检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zeng, Gangyan Zhang, Yuan Wei, Jin Yang, Dongbao Zhang, Peng Gao, Yiwen Qin, Xugong Zhou, Yu School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China Lenovo Research Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China TMCC College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9798400706868

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP's particular advantages in handling diverse forms of query text. The source code will be available at https://***/Gyann-z/FDP. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection

arXiv

引用

arXiv 2024年

作者： Song, Chengyu Ma, Linru Zheng, Jianming Liao, Jinzhi Kuang, Hongyu Yang, Lin Systems Engineering Institute Academy of Military Sciences Beijing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha China

Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, Large Language Models (LLMs) with strong common sense knowledge are emerging in the domain of ITD. Nevertheless, diverse activity types and overlong log files pose a significant challenge for LLMs to directly discern malicious ones within myriads of normal activities. Furthermore, the faithfulness hallucination issue from LLMs aggravates its application difficulty in ITD, as the generated conclusion may not align with user commands and activity context. In response to these challenges, we introduce Audit-LLM, a multi-agent log-based insider threat detection framework comprising three collaborative agents: (i) the Decomposer agent, breaking down the complex ITD task into manageable sub-tasks using Chain-of-Thought (COT) reasoning;(ii) the Tool Builder agent, creating reusable tools for sub-tasks to overcome context length limitations in LLMs;and (iii) the Executor agent, generating the final detection conclusion by invoking constructed tools. To enhance conclusion accuracy, we propose a pair-wise Evidence-based Multi-agent Debate (EMAD) mechanism, where two independent Executors iteratively refine their conclusions through reasoning exchange to reach a consensus. Comprehensive experiments conducted on three publicly available ITD datasets—CERT r4.2, CERT r5.2, and PicoDomain—demonstrate the superiority of our method over existing baselines and show that the proposed EMAD significantly improves the faithfulness of explanations generated by LLMs. 1 2 Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Computation Offloading for Multi-user Sequential Tasks in Heterogeneous Mobile Edge computing 17th

Computation Offloading for Multi-user Sequential Tasks in He...

引用

17th EAI International Conference on Collaborative computing: Networking, Applications, and Worksharing, CollaborateCom 2021

作者： Xu, Huanhuan Zhou, Jingya Gu, Fei School of Computer Science and Technology Soochow University Suzhou215006 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214125 China

ISBN: (纸本)9783030926342

Currently, many computation offloading studies in Mobile Edge computing (MEC) mainly focus on the multi-user and multi-task offloading, where the tasks are independent and inseparable. However, nowadays many mobile applications, such as Augmented Reality (AR) glasses, face recognition, etc., can be classified into sequential tasks. Dependencies among tasks and resource competition among multiple users in the heterogeneous edge environment make the offloading problem very challenging. In this paper, we propose a new multi-user sequential task (MUST) framework to address the above challenge. Specifically, we present a comprehensive analysis of the time cost of the task offloading process in the MUST framework and define the multi-user sequential task offloading problem. Moreover, we prove the problem is NP-hard and propose a reMUST algorithm based on regular expression to obtain the approximate optimal solution. Numerous experiments have shown that the proposed method is superior to existing alternatives in terms of cost and system scalability. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

High-performance optimization of SM4-GCM based on FPGA

High-performance optimization of SM4-GCM based on FPGA

引用

advanced computing and Endogenous Security, International Conference on

作者： Shun Sen Lv Bin Li Xiaojie Chen Qinglei Zhou School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Mathmatical Engineering and Advanced Computing Zhengzhou China Schoo of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665424509

SM4-GCM is an encryption algorithm with authentication function. The algorithm achieves the purpose of data security and information integrity. The SM4-GCM algorithm, implemented using traditional software methods, has low throughput and high resource consumption. In order to further improve the algorithm performance, this paper uses FPGA to optimize the SM4-GCM algorithm to achieve full-pipeline parallel acceleration. Firstly, the SM4 module is optimized using pipelining techniques. Then, the GHASH module is optimized using the Karatsuba algorithm and fast reduction. Finally, a loosely coupled architecture is used to connect various modules with asynchronous FIFOs, which improves the resource utilization and throughput of the FPGA circuit. The experimental results show that the throughput of the optimized SM4-GCM algorithm reaches 28.8 Gbps. It is better than other schemes, has a higher throughput, and meets the actual application requirements.

关键词： Power demand Software algorithms Computer architecture Throughput Software Encryption Resource management

来源：评论

学校读者我要写书评

暂无评论

Implementation of Multi-compartment Neuron Model with Synaptic Plasticity Using FPGA 21

Implementation of Multi-compartment Neuron Model with Synapt...

引用

21st IEEE International Conference on Communication Technology, ICCT 2021

作者： DIng, Yiwen Fu, Wenlong Cao, Lihong Communication University of China State Key Laboratory of Media Convergence and Communication Beijing China Neuroscience and Intelligent Media Institute Communication University of China Beijing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China

ISBN: (纸本)9781665432061

Computational neuroscience is interdisciplinary and plays an essential role in facilitating the development of cognitive neuroscience and Artificial General Intelligence (AGI). To explore the computational efficiency of Spiking Neural Network (SNN) on a computational hardware platform, we deploy SNN on the Xilinx Zynq7 Zedboard Field Programmable Gate Array (FPGA). Specifically, we use multi-compartmental Hodgkin-Huxley (HH) neuron model to construct neural circuits via C++ code and adopt a biologically plausible calcium concentration-based plasticity model as the learning rule of SNN. Our experimental results show that the FPGA platform can support parallel computation of the multi-compartment HH model with synaptic plasticity. Compared to other methods, FPGA-based computing has a significant speed advantage, suggesting that FPGA can be a good choice for implementing brain-inspired computation. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Human Body Reconstruction Algorithm of Monocular Image 5

Research on 3D Human Body Reconstruction Algorithm of Monocu...

引用

5th Asian Conference on Artificial Intelligence Technology, ACAIT 2021

作者： Liang, Zijian Liang, Huan Fu, Wenlong Neuroscience and Intelligent Media Institute Communication University of China Beijing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China

ISBN: (纸本)9781665426305

The three-dimensional human body feature parameters extracted by the neural network method are coupled in the high-dimensional feature space. The fully connected network processes the three-dimensional human pose and shape feature information synchronously, which cannot handle multifactor features well, which makes the model perform poorly. To solve this problem, on the basis of the benchmark network, a decoupling model is added, which processes the three-dimensional human pose and shape information separately, and finally integrates the features through the bi-linear transformation method. Through experimental verification, the algorithm effectively reduces the reconstruction error, and the improved algorithm performs better. © 2021 IEEE.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

A Survey on Neural Machine Translation Applied to Sign Language Generation 3

A Survey on Neural Machine Translation Applied to Sign Langu...

引用

3rd International Conference on Applied Machine Learning, ICAML 2021

作者： Zhang, Yue Cao, Lihong State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China Neuroscience and Intelligent Media Institute Communication University of China Beijing100024 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214125 China

ISBN: (纸本)9781665421256

Sign languages are the primary medium of communication for the deaf and hearing-impaired community, and the number of human beings with hearing impairment is increasing at a rapid rate. There is a signifîcant communication barrier between the hearing-impaired and normal-hearing communities. One solution to this issue is to offload the effort of text imderstanding for the deaf and hearing-impaired community in the form of Sign Language Generation (SLG). In this paper, first of all, we systematically review the mainstream Neural Machine Translation (NMT)based SLG approaches. Specifically, according to their model architectures, we divide them into two categories: the Recurrent Neural Networks (RNNs)-based and Transformer-based models, and discuss their advantages and limitations. Next, we introduce the existing publicly available datasets and the data pre pros ses sing methods in the field of SLG. Then, we summarize the performance evaluation methods for NMT-based SLG models. Finally, we offer two possible future research directions for better development in the field of SLG. © 2021 IEEE

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Multikernel:Operating system solution to generalized functional safety

引用

Security and Safety 2023年第2期2卷 30-43页

作者： Yijing Song Huasheng Dai Jinhu Jiang Weihua Zhang School of Computer Science Fudan UniversityShanghai 200433China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214125China Institute of Big Data Fudan UniversityShanghai 200433China Parallel Processing Institute Fudan UniversityShanghai 200433China

With the trend of digitalization,intelligence,and networking sweeping the world,functional safety and cyber security are increasingly intertwined and overlapped,evolving into the issue of generalized functional *** system reliability technology and network defense technology cannot provide quantifiable design implementation theories and *** the cornerstone of software systems,operating systems in particular are in need of efficient safety *** DHR architecture is a mature and comprehensive solution,and it is necessary to implement an OS-level DHR architecture,for which the multi-kernel operating system is a good *** multi-kernel operating system takes the kernel as the processing scenario element and constructs redundancy,heterogeneity,and dynamism on the kernel,so it has the generalized robustness of the DHR *** article analyzes the significance and requirements of OS-level DHR architecture,and systematically explains how the multi-kernel operating system responds to the requirements of OS-level DHR architecture by analyzing the technical routes of multi-kernel operating systems and develops an operating system solution idea for the generalized functionally safety.

关键词： Metaverse New infrastructure Security base Highly trusted network Trusted identiry Trusted circulation of data

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence into Operating Systems: A Comprehensive Survey on Techniques, Applications, and Future Directions

arXiv

引用

arXiv 2024年

作者： Zhang, Yifan Zhao, Xinkui Li, Ziying Yin, Jianwei Zhang, Lufei Chen, Zuoning School of Software Technology Zhejiang University Zhejiang Ningbo315048 China College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310058 China State Key Laboratory of Mathematical Engineering and Advanced Computing Jiangsu Wuxi214125 China Chinese Academy of Engineering Beijing100088 China

In the era of the Internet of Everything, operating systems (OSs) face unprecedented challenges posed by an evolving application landscape and increasingly heterogeneous hardware ecosystems. This shift toward increasingly dynamic and unpredictable operational contexts presents significant challenges for both OS developers and users. Against this backdrop, the fusion of Artificial Intelligence (AI) with Operating Systems emerges as a critical frontier for innovation. This survey delves into the intricate interplay between AI and OSs, illustrating how existing OS mechanisms combined with AI significantly elevate the performance, security, and efficiency of modern operating systems. We investigate a range of AI methodologies applied to optimize core OS functionalities and clarify the correlation to related studies. Our analysis touches on the existing hurdles and prospective avenues in this interdisciplinary domain, underscoring the imperative for robust and seamless integration of AI capabilities into OS architectures. Through an examination of illustrative case studies and cutting-edge developments, we offer a thorough review of the current status of AI-OS integration, accentuating its pivotal role in steering the evolution of advanced computing paradigms. We also envision the promising prospects of Intelligent Operating Systems, debating how groundbreaking OS designs will usher in novel possibilities and highlight the central role that AI will assume in propelling these next-generation systems forward. This forward-thinking outlook illuminates the profound influence of AI on the foundational elements of computing, heralding the advent of a new epoch characterized by intelligent, self-adapting, and highly adaptive software ecosystems. Copyright © 2024, The Authors. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

ODCP: Optimizing Data Caching and Placement in Distributed File System Using Erasure Coding 17th

ODCP: Optimizing Data Caching and Placement in Distributed F...

引用

17th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2020

作者： Wu, Shuhan Li, Yunchun Yang, Hailong Luan, Zerong Li, Wei School of Computer Science and Engineering Beihang University Beijing100191 China College of Life Sciences and Bioengineering Beijing University of Technology Beijing100083 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214125 China

ISBN: (纸本)9783030794774

Many current distributed file systems use erasure-coding based data redundancy techniques to improve the reliability of data storage. Such techniques can significantly improve the effective storage utilization. However, there are several drawbacks to the above techniques. Firstly, they introduce non-negligible computation overhead for decoding. Secondly, traditional data caching and placement strategies become less effective in such cases. To solve the above drawbacks, this paper proposes a new data cache allocation mechanism based on simulated annealing and a new data placement strategy based on convex optimization, which effectively reduces data block transmission delay and decoding delay. We have implemented the proposed data placement strategy in the real-world distributed file system Alluxio, and evaluated the performance of our strategy. Experiment results show that our strategy can significantly reduce the file read delay compared to traditional data placement strategies. © 2021, IFIP International Federation for Information Processing.

关键词： Convex optimization

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：