced feature vectors are combined with the pseudo random matrix, which is produced by a token to generate a cancelable template to guarantee the security. Finally, cancelable templates in two orientations are fused to increase the irreversibility of templates by using the improved canonical correlation analysis. Extensive experiments on the SDUMLA-FV and PolyU databases demonstrate the superiority of the proposed method in terms of verification performance, diversity, revocability/reusability and irreversibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Low-Complexity and High-Efficient Pilot Allocation Scheme Based on User Grouping in Massive MIMO System

A Low-Complexity and High-Efficient Pilot Allocation Scheme ...

引用

International Conference on Communication Technology (ICCT)

作者： Xinying Zhao Yijing Yao Lei Xu Hongyu Fang Hongwei Zhang Xiaohui Li Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China

Pilot allocation is one of the effective means to reduce pilot pollution in massive Multiple-Input Multiple-Output (MIMO) systems. The goal of this paper is to improve the uplink achievable sum rates of strong users, and ensure the quality of service (QoS) requirements of weak users at the same time, so that the sum rates of system can be improved. Combining with the technical advantage of pilot grouping, a low complexity pilot allocation scheme based on matching algorithm is proposed, which divides the users in the target cell into weak user group and strong user group, and adopts the minimum-maximum matching method to allocate pilots in weak user group. Through the introduction of Hungarian algorithm, a pilot allocation method is designed to ensure the fairness of the strong users. The simulation results show that, compared with the smart pilot allocation scheme, the pilot allocation scheme based on Hungarian algorithm, the pilot allocation scheme based on user grouping and the random pilot allocation scheme, the system performance of the proposed scheme has been effectively improved.

关键词： Resource management Pollution Uplink Interference Fading channels Antennas Massive MIMO

来源：评论

学校读者我要写书评

暂无评论

Meta auxiliary learning for facial action unit detection

arXiv

引用

arXiv 2021年

作者： Li, Yong Shan, Shiguang Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Cas Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Cas Center for Excellence in Brain Science and Intelligence Technology

Despite the success of deep neural networks on facial action unit (AU) detection, better performance depends on a large number of training images with accurate AU annotations. However, labeling AU is time-consuming, expensive, and error-prone. Considering AU detection and facial expression recognition (FER) are two highly correlated tasks, and facial expression (FE) is relatively easy to annotate, we consider learning AU detection and FER in a multi-task manner. However, the performance of the AU detection task cannot be always enhanced due to the negative transfer in the multi-task scenario. To alleviate this issue, we propose a Meta Auxiliary Learning method (MAL) that automatically selects highly related FE samples by learning adaptative weights for the training FE samples in a meta learning manner. The learned sample weights alleviate the negative transfer from two aspects: 1) balance the loss of each task automatically, and 2) suppress the weights of FE samples that have large uncertainties. Experimental results on several popular AU datasets demonstrate MAL consistently improves the AU detection performance compared with the state-of-the-art multi-task and auxiliary learning methods. MAL automatically estimates adaptive weights for the auxiliary FE samples according to their semantic relevance with the primary AU detection task. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Graph jigsaw learning for cartoon face recognition

arXiv

引用

arXiv 2021年

作者： Li, Yong Lao, Lingjie Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognize cartoon faces is to precisely perceive their sparse and critical shape patterns. However, it is quite difficult to learn a shape-oriented representation for cartoon face recognition with convolutional neural networks (CNNs). To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner. Solving the puzzles requires the model to spot the shape patterns of the cartoon faces as the texture information is quite limited. The key idea of GraphJigsaw is constructing a jigsaw puzzle by randomly shuffling the intermediate convolutional feature maps in the spatial dimension and exploiting the GCN to reason and recover the correct layout of the jigsaw fragments in a self-supervised manner. The proposed GraphJigsaw avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification. Specially, GraphJigsaw can be incorporated at various stages in a top-down manner within the classification model, which facilitates propagating the learned shape patterns gradually. GraphJigsaw does not rely on any extra manual annotation during the training process and incorporates no extra computation burden at inference time. Both quantitative and qualitative experimental results have verified the feasibility of our proposed GraphJigsaw, which consistently outperforms other face recognition or jigsaw-based methods on two popular cartoon face datasets with considerable improvements. © 2021, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Learning fair face representation with progressive cross transformer

arXiv

引用

arXiv 2021年

作者： Li, Yong Sun, Yufei Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identityrelated representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/racespecific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions. © 2021, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Solution of Underdetermined Equations for DGTD based on Prior knowledge

A Novel Solution of Underdetermined Equations for DGTD based...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Qi Qi Xinyuan Cao Mingsheng Chen Zhixiang Huang Yi Liu Xianliang Wu Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei Anhui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Hefei China School of Electronic Engineering Huainan Normal University Huainan China

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

To accelerate solving transient electromagnetic problems by discontinuous Galerkin time domain (DGTD) method, a solution of underdetermined equations is established based on prior knowledge. In the proposed method, nodal basis function and a leapfrog scheme are used to Maxwell curl equations for spatial and time discretization. Electromagnetic fields in each element of computation domain are updated individually by applying conventional DGTD in initial time. When the electromagnetic wave covers the domain, the fields of all elements are updated as a whole. The underdetermined equations are established by randomly extracting rows from global mass matrix. Taking the results of a few previous time steps as the prior knowledge, a sparse transform is constructed. Then the underdetermined system of equations can be solved by recovery algorithms. Meanwhile,in order to maintain the advantage of low computational complexity, a restart mechanism is presented. The validity of the proposed method is verified by numerical experiments.

关键词： Microwave technology Millimeter wave technology Transforms Sparse matrices Electromagnetic fields Transient analysis Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Invariant-preserving schemes with arbitrarily high-order accuracy for the two-component Camassa–Holm system via Hamiltonian boundary value methods

引用

Communications in Nonlinear Science and Numerical Simulation 2025年 150卷

作者： Luo, Qian Xiao, Aiguo Li, Min Yan, Xiaoqiang School of Mathematics and Computational Science & Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan411105 China School of Mathematics and Physics China University of Geosciences Wuhan430074 China National Center for Applied Mathematics in Hunan Xiangtan University Hunan411105 China

In this paper, we present an arbitrarily high-order numerical scheme for the two-component Camassa–Holm system, ensuring the preservation of three invariants: energy and two Casimir functions. The spatial discretization is achieved using Fourier–Galerkin methods, resulting in a semi-discrete system which retains a Hamiltonian structure and approximates the invariants of the original continuous system. Subsequently, an energy-preserving Runge–Kutta method, such as Hamiltonian boundary value methods, is applied to the semi-discrete system, yielding a fully discrete scheme of arbitrarily high order. The proposed scheme is validated through numerical simulations, demonstrating its accuracy and capability in capturing different types of solutions of the two-component Camassa–Holm equation. © 2025 Elsevier B.V.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

3R: Word and Phoneme Edition based Data Augmentation for Lexical Punctuation Prediction

3R: Word and Phoneme Edition based Data Augmentation for Lex...

引用

International Conference on Computational Intelligence and Security

作者： Aihua Zheng Naipeng Ye Xiao Wang Xiao Song Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Peking University Shenzhen Institute Shenzhen China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

Existing Lexical Punctuation Prediction methods are mainly trained on the standard clean data while losing the generalization in practical automatic speech recognition (ASR) system with ubiquitous transcription errors. To bridge the gap between clean training data and noisy testing data, we propose three random (3R) data augmentation strategies: random word deletion (RWD), random word substitution (RWS), and random phoneme edition (RPE) in both word and phoneme levels on the training dataset. Specifically, we contribute an acoustically similar vocabulary with phoneme level editions for acoustically similar word substitution. In addition, we first introduce the RoBERTa-large model into a punctuation prediction task to capture the semantics and the long-distance dependencies in language. Extensive experiments on the English dataset IWSLT2011 yield to a new state-of-the-art comparing to the prevalent punctuation prediction methods.

关键词： Training Vocabulary Semantics Training data Predictive models Noise measurement Security

来源：评论

学校读者我要写书评

暂无评论

A Pilot Allocation Method of Jointing Cell Grouping and Alliance Game in Massive MIMO System

A Pilot Allocation Method of Jointing Cell Grouping and Alli...

引用

第二届材料科学应用与能源材料国际研讨会

作者： Feiyue Wang Hui Zhi Ziju Huang Key Lab of Computing Intelligent and Signal Processing(Ministry of Education) Anhui University

In order to improve the uplink channel estimation performance and reduce pilot contamination(PC),this paper proposes a pilot allocation method of jointing cell grouping and alliance game(JCG-AG) for massive multiple-input multiple-output(MIMO) cellular *** can be divided into two ***,by properly dividing all cells into different cell-groups,the users in different cell-groups are allocated different orthogonal pilot ***,the users in the same cell-group are further divided into several mutually disjoint *** belonging to different sub-alliances are allocated different pilots,and users belonging to the same sub-alliance reuse the same *** the second step,the alliance formation algorithm is used to suppress *** JCG-AG method takes practical application as the starting point,focuses on the random distribution of users,and uses the idea of alliance *** these make it more flexible and *** demonstrated in the simulation results,the JCG-AG method can greatly mitigate the PC and reduce the average mean square error(MSE) for all channel estimations in the uplink.

关键词： MSE red A Pilot Allocation Method of Jointing Cell Grouping and Alliance Game in Massive MIMO System

来源：评论

学校读者我要写书评

暂无评论

The Downlink Performance of Massive MIMO Systems under Different Uplink Pilot Allocation Schemes

The Downlink Performance of Massive MIMO Systems under Diffe...

引用

第二届材料科学应用与能源材料国际研讨会

作者： Ziju Huang Hui Zhi Feiyue Wang Key Lab of Computing Intelligent and Signal Processing(Ministry of Education) Anhui University

In the scenario of time division duplexing(TDD) massive multiple-input multiple-output(MIMO) system,when there is pilot contamination(PC) in the uplink,different pilot allocation schemes will affect the results of the uplink channel *** the channel estimation results are used for downlink transmission precoding,which will further affects the downlink *** paper analyses the impact of different pilot allocation(PA) schemes on downlink *** theoretical analysis,the system downlink signal to interference plus noise ratio(SINR) and spectral efficiency expressions of different pilot allocation schemes are obtained *** simulation results show that the pilot allocation schemes with cell grouping is better than the schemes without cell *** SINR increases as the number of cell grouping increases,and the spectrum efficiency increases first and then decreases as the number of cell grouping increases.

关键词： TDD The Downlink Performance of Massive MIMO Systems under Different Uplink Pilot Allocation Schemes

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：