检索结果-内蒙古大学图书馆

IEEE International Conference on Big Knowledge (ICBK)

作者： Menghao Guo Jinling Jiang Fan Wu Shanxin Sun Chen Zhang Wenhui Li Zeyi Sun Guangyong Chen Xindong Wu Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

This paper presents a Scientific Literature Management Platform (SLMP, demo link 1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM 2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge.

关键词： Training Large language models Knowledge graphs Information retrieval data models Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal GNN-Based Cell-Free Massive MIMO Network with Maximal Benefit-Cost Ratio

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Jiang, Jing Li, Yanni Ye, Yinghui Feng, Dan Zhang, Jiayi Sutthiphan, Worakrin Niyato, Dusit Xi'an Uni versity of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Xi'an710121 China Beijing Jiaotong University Frontiers Science Center for Smart High-Speed Railway System Beijing100044 China National Telecommunication Public Company Mobile System Development Department Bangkok10210 Thailand Nanyang Technological University College of Computing and Data Science Singapore

Due to the network's rapid expansion, mobile networks bear extra high deployment costs. Being a key enabler of 6th generation (6G) mobile networks, it is crucial that cell-free massive MIMO (CF mMIMO) networks achieve green and cost-effective development. In this correspondence, we propose spatio-temporal graph neural networks (STGNN)-based CF mMIMO networks with a maximal benefit-cost ratio. First, we formulate a new coverage cost metric named benefit-cost ratio (BCR), which can evaluate the deployment cost while fulfilling various traffic requirements. Next, CF mMIMO networks are modeled as a spatio-temporal graph to utilize STGNN to extract the spatial-temporal properties of traffic demands. Finally, STGNN optimizes the number and location of access points (APs) based on the maximal BCR criterion so that the CF mMIMO networks can achieve on-demand service capability with minimum deployment cost. Numerical results demonstrate that the proposed algorithm can significantly reduce the deployment cost while providing on-demand and high-quality mobile service. © 1967-2012 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Pyroelectric Response in Quenched BNT-Based Lead-Free Ferroelectrics for Uncooled Infrared Detection

引用

Advanced Functional Materials 2025年

作者： Shen, Meng Zhang, Xian Cen, Fangjie Zhang, Qingfeng Zhang, Haibo Zhang, Guangzu Jiang, Shenglin Chen, Yong Hu, Yongming Yao, Kui Hubei Key Laboratory of Micro-Nanoelectronic Materials and Devices Key Laboratory of Intelligent Sensing System and Security of Ministry of Education and School of Microelectronics Hubei University Wuhan430062 China School of Integrated Circuits Engineering Research Center for Functional Ceramics MOE and Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan430074 China Ministry of Education Key Laboratory of Green Preparation and Application for Functional Materials Hubei Key Laboratory of Micro-Nanoelectronic Materials and Devices Hubei Key Laboratory of Polymer Materials School of Materials Science & Engineering Hubei University Wuhan430062 China School of Materials Science and Engineering State Key Laboratory of Material Processing and Die & Mould Technology Huazhong University of Science and Technology Wuhan430074 China Singapore138634 Singapore

Excellent pyroelectric performance in environmentally friendly lead-free ferroelectrics is highly demanded for uncooled infrared detector. However, the trade-off between room temperature pyroelectric coefficient (proom) and depolarization temperature (Td) remains a major challenge of lead-free ferroelectrics for their device applications. Herein, a superior proom of 13.8 × 10−4 C m−2 K−1 with high Td of 155 °C is achieved in quenched BNT-Fe/Mn-NBT sample. Oxygen vacancy engineering is proposed to solve the constraint between proom and Td in BNT-based ceramics. The local A/B site displacement and oxygen vacancies are constructed in the BNT-Fe/Mn-NBT perovskite structure by quenching treatment, resulting in larger lattice distortion and superior proom. Meanwhile, defect-induced inhomogeneous random field compensates the ferroelectric depolarization field and down-shifts the free energy well, maintaining high Td. The resulting pyroelectric infrared detector made from the high-performance quenched BNT-Fe/Mn-NBT generates the voltage responsivity of 5906 V W−1 and specific detection rate of 1.8 × 108 cm Hz1/2 W−1, which is comparable to the commercial RD-624 type PZT-based pyroelectric infrared detector. © 2025 Wiley-VCH GmbH.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Neural Network Based Preselection for Expensive Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural Network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Lightweight Cross-Chain Transaction Scheme Based on Proxy Re-signature 23

Decentralized and Lightweight Cross-Chain Transaction Scheme...

引用

23rd IEEE International Conference on Trust, security and Privacy in Computing and Communications, TrustCom 2024

作者： Zou, Huiying Duan, Jia Liu, Xi Ren, Wei Li, Tao Zheng, Xianghan Choo, Kim-Kwang Raymond Hunan Engineering Research Center of Geographic Information Security and Application The Third Surveying and Mapping Institute of Hunan Province Hunan China China University of Geosciences School of Computer Science Wuhan China Sichuan University Ministry of Education Key Laboratory of Data Protection and Intelligent Management China Casm State Key Laboratory of Geo-Information Engineering Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of Mnr Beijing China Fuzhou University College of Computer and Big Data China Sanya College School of Information and Intelligent Engineering China University of Texas at San Antonio Department of Information Systems and Cyber Security San Antonio United States

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach's security. © 2024 IEEE.

关键词： blockchain transaction cross-chain technology notary schemes proxy re-signature

来源：评论

学校读者我要写书评

暂无评论

A dynamic multi-objective evolutionary algorithm based on Niche prediction strategy

引用

Applied Soft Computing 2023年 142卷

作者： Zheng, Jinhua Zhang, Bo Zou, Juan Yang, Shengxiang Hu, Yaru Hunan Engineering Research Center of Intelligent System Optimization and Security Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Xiangtan University Hunan Province Xiangtan411105 China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

In reality, many multi-objective optimization problems are dynamic. The Pareto optimal front (PF) or Pareto optimal solution (PS) of these dynamic multi-objective problems (DMOPs) changes as the environment change. Therefore, solving such problems requires an optimization algorithm that can quickly track the PF or PS after an environment change. Prediction-based response mechanism is a common method used to deal with environmental changes, which is commonly known as center point-based prediction. However, if the predicted direction of the center point is inaccurate, the predicted population will be biased towards one side. In this paper, we propose a niche prediction strategy based on center and boundary points (PCPB) to solve the dynamic multi-objective optimization problems, which consists of three steps. After environmental changes are detected, the first step is to divide the niche, dividing different individuals in the PS into different niche populations. The second step is to independently predict different niches, and select individuals with good convergence and distribution in the niche to predict the individuals that will produce the next generation. Finally, some different individuals are randomly generated in the next possible PS area to ensure the diversity of the population. To verify whether our proposed strategy is effective and competitive, PCPB was compared with five state-of-the-art strategies. The experimental results show that PCPB performed competitively in solving dynamic multi-objective optimization problems, which proves that our algorithm has good competitiveness. © 2023 Elsevier B.V.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China School of Information and Communication Technology Griffith University Australia University of Technology Sydney Australia RMIT University Australia

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: SPONGE for triggering widespread misidentifications and BLINDING for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (∼10%-60% absolute and ∼2-7× relative) in attack efficacy over state-of-the-art attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Empirical Study on Semantic Versioning in Golang Ecosystem

A Large-Scale Empirical Study on Semantic Versioning in Gola...

引用

IEEE International Conference on Automated Software Engineering (ASE)

作者： Wenke Li Feng Wu Cai Fu Fan Zhou School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Platform and Content Group Tencent Technology (Shenzhen) Co.Ltd Shenzhen China

Third-party libraries (TPLs) have become an essential component of software, accelerating development and reducing maintenance costs. However, breaking changes often occur during the upgrades of TPLs and prevent client programs from moving forward. Semantic versioning (SemVer) has been applied to standardize the versions of releases according to compatibility, but not all releases follow SemVer compliance. Lots of work focuses on SemVer compliance in ecosystems such as Java and JavaScript beyond Golang (Go for short). Due to the lack of tools to detect breaking changes and dataset for Go, developers of TPLs do not know if breaking changes occur and affect client programs, and developers of client programs may hesitate to upgrade dependencies in terms of breaking changes. To bridge this gap, we conduct the first large-scale empirical study in the Go ecosystem to study SemVer compliance in terms of breaking changes and their impact. In detail, we propose GoSVI (Go Semantic Versioning Insight) to detect breaking changes and analyze their impact by resolving identifiers in client programs and comparing their types with breaking changes. Moreover, we collect the first large-scale Go dataset with a dependency graph from GitHub, including 124K TPLs and 532K client programs. Based on the dataset, our results show that 86.3% of library upgrades follow SemVer compliance and 28.6% of no-major upgrades introduce breaking changes. Furthermore, the tendency to comply with SemVer has improved over time from 63.7% in 2018/09 to 92.2% in 2023/03. Finally, we find 33.3% of downstream client programs may be affected by breaking changes. These findings provide developers and users of TPLs with valuable insights to help make decisions related to SemVer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension 39

Hierarchical Alignment-enhanced Adaptive Grounding Network f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yaxian Ding, Henghui He, Shuting Jiang, Xudong Wei, Bifan Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University China Institute of Big Data Fudan University China Shanghai University of Finance and Economics China Nanyang Technological University Singapore School of Continuing Education Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China

ISBN: (纸本)157735897X

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Modal analysis

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：