检索结果-内蒙古大学图书馆

arXiv 2025年

作者： You, Zhichao Dong, Xuewen Cheng, Ke Mu, Xutong Fu, Jiaxuan Ma, Shiyang Qu, Qiang Shen, Yulong School of Computer Science & Technology Xidian University Shaanxi Key Laboratory of Network and System Security Xi’an China Shenzhen Institues of Advanced Technology Chinese Academy of Sciences China

Fine-tuning large language models (LLMs) raises privacy concerns due to the risk of exposing sensitive training data. Federated learning (FL) mitigates this risk by keeping training samples on local devices, but recent studies show that adversaries can still infer private information from model updates in FL. Additionally, LLM parameters are typically shared publicly during federated fine-tuning, while developers are often reluctant to disclose these parameters, posing further security challenges. Inspired by the above problems, we propose PriFFT, a privacy-preserving federated fine-tuning mechanism, to protect both the model updates and parameters. In PriFFT, clients and the server share model inputs and parameters by secret sharing, performing secure fine-tuning on shared values without accessing plaintext data. Due to considerable LLM parameters, privacy-preserving federated fine-tuning invokes complex secure calculations and requires substantial communication and computation resources. To optimize the efficiency of privacy-preserving federated fine-tuning of LLMs, we introduce function secret-sharing protocols for various operations, including reciprocal calculation, tensor products, natural exponentiation, softmax, hyperbolic tangent, and dropout. The proposed protocols achieve up to 4.02× speed improvement and reduce 7.19× communication overhead compared to the implementation based on existing secret sharing methods. Besides, PriFFT achieves a 2.23× speed improvement and reduces 4.08× communication overhead in privacy-preserving fine-tuning without accuracy drop compared to the existing secret sharing methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

Using Depth-Enhanced Spatial Transformation for Student Gaze...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Miao, Haonan Zhao, Peizheng Sun, Yuqi Nan, Fang Zhang, Xiaolong Wu, Yaqiang Tian, Feng School of Computer Science and Technology Xi'an Jiaotong University Xi'an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou215123 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798350368741

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the gaze cone to intersect with an incorrect object. This paper introduces a novel dual-view gaze target estimation method tailored for classroom settings, leveraging depth-enhanced spatial transformations. By formulating a depth-enhanced 2D space, our method uses depth-enhanced spatial transformation to accurately project students' gaze cones to the teacher-oriented image. Additionally, we collected a dataset named DVSGE, specifically for student gaze target estimation in dual-view classroom images. Experimental results demonstrate significant performance improvements of 9.8% in AUC and 19.9% in L2-Distance for our method, surpassing existing methods. © 2025 IEEE.

关键词： classroom depth-enhanced 2D space dual-view gaze target estimation spatial transformation

来源：评论

学校读者我要写书评

暂无评论

HiCoCS: High Concurrency Cross-Sharding on Permissioned Blockchains

引用

IEEE Transactions on Computers 2025年

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Lu, Di Zhang, Yushu Shen, Yulong Xidian University School of Computer Science and Technology China Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China Zhejiang Lab Zhejiang Hangzhou311121 China Shaanxi Key Laboratory of Network and System Security Xi’an710071 China Jiangxi University of Finance and Economics School of Computing Nanchang330013 China Jiangxi University of Finance and Economics Nanchang330013 China

As the foundation of the Web3 trust system, blockchain technology faces increasing demands for scalability. Sharding emerges as a promising solution, but it struggles to handle highly concurrent cross-shard transactions (CSTxs), primarily due to simultaneous ledger operations on the same account. Hyperledger Fabric, a permissioned blockchain, employs multi-version concurrency control for parallel processing. Existing solutions use channels and intermediaries to achieve cross-sharding in Hyperledger Fabric. However, the conflict problem caused by highly concurrent CSTxs has not been adequately resolved. To fill this gap, we propose HiCoCS, a high concurrency cross-shard scheme for permissioned blockchains. HiCoCS creates a unique virtual sub-broker for each CSTx by introducing a composite key structure, enabling conflict-free concurrent transaction processing while reducing resource overhead. The challenge lies in managing large numbers of composite keys and mitigating intermediary privacy risks. HiCoCS utilizes virtual sub-brokers to receive and process CSTxs concurrently while maintaining a transaction pool. Batch processing is employed to merge multiple CSTxs in the pool, improving efficiency. We explore composite key reuse to reduce the number of virtual sub-brokers and lower system overhead. Privacy preservation is enhanced using homomorphic encryption. Evaluations show that HiCoCS improves cross-shard transaction throughput by 3.5-20.2 times compared to the baselines. © 1968-2012 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Mamba-based spatial-spectral fusion network for hyperspectral unmixing

引用

Journal of King Saud University - Computer and Information Sciences 2025年第3期37卷 1-24页

作者： Gan, Yuquan Wei, Jingtao Xu, Mengmeng School of Telecommunication and Information Engineering Xi’an University of Posts & Telecommunications Xi’an 710121 China Xi’ an Key Laboratory of Image Processing Technology and Applications for Public Security Xi’an University of Posts & Telecommunications Xi’an 710121 China Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications Xi’an 710121 China

Hyperspectral unmixing (HU) is a critical technique in hyperspectral image (HSI) analysis, aimed at decomposing mixed pixels into a set of spectral signatures (endmembers) and their corresponding abundance values. Recently, the Mamba model has gained significant attention for its exceptional performance in natural language processing and has been extended to vision research. With its strong capability for long-range modeling and linear computational complexity, Mamba demonstrates substantial potential in hyperspectral image processing. However, due to the intrinsic requirement of HU tasks for comprehensive integration of spatial and spectral information, challenges remain in effectively leveraging Mamba for hyperspectral representation. To address these issues, we propose a novel Mamba-based spatial-spectral fusion network for hyperspectral unmixing (Mamba-SSFN). This network introduces a fusion mechanism to jointly learn spectral and spatial feature representations, enabling more efficient extraction of critical HSI features. Specifically, in the spatial feature extraction module, we integrate multi-scale analysis with the Mamba module, enabling the capturing of both local and global spatial information. In the spectral feature extraction module, the Mamba module is employed in a grouped manner to process spectral vectors, exploring the correlations among different spectral groups. Finally, an effective fusion mechanism is implemented to integrate spatial and spectral *** results demonstrate that Mamba-SSFN achieves outstanding performance across multiple benchmark datasets, significantly surpassing existing state-of-the-art methods in terms of unmixing accuracy, model robustness, and computational efficiency. © The Author(s) 2025.

关键词： Fusion mechanism Hyperspectral image Hyperspectral unmixing Mamba model Multi-Scale analysis

来源：评论

学校读者我要写书评

暂无评论

Source-free Domain Adaptation with Multiple Alignment for Efficient Image Retrieval

Source-free Domain Adaptation with Multiple Alignment for Ef...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jinghui Ni Hui Cui Lihai Zhao Fengling Li Xiaohui Han Lijuan Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Quan Cheng Laboratory Shandong Open University University of Technology Sydney

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Domain adaptation techniques help models generalize to target domains by addressing domain discrepancies between the source and target domain data distributions. These techniques are particularly valuable for cross-domain hashing retrieval, as they reduce training costs while maintaining high retrieval efficiency. However, existing unsupervised domain adaptative hashing methods often require access to both source and target domain data, which may raise privacy concerns regarding source domain data. To address these concerns, restricting access to source domain data is crucial, but this restriction also makes the alignment process between domains more challenging. In this paper, we propose a Source-free Domain Adaptive Hashing with Multiple Alignment (SFDAH-MA) approach for image retrieval. SFDAH-MA integrates model structure alignment, class moment alignment, and semantic relationship alignment to maximize inter-domain knowledge transfer. This comprehensive alignment strategy not only enhances retrieval performance across domains but also minimizes reliance on source domain data, thereby supporting data privacy protection. Extensive experiments show that SFDAH-MA achieves state-of-the-art performance in source-free settings and achieves comparable results to existing unsupervised domain adaptive hashing methods under conventional settings. The source codes of our method are available at: https://***/Nikphyc/SFDAH-MA.

关键词： Training Data privacy Adaptation models Source coding Semantics Image retrieval Signal processing Protection Speech processing Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

WiViPose: A Video-aided Wi-Fi Framework for Environment-Independent 3D Human Pose Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Lei Ning, Haoran Tang, Jiaxin Chen, Zhenxiang Zhong, Yaping Han, Yahong Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Advanced Network Technology and Application Tianjin300050 China Key Laboratory of Computing Power Network and Information Security Ministry of Education China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing the School of Information Science and Engineering Jinan250022 China Wuhan Sports University Sports Big-data Research Center Wuhan430079 China Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Machine Learning Tianjin300350 China

The inherent complexity of Wi-Fi signals makes video-aided Wi-Fi 3D pose estimation difficult. The challenges include the limited generalizability of the task across diverse environments, its significant signal heterogeneity, and its inadequate ability to analyze local and geometric information. To overcome these challenges, we introduce WiViPose, a video-aided Wi-Fi framework for 3D pose estimation, which attains enhanced cross-environment generalization through cross-layer optimization. Bilinear temporal-spectral fusion (BTSF) is initially used to fuse the time-domain and frequency-domain features derived from Wi-Fi. Video features are derived from a multiresolution convolutional pose machine and enhanced by local self-attention. Cross-modality data fusion is facilitated through an attention-based transformer, with the process further refined under a supervisory mechanism. WiViPose demonstrates effectiveness by achieving an average percentage of correct keypoints (PCK)@50 of 91.01% across three typical indoor environments. © 2025 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

PPEC: A Privacy-Preserving, Cost-Effective Incremental Density Peak Clustering Analysis on Encrypted Outsourced Data

引用

IEEE Transactions on Cloud computing 2025年

作者： Yang, Haomiao Ding, Zikang Lu, Ruiheng Xiang, Kunlan Li, Hongwei Wu, Dakui University of Electronic Science and Technology of China Chengdu611731 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250353 China Shanghai University Shanghai200444 China

Call detail records (CDRs) provide valuable insights into user behavior, which are instrumental for telecom companies in optimizing network coverage and service quality. However, while cloud computing facilitates clustering analysis on a vast scale of CDR data, it introduces privacy risks. The challenge lies in striking a balance between efficiency, security, and cost-effectiveness in privacy-preserving algorithms. To tackle this issue, we propose a privacy-preserving and cost-effective incremental density peak clustering scheme. Our approach leverages homomorphic encryption and order-preserving encryption to enable direct computations and clustering on encrypted data. Moreover, it employs reaching definition analysis to optimize the execution flow of static tasks, pinpointing the optimal junctures for transitioning between the two types of encryption to reduce communication overhead. Furthermore, our scheme utilizes a game theory-based verification strategy to ascertain the accuracy of the results. This methodology can be effectively deployed on the Ethereum blockchain via smart contracts. A comprehensive security analysis confirms that our scheme upholds both privacy and data integrity. Experimental evaluations substantiate the clustering accuracy, communication load, and computational efficiency of our scheme, thereby validating its viability in real-world applications. © 2025 IEEE. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction

arXiv

引用

arXiv 2025年

作者： Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Shaanxi Xi’an China

Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4% in event detection and 6.1% in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9% improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Based on 3d Pdc with Swin Transformer

SSRN

引用

SSRN 2025年

作者： Fan, Lin Ding, Xiaojia Wang, Zhongmin Wang, Hai Zhang, Rong School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China The School of Information Science and Technology Northwest University Shaanxi Xi’an710121 China

3D medical image segmentation is vital for disease diagnosis and effective treatment strategies. Despite the advancements in Convolutional Neural networks (CNN), their fixed receptive fields constrain global context modeling, leading to suboptimal performance, particularly with complex shapes and multi-scale variations. Transformer enhances the global modeling capability through self-attention mechanism. However, challenges persist in capturing fine-grained local features and extracting edge features. To overcome these issues, In this study, a dual-path encoder is proposed, which consists of a 3D PDC and a Swin Transformer and is combined with a CNN for the decoder. The 3D PDC module extracts local features by calculating the differences between neighboring pixels. To improve the ability of capturing edge structures, three 3D PDC variants (3D CPDC, 3D APDC, and 3D RPDC) are proposed to optimize the processing ability of complex edges, multi-directional edges, and multi-scale structures, respectively. After performance evaluation, the selected CARV combinations (3D CPDC, 3D APDC, 3D RPDC, and 3D ordinary convolution) achieve a compromise between high segmentation accuracy and low computational cost. The Swin Transformer encoder captures global context using a hierarchical shift-window mechanism, while the CNN decoder fuses features progressively to produce precise pixel-level segmentation. The proposed method exceeds the performance of existing state-of-the-art techniques, as shown by experiments conducted on the BTCV, FLARE21, and AMOS22 datasets. © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Digital Human Techniques for Education Reform 24

Digital Human Techniques for Education Reform

引用

7th International Conference on Educational technology Management, ICETM 2024

作者： Guo, Peirong Zhang, Qi Tian, Chunwei Xue, Wanli Feng, Xiaocheng School of Software Northwestern Polytechnical University Shaanxi Xi’an China School of Economics and Management Harbin Institute of Technology at Weihai Shandong Weihai China Shenzhen Research Institute of Northwestern Polytechnical University Northwestern Polytechnical University Guangdong Shenzhen China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Heilongjiang Harbin China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Guangdong Shenzhen China

ISBN: (纸本)9798400717468

The rapid evolution of artificial intelligence, big data, and generative AI models has ushered in significant transformations across various sectors, including education. Digital Human Technique, an innovative technology grounded in advanced computer science and artificial intelligence, is reshaping educational paradigms by enabling virtual humans to simulate human behavior, express emotions, and interact with users. This paper explores the application of Digital Human Technique in education reform, focusing on creating immersive, intelligent classroom experiences that foster meaningful interactions between teachers and students. We define Digital Human Technique and delve into its key technical components such as character modeling and rendering, natural language processing, computer vision, and augmented reality technologies. Our methodology involves analyzing the role of educational digital humans created through these technologies, assessing their impact on educational processes, and examining various application scenarios in educational reform. Results indicate that Digital Human Technique significantly enhances the learning experience by enabling personalized teaching, increasing engagement, and fostering emotional connections. Educational digital humans serve as virtual teachers, interactive learning aids, and facilitators of emotional interaction, effectively addressing the challenges of traditional educational methods. They also promote a deeper understanding of complex concepts through simulated environments and interactive digital content. © 2024 Copyright held by the owner/author(s).

关键词： Digital elevation model

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：