检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhan, Jingtao Xie, Xiaohui Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MSONoC: A Metasurface-assisted Hybrid Waveguide/FSO Network-on-Chip Architecture

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2024年

作者： Sun, Wei Li, Jingsi Guo, Pengxing He, Xiangyu Wang, Zimo Hu, Cong Liu, Weichen Hou, Weigang Guo, Lei School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Institute of Intelligent Communications and Network Security Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin541004 China School of Computer Science and Engineering Nanyang Technological University Singapore

Optical networks-on-chips (ONoCs) have emerged as the most promising solution for on-chip interconnection networks, offering distinct advantages such as high bandwidth and low latency. However, traditional wired-based ONoCs often suffer from a high average number of hops, leading to challenges such as increased insertion loss, crosstalk noise, and energy consumption. Therefore, this paper presents a novel ONoC structure known as the metasurface ONoC (MSONoC), which integrates wired waveguide and free-space optical (FSO) transmission with the assistance of metasurfaces. Specifically, this work encompasses the design of a passive metasurface structure tailored for ONoCs, a virtual network cluster partitioning method, an optical metasurface access points select strategy, and a shortest-path routing algorithm. Performance verification is conducted using a modified Noxim simulator. The simulation results demonstrate that the proposed MSONoC offers advantages over traditional NoCs, radio frequency (RF)-based hybrid wired/wireless NoCs, and wired-based ONoCs in terms of throughput, delay, energy consumption, and signal-to-noise ratio under both synthetic traffic and real traffic models. These improvements proves the effectiveness of the MSONoC architecture in optimizing network performance, making it a promising solution for high-performance, energy-efficient communication in on-chip networks. © 2017 IEEE.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Demand Response Scheme: Achieving Sustainability in Distributed data Processing

Demand Response Scheme: Achieving Sustainability in Distribu...

引用

IEEE International Conference on data science in Cyberspace (DSC)

作者： Xueying Zhai Yunfeng Peng Xiuping Guo Liang Zhang Wei Zhang School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Guizhou Key Laboratory of Electric Power Big Data Guizhou Institute of Technology Guizhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

The rapid development of Internet of Things (IoT) technology has driven the intelligent transformation of various industries, including manufacturing, agriculture, and healthcare, etc., significantly enhancing their management capabilities and decision-making efficiency. data analysis is crucial, serving as both the core technology of this transformation and a major driving force for advancing industry intelligence. However, the increasing volume of data has led to high energy consumption during data analysis, posing significant challenges to environmental and economic sustainability. Integrating renewable energy sources (RESs) is an effective way to reduce greenhouse gas emissions due to their low-carbon and renewable nature. Additionally, the spatiotemporal variability and complementarity of RES generation and grid electricity prices provide favorable conditions for distributed data processing. Therefore, a two-stage demand response scheme is proposed to reduce carbon emissions and electricity costs by prioritizing data processing in data centers (DCs) where RES is abundant or electricity prices are low, based on RES generation and electricity price signals. Simulation results show that the proposed scheme reduces 36.37% carbon emissions and 20.49% electricity costs compared to the benchmark algorithm, indicating its potential for both environmental and economic optimization.

关键词： Renewable energy sources Energy consumption Costs Electricity Simulation Carbon dioxide Spatiotemporal phenomena Internet of Things Sustainable development Optimization

来源：评论

学校读者我要写书评

暂无评论

Classical Machine Learning: Seventy Years of Algorithmic Learning Evolution

arXiv

引用

arXiv 2024年

作者： Ezugwu, Absalom E. Ho, Yuh-Shan Egwuche, Ojonukpe S. Ekundayo, Olufisayo S. Van Der Merwe, Annette Saha, Apu K. Pal, Jayanta Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 South Africa Trend Research Centre Asia University No. 500 Lioufeng Road Taichung41354 Taiwan School of Computer Science and Information Systems North-West University 11 Hoffman Street Potchefstroom2520 South Africa Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Department of IT Tripura University Suryamaninagar Tripura 799022 India

Machine learning (ML) has transformed numerous fields, but understanding its foundational research is crucial for its continued progress. This paper presents an overview of the major classical ML algorithms and examines the state-of-the-art publications, spanning twelve decades, through an extensive bibliometric analysis study. We analyzed a dataset of highly cited papers from prominent ML conferences and journals, employing techniques such as citation and keyword analyses to uncover key insights. The study further identifies the most influential papers and authors, reveals the evolving collaborative networks within the ML community, and pinpoints prevailing research themes and emerging areas of focus. Additionally, we examine the geographic distribution of highly cited publications, highlighting the leading countries in ML research. This study provides a comprehensive overview of the evolution of traditional learning algorithms, and their impacts, and discusses challenges and opportunities for future development, with a particular focus on the Global South. The findings from this paper offer valuable insights for both ML experts and the broader research community, enhancing understanding of the field's trajectory and its significant influence on recent advances in learning algorithms. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Blockchain Scheme for Tracing Manufacturing Processes and Trading Transactions

A Hybrid Blockchain Scheme for Tracing Manufacturing Process...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Ye Yuan Mingxing Yang Ruoting Xiong Yani Sun Xianchao Zhang Wei Ren HuBei Land Resources Vocational College China Gemological Institute China University of Geosciences Wuhan China School of Computing Science University of East Anglia UK Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Institute of Beihang University Kunming China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR Beijing China Ministry of Education Key Laboratory of Data Protection and Intelligent Management (Sichuan University) China School of Computer Science China University of Geosciences Wuhan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Blockchain can be envisioned as an enabling framework in terms of cryptography and distributed computing to construct trusted data records among un-trusted users. It can be applied in two typical scenarios - historical process provenance and transaction tracing, by immutably sequentialized blocks. In the former there exists no tokens; but in the latter token handover among accounts should be cryptographically guaranteed. In some situations, above two applications may be both required. E.g., in the manufacture of a jewel, processing flow by different operators should be recorded for quality guaranteeing, and in its trading stage, the ownership handover should be recorded for value confirmation. To tackle above two requirements, two chains are usually thus demanded. In this paper, we propose a single chain solution to avoid cross-chain burden, by a hybrid block structure. The process data can be imported from the legacy (non-anonymous) information processing system, and transaction data stems from anonymous payment demand for ownership handover. We formally describe and prove token handover model with cryptographical authenticity. We also propose several security enhancements in the design for shortening the length of the chain, and protecting the data confidentiality in the chain. Our design is general and not limited to single application. The experimental results and extensive analysis justified that the performance and security of our proposed scheme is efficient.

关键词： Distributed processing data privacy Manufacturing processes information processing Handover Throughput data structures Blockchains Delays Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction

arXiv

引用

arXiv 2023年

作者： Li, Qian Guo, Shu Ji, Cheng Peng, Xutan Cui, Shiyao Li, Jianxin Wang, Lihong School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China China The University of Sheffield South Yorkshire United Kingdom Institute of Information Engineering Chinese Academy of Sciences Beijing China

Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations among different modalities, failing to capture the truly helpful visual information and thus limiting relation extraction performance. In this paper, we propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects, so as to mine more helpful information for the task, termed as DGF-PT. We first propose a prompt-based autoregressive encoder, which builds the associations of intra-modal and inter-modal features related to the task, respectively by entity-oriented and object-oriented prefixes. To better integrate helpful visual information, we design a dual-gated fusion module to distinguish the importance of image/objects and further enrich text representations. In addition, a generative decoder is introduced with entity type restriction on relations, better filtering out candidates. Extensive experiments conducted on the benchmark dataset show that our approach achieves excellent performance compared to strong competitors, even in the few-shot situation. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

arXiv

引用

arXiv 2022年

作者： Liang, Siyuan Li, Longkang Fan, Yanbo Jia, Xiaojun Li, Jingzhi Wu, Baoyuan Cao, Xiaochun State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Data Science Secure Computing Lab of Big Data The Chinese University of Hong Kong Shenzhen China Tencent AI Lab Shenzhen China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen China

Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods aim to minimize the true positive rate, which often shows poor attack performance, as another sub-optimal bounding box may be detected around the attacked bounding box to be the new true positive one. To settle this challenge, we propose to minimize the true positive rate and maximize the false positive rate, which can encourage more false positive objects to block the generation of new true positive bounding boxes. It is modeled as a multi-objective optimization (MOP) problem, of which the generic algorithm can search the Pareto-optimal. However, our task has more than two million decision variables, leading to low searching efficiency. Thus, we extend the standard Genetic Algorithm with Random Subset selection and Divide-and-Conquer, called GARSDC, which significantly improves the efficiency. Moreover, to alleviate the sensitivity to population quality in generic algorithms, we generate a gradient-prior initial population, utilizing the transferability between different detectors with similar backbones. Compared with the state-of-art attack methods, GARSDC decreases by an average 12.0 in the mAP and queries by about 1000 times in extensive experiments. Our codes can be found at https://***/LiangSiyuan21/ GARSDC. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Security with AI: Developing Robust, Scalable Solutions for Threat Mitigation and data Protection in Cloud Platforms

Enhancing Cloud Security with AI: Developing Robust, Scalabl...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： AbuFaizur Rahman Abusalih Rahumath Ali K Saravanan B.Bala Abirami V.Samuthira Pandi Vijay Vasanth Aroulanandam S. Parthiban Enterprise Solution Architect Tekskills Inc. Princeton NJ USA Department of Information Technology R.M.K Engineering College Kavaraipettai Tamil Nadu India Department of Artificial Intelligence and Data Science Panimalar Engineering College Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Networking and Communications Department School of Computing SRM Institute of Science & Technology Kattankulathur Tamil Nadu India Department of CSE SIMATS Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Thandalam Chennai

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

As cloud computing continues to gain popularity, guaranteeing the security of cloud environments has become an issue of the utmost importance for businesses all over the world. With a particular emphasis on the development of solutions that are both robust and scalable for the purpose of threat mitigation and data protection, this study investigates the application of artificial intelligence (AI) in the process of improving cloud security. Security frameworks that are driven by artificial intelligence are able to proactively discover, evaluate, and respond to new threats in real time. This is accomplished by employing machine learning algorithms and advanced analytics. With the purpose of demonstrating the efficacy of various artificial intelligence approaches in tackling common vulnerabilities such as data breaches, unauthorized access, and distributed denial of service attacks, we investigate a variety of AI methodologies, such as anomaly detection, behavior analysis, and automated incident response. In addition, we analyze the significance of a multilayered security approach, which involves integrating artificial intelligence tools with conventional security measures in order to develop an all-encompassing defense plan. The purpose of this article is to present case studies that illustrate successful implementations of artificial intelligence-enhanced security solutions on cloud platforms. These case studies demonstrate the influence that these solutions have on increasing security posture and operational efficiency. Ultimately, the findings of this study highlight the significant role that artificial intelligence plays in the transformation of cloud security practices. This paves the way for cloud infrastructures that are more robust and secure in the face of changing cyber threats.

关键词： Cloud computing security Prevention and mitigation data protection data breach Real-time systems Vectors Security Artificial intelligence Faces Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

LSN:Long-Term Spatio-Temporal Network for Video Recognition

LSN:Long-Term Spatio-Temporal Network for Video Recognition

引用

作者： Zhenwei Wang Wei Dong Bingbing Zhang Jianxin Zhang School of Computer Science and Engineering Dalian Minzu University SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Institute of Machine Intelligence and Bio-Computing Dalian Minzu University School of Information and Communication Engineering Dalian University of Technology

Although recurrent neural networks(RNNs) are widely leveraged to process temporal or sequential data,they have attracted too little attention in current video action recognition ***,this work attempts to model the long-term spatio-temporal information of the video based on a variant of RNN,i.e.,higher-order ***,we propose a novel long-term spatio-temporal network(LSN) for solving this video task,the core of which integrates the newly constructed high-order ConvLSTM(HO-ConvLSTM) modules with traditional2D convolutional ***,each HO-Conv LSTM module consists of an accumulated temporary state(ATS) module as well as a standard Conv LSTM module,and several previous hidden states in the ATS module are accumulated to one temporary state that will enter the standard Conv LSTM to determine the output together with the current *** HO-Conv LSTM module can be inserted into different stages of the 2D convolutional neural network(CNN) in a plug-andplay manner,thus well characterizing the long-term temporal evolution at various spatial *** results on three commonly used video benchmarks demonstrate that the proposed LSN model can achieve competitive performance with the representative models.

关键词：

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：