检索结果-内蒙古大学图书馆

6th International Conference on Machine Learning and Natural Language processing, MLNLP 2023

作者： Zhou, Maoxian The Computer College of Qinghai Normal University Qinghai Xining810016 China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Qinghai Xining810008 China Qinghai Engineering and Technology Research Center for Tibetan Information Processing Qinghai Xining810008 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China

ISBN: (纸本)9798400709241

In recent years, with the emergence of deep learning methods, Neural Machine Translation has become a new research direction of machine translation. Due to the scarcity of digital resources in Tibetan, there is only a small-scale Tibetan-Chinese bilingual parallel corpus to train translation models. In the case of insufficient resources, the performance of Neural Machine Translation decreases significantly. In this regard, considering that the word alignment results in Tibetan-Chinese Statistical Machine Translation are better, and the alignment information in Tibetan-Chinese Neural Machine Translation model is significantly different from that in Tibetan-Chinese Statistical Machine Translation, this paper proposes a Tibetan-Chinese Neural Machine Translation method that integrates statistical methods. We using Statistical Machine Translation method to generate word alignment information of Tibetan-Chinese parallel corpus to supervise the training process of Tibetan-Chinese Neural Machine Translation model to make the model achieve more accurate translation and alignment effect. Experimental results show that this method can effectively improve translation quality in low resource environment. © 2023 ACM.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Robust ∞ model reduction for the continuous fractional-order two-dimensional Roesser system: The 0 < Ε ≤ 1 case

引用

Mathematical Methods in the Applied Sciences 2024年第2期47卷 782-798页

作者： Zhang, Jia-Rui Lu, Jun-Guo Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

This study analyzes the (Formula presented.) model reduction methods and the robust (Formula presented.) model reduction methods for the continuous fractional-order (FO) two-dimensional (2D) Roesser system with the FO ranging from 0 to 1. A sufficient LMI-based condition is given by Projection Lemma, the FO-stable-region-analyze method and matrix analysis, guaranteeing that the error system is stable and that its transfer function's (Formula presented.) -norm is bounded. Then, the approach to design the reduced-model system of the original continuous FO 2D Roesser model is given. The robust (Formula presented.) model reduction methods for continuous FO 2D Roesser systems with polytopic uncertainties are proposed based on the results above. In the end, two numerical examples are used to demonstrate the effectiveness of the results. © 2023 John Wiley & Sons, Ltd.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

SiamAHG: adaptive hierarchical graph attention for lightweight siamese tracking

引用

Journal of King Saud University - Computer and information Sciences 2025年第4期37卷 1-12页

作者： Li, Na Fan, Yaofu Chen, Xuhao Liu, Xinyu He, Jinglu School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an 710121 China Xi’an Key Laboratory of Image Processing Technology and Applications for Public Security Xi’an 710121 China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi’an 710121 China

In order to balance the tracking performance and inference speed, a lightweight Siamese-based tracker named SiamAHG is proposed in this paper. It employs the lightweight network ShuffleNet V2 for feature extraction and a novel adaptive hierarchical graph attention for feature fusion. Specifically, the feature fusion sub-network consists of an adaptive feature map refinement module (AFMRM) and a hierarchical graph attention module (HGAM). AFMRM refines feature maps of different stages and strengthens the model expression by combining multiple convolutional kernels dynamically based upon diverse attentions. HGAM realizes node-level information interaction of the same stage between the template and search branches, and integrates the features of different stages to get complementary information for tracking. Experiments on LaSOT, OTB100, GOT-10k, and UAV123 validate the effectiveness and efficiency of our proposed tracker. It has significant advantages in model complexity and inference speed, while achieving competitive results with state-of-the-art trackers. © The Author(s) 2025.

关键词： Adaptive hierarchical graph attention Lightweight Siamese network Visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Hybrid Metric-Induced Nonnegative Matrix Factorization

Hybrid Metric-Induced Nonnegative Matrix Factorization

引用

2023 China Automation Congress, CAC 2023

作者： Yang, Sijun Chen, Wen-Sheng Pan, Binbin College of Mathematics and Statistics Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9798350303759

NMF is a promising feature representation method for data analysis. Matrix decomposition losses can be described using different metrics, based on which different NMF algorithms can be developed. However, a small Euclidean distance metric is not guaranteed to have a small cosine similarity metric, and vice versa. To overcome the shortcomings of these metrics, we integrate these two metrics to present a novel hybrid metric-induced NMF (HMNMF) model. The update rules for the HMNMF algorithm are obtained using the gradient descent method to resolve the optimization problem. The proposed algorithm is proven to be convergent, which implies that it is reasonable and stable. The proposed HMNMF approach is compared with different metric-induced NMF algorithms for face recognition, the experimental results confirm the effectiveness and good performance of the proposed algorithm. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

C-privacy:A social relationship-driven image customization sharing method in cyber-physical networks

引用

Digital Communications and Networks 2025年第2期11卷 563-573页

作者： Dapeng Wu Jian Liu Yangliang Wan Zhigang Yang Ruyan Wang Xinqi Lin School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Aerospace Tianmu Satellite Technology Company Limited Chongqing401332China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing400065China College of Computer and Cyber Security Fujian Normal UniversityFujian350117China The Advanced Network and Intelligent Connection Technology Key Laboratory Chongqing400065China Key Laboratory of Ubiquitous Sensing and Networking Chongqing400065China

Cyber-Physical Networks(CPN)are comprehensive systems that integrate information and physical domains,and are widely used in various fields such as online social networking,smart grids,and the Internet of Vehicles(IoV).With the increasing popularity of digital photography and Internet technology,more and more users are sharing images on ***,many images are shared without any privacy processing,exposing hidden privacy risks and making sensitive content easily accessible to Artificial Intelligence(AI)*** image sharing methods lack fine-grained image sharing policies and cannot protect user *** address this issue,we propose a social relationship-driven privacy customization protection model for publishers and *** construct a heterogeneous social information network centered on social relationships,introduce a user intimacy evaluation method with time decay,and evaluate privacy levels considering user interest *** protect user privacy while maintaining image appreciation,we design a lightweight face-swapping algorithm based on Generative Adversarial Network(GAN)to swap faces that need to be *** proposed method minimizes the loss of image utility while satisfying privacy requirements,as shown by extensive theoretical and simulation analyses.

关键词： Cyber-physical networks Customized privacy Face-swapping Heterogeneous information network Deep fakes

来源：评论

学校读者我要写书评

暂无评论

Verifiable searchable symmetric encryption for conjunctive keyword queries in cloud storage

引用

Frontiers of Computer Science 2022年第6期16卷 103-121页

作者： Qingqing GAN Joseph K.LIU Xiaoming WANG Xingliang YUAN Shi-Feng SUN Daxin HUANG Cong ZUO Jianfeng WANG Guangzhou Key Laboratory of Multilingual Intelligent Processing School of Information Science and Technology/School of Cyber SecurityGuangdong University of Foreign StudiesGuangzhou510006China Department of Computer Science Jinan UniversityGuangzhou510632China Faculty of Information Technology Monash UniversityClayton3168Australia State Key Laboratory of Integrated Service Networks(ISN) Xidian UniversityXi’an710071China

Searchable symmetric encryption(SSE)has been introduced for secure outsourcing the encrypted database to cloud storage,while maintaining searchable *** various SSE schemes,most of them assume the server is honest but curious,while the server may be trustless in the real *** a malicious server not honestly performing the queries,verifiable SSE(VSSE)schemes are constructed to ensure the verifiability of the search ***,existing VSSE constructions only focus on single-keyword search or incur heavy computational cost during *** address this challenge,we present an efficient VSSE scheme,built on OXT protocol(Cash et al.,CRYPTO 2013),for conjunctive keyword queries with sublinear search *** proposed VSSE scheme is based on a privacy-preserving hash-based accumulator,by leveraging a well-established cryptographic primitive,Symmetric Hidden Vector Encryption(SHVE).Our VSSE scheme enables both correctness and completeness verifiability for the result without pairing operations,thus greatly reducing the computational cost in the verification ***,the proposed VSSE scheme can still provide a proof when the search result is ***,the security analysis and experimental evaluation are given to demonstrate the security and practicality of the proposed scheme.

关键词： searchable symmetric encryption verifiability conjunctive keyword queries hash-based accumulator cloud storage

来源：评论

学校读者我要写书评

暂无评论

Exploring Trial-and-Error in Deep Learning:Initial Application to Isotope Detection in Mass Spectrometry

引用

Big Data Mining and Analytics 2024年第4期7卷 1251-1261页

作者： Qihong Jiao Yuxiao Wang Yongshuai Wang Shiwei Sun Xuefeng Cui School of Computer Science and Technology Shandong UniversityQingdao 266237China Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China

Mass spectrometry plays a crucial role in biomedicine by detecting isotopes,contributing significantly to research,diagnostics,and therapy *** study introduces IsoFusion,a deep learning model designed to address isotope detection in raw mass *** than directly applying convolutional layers to all signal and noise peaks,IsoFusion employs a trial-and-error ***,it investigates all potential charge states(trials)and collects signal peaks around expected m/z values for each ***,convolutional layers extract features from each trial,which are fused to identify the correct ***,the reparameterization trick predicts isotope features based on this correct trial.A key advantage of IsoFusion is shared model parameters across all trials,enhancing feature learning for less common charge states using data from prevalent *** results show a significant accuracy improvement for charge state 5,reaching 99.42%,compared to DeepIso’s 43.36%.Moreover,IsoFusion achieves a 97.33%detection accuracy for isotopes,with 2.4%of detected isotopes previously unidentified by four commonly used methods.

关键词： Liquid Chromatography-Mass Spectrometry(LC-MS) isotope detection retention time prediction charge state prediction deep learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Physiological Signal Analysis Using Attention-Based Feature and Model Fusion 17th

Multimodal Physiological Signal Analysis Using Attention-Bas...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Liu, Wei Jia, Kebin Sun, Zhonghua Feng, Jinchao Zhao, Xiaohu Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Laboratory of Advanced Information Networks Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

ISBN: (纸本)9789819632930

Disease analysis using multimodal physiological signals is currently a hot research area. Aiming at the problem that current multimodal feature fusion approaches neglect the correlation between different modalities, this paper proposes a hybrid multimodal fusion model based on the attention mechanism for depression recognition. The model selects two modalities, EEG and speech signals, for feature fusion. In the feature extraction stage of EEG signals, the correlation between features is analyzed using Spearman’s rank correlation coefficient to achieve dimensionality reduction. In the feature-level modal fusion stage, the attention mechanism is applied to automatically learn the contribution of different features and the complementarity between different modalities. In the model fusion layer, a multi-layer long and short-term memory network (ML-LSTM) is adopted, which makes full use of the complementarity between the features of EEG signals and audio signals. Finally, the outputs of feature-level fusion and model-level fusion are weighted and combined to obtain the final prediction results. Experimental results on the MODMA dataset show that the accuracy of the proposed multimodal fusion model for depression recognition reached 88.54%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

IMPULSE NOISE REMOVAL BY L1 WEIGHTED NUCLEAR NORM MINIMIZATION

引用

Journal of Computational Mathematics 2023年第6期41卷 1171-1191页

作者： Jian Lu Yuting Ye Yiqiu Dong Xiaoxia Liu Yuru Zou Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China Guangdong Key Laboratory of Intelligent Information Processing Pazhou LabGuangzhou 510335China Department of Applied Mathematics and Computer Science Technical University of Denmark2800 Kgs.LyngbyDenmark

In recent years,the nuclear norm minimization(NNM)as a convex relaxation of the rank minimization has attracted great research *** assigning different weights to singular values,the weighted nuclear norm minimization(WNNM)has been utilized in many ***,most of the work on WNNM is combined with the l 2-data-fidelity term,which is under additive Gaussian noise *** this paper,we introduce the L1-WNNM model,which incorporates the l 1-data-fidelity term and the regularization from *** apply the alternating direction method of multipliers(ADMM)to solve the non-convex minimization problem in this *** exploit the low rank prior on the patch matrices extracted based on the image non-local self-similarity and apply the L1-WNNM model on patch matrices to restore the image corrupted by impulse *** results show that our method can effectively remove impulse noise.

关键词： Image denoising Weighted nuclear norm minimization l 1-data-fidelity term Low rank analysis Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Research on Automotive Parts Recognition Based on Improved YOLOv5 Algorithm

Research on Automotive Parts Recognition Based on Improved Y...

引用

2024 International Conference on Remote Sensing, Mapping, and Image processing, RSMIP 2024

作者： Xu, Yu Hu, Shan Ming, Rui Zhang, Tianzhi School of Automation and Electrical Engineering Tianjin University of Technology and Education Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9781510680012

With the continuous development of the automotive industry, the target detection and recognition of automotive parts have become crucial factors for automakers to enhance automation levels. In this paper, to ensure improved detection accuracy while meeting real-time detection requirements, we propose an enhanced YOLOv5 model for automotive parts recognition. This method optimizes candidate box parameters using the K-Means algorithm, addresses feature mismatch issues through variational convolution, and optimizes the loss function using GIOU instead of IOU. Experimental results show that the improved YOLOv5 algorithm achieves an average precision of 99.1%, representing a relative improvement of 1.72% over Fast R-CNN and 3.91% over the standard YOLOv5 algorithm. Furthermore, it demonstrates excellent real-time detection performance, meeting the demands of practical application scenarios. © 2024 SPIE.

关键词： Object recognition

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：