检索结果-内蒙古大学图书馆

44th ACM/IEEE International Conference on software Engineering, ICSE 2024

作者： Pan, Zhiyuan Hu, Xing Xia, Xin Zhan, Xian Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Huawei Software Engineering Application Technology Lab Hangzhou China The Hong Kong Polytechnic University Hong Kong School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400702174

The number of vulnerabilities reported in open source software has increased substantially in recent years. Security patches provide the necessary measures to protect software from attacks and vulnerabilities. In practice, it is difficult to identify whether patches have been integrated into software, especially if we only have binary files. Therefore, the ability to test whether a patch is applied to the target binary, a.k.a. patch presence test, is crucial for practitioners. However, it is challenging to obtain accurate semantic information from patches, which could lead to incorrect results. In this paper, we propose a new patch presence test framework named Ppt4j (Patch Presence Test forJava Binaries). Ppt4j is designed for open-source Java libraries. It takes Java binaries (i.e. bytecode files) as input, extracts semantic information from patches, and uses feature-based techniques to identify patch lines in the binaries. To evaluate the effectiveness of our proposed approach Ppt4j, we construct a dataset with binaries that include 110 vulnerabilities. The results show that Ppt4j achieves an F1 score of 98.5% with reasonable efficiency, improving the baseline by 14.2%. Furthermore, we conduct an in-the-wild evaluation of Ppt4j on JetBrains IntelliJ IDEA. The results suggest that a third-party library included in the software is not patched for two CVEs, and we have reported this potential security problem to the vendor. © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A review of video-based human activity recognition: theory, methods and applications

引用

Multimedia Tools and Applications 2025年第17期84卷 18499-18545页

作者： Bukht, Tanvir Fatima Naik Rahman, Hameedur Shaheen, Momina Algarni, Asaad Almujally, Nouf Abdullah Jalal, Ahmad Faculty of Computing and AI Air University E-9 Islamabad Pakistan Department of Computing School of Arts Humanities and Social Sciences University of Roehampton London UK SW15 5PJ London United Kingdom Department of Computer Sciences Faculty of Computing and Information Technology Northern Border University Rafha91911 Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Video-based human activity recognition (HAR) is an important task in many fields, such as healthcare monitoring, video surveillance, and sports analysis. This review paper aims to give an in-depth look at the current state of the art in HAR from 2018 to 2024. This will include a discussion of the different methods and models used for extracting, representing, and classifying human actions from video, as well as the challenges and limits of this field. The paper will also discuss recent improvements and plans for making HAR systems more accurate and useful. Even though there has been a lot of progress, a few knowledge gaps still need to be filled to make recognition more accurate and efficient. The purpose of this review paper is to offer scholars and professionals an overview of the theory, methods, and applications of HAR in videos. Through a critical analysis of the extant literature, this paper seeks to identify prospective avenues for future research and contribute towards advancing HAR systems that are more precise and efficient. By showing the different ways that HAR can be used, the paper shows how important this field is in many different areas. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Collaborative Fair-is-Better Filtering for Implicit Feedback 28th

Collaborative Fair-is-Better Filtering for Implicit Feedback

引用

28th International Conference on Knowledge Based and Intelligent information and Engineering systems, KES 2024

作者： Dong, Hoang V. Nguyen, Huu-Quang Nguyen, Hoang D. Le, Duc-Trong School of Computing and Information Systems Singapore Management University Singapore University of Engineering and Technology Vietnam National University Hanoi Viet Nam University College Cork Cork Ireland

With the wide adoption of recommender systems, fairness has increasingly become a critical topic in many applications, such as e-commerce, job search, and online entertainment. Collaborative filtering is susceptible to unfair recommendations for users from sensitive groups due to the non-negligible presence of biases. Whereas recent work mostly concerned fairness with the explicit ratings, we propose fairness-awareness recommendation models, referred to as CFBF, for implicit feedback (e.g., clicks, views, or purchases), which are ubiquitous in today's context. This paper considers sensitive attributes, such as gender and age, in both disjoined and combined manners to investigate the models' unfairness. We discuss several fairness metrics for implicit feedback recommendations based on Spearman's rank correlation and Kendal Tau. Comprehensive experiments on Movielens and LastFM show that CFBF significantly improves user groups' fairness with comparable and even better ranking performance. © 2024 The Authors.

关键词： Collaborative filtering fairness implicit feedback

来源：评论

学校读者我要写书评

暂无评论

Visual-text cross alignment: refining the similarity score in vision-language models 24

Visual-text cross alignment: refining the similarity score i...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jinhao Li Haopeng Li Sarah M. Erfani Lei Feng James Bailey Feng Liu School of Computing and Information Systems University of Melbourne Australia Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

It has recently been discovered that using a pretrained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting technique, designed to identify local visual areas within the query image. The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM. To determine how well a query image aligns with each category, we develop a score function based on the weighted similarities in this matrix. Extensive experiments demonstrate that our method significantly improves zero-shot performance across various datasets, achieving results that are even comparable to few-shot learning methods. The code is available at ***/tmlr-group/WCA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel deep domain-adversarial method based on DRN-DATL for rolling bearing 43

A novel deep domain-adversarial method based on DRN-DATL for...

引用

43rd Chinese Control Conference, CCC 2024

作者： Li, Zhuorui Wang, Xiaodong Ma, Bao Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming650500 China

ISBN: (纸本)9789887581581

In recent years, a variety of rolling bearing fault diagnosis methods based on deep learning has become an emerging research orientation. However, there is still a gap between the existing diagnostic model and the practical application, i.e., 1) due to the variability of working conditions, the domain shift problem between source domain and the target domain have led to the obvious degradation of the diagnostic performance. 2) It is time-consuming and expensive to label a mass of monitoring data in practical situation. To address this problem, a domain-adversarial transfer learning method based on deep residual network (DRN-DATL) for rolling bearing fault diagnosis is proposed. Firstly, DRN is designed to extract features from raw vibration signal, which can avoid gradient problems. Then, the APReLU activation function is adopted to improved diagnostic accuracy under different working conditions. Meanwhile, domain-adversarial training is utilized to minimize distribution differences between source domain and target domain. Finally, seven comparison methods are selected for systematic analysis, and the results show that the proposed method can effectively improve the overall performance of the diagnosis model, which has achieved higher classification accuracy. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Network Efficiency in Clustered Tree Topology through PSO Optimization in IEEE 802.15.4-DSME based IoT Networks 18

Improving Network Efficiency in Clustered Tree Topology thro...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications systems, ANTS 2024

作者： Anand, Sonali Choudhury, Nikumani Ojha, Tamoghna Hazarika, Anakhi Dave, Jay Birla Institute of Technology & Science Dept. of Computer Science & Information Systems Pilani Hyderabad India Indian Institute of Technology Indian School of Mines Dept. of Mathematics & Computing Dhanbad India

ISBN: (纸本)9798350391725

The IEEE 802.15.4 standard is designed for low-rate wireless personal area networks (LR-WPANs). Deterministic and Synchronous Multi-channel Extension (DSME) is one of the key Medium Access Control (MAC) modes of the IEEE 802.15.4 standard that was introduced to address the need for higher reliability, lower latency, and better scalability in network communication in Internet of Things (IoT) applications. However, in dynamic network conditions (topology and channel traffic), the network suffers from several limitations, such as low packet delivery ratio, high latency and packet collisions, and finally, higher power consumption. This is because of sub-optimal parameter settings. The standard does not define any mechanism to adapt the parameters based on network conditions. In this paper, we propose a mechanism to adapt/fine-tune the network parameters DSME along with the optimization of QoS using an algorithm based on Particle Swarm Optimization(PSO) for dense and dynamic DSME-based IoT networks. Through simulations, the proposed mechanisms' performance is analyzed in terms of energy efficiency, transmission overhead, throughput, and latency and is shown to outperform the existing DSME MAC scheme. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

ChatGPT, Let Us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions

ChatGPT, Let Us Chat Sign Language: Experiments, Architectur...

引用

2023 International Symposium on Networks, Computers and Communications, ISNCC 2023

作者： Shahin, Nada Ismail, Leila Lab UAE University Department of CS and Software Engineering Al-Ain United Arab Emirates School of Computing and Information Systems CLOUDS Lab The University of Melbourne Melbourne Australia

ISBN: (纸本)9798350335590

ChatGPT is a language model based on Generative AI. Existing research work on ChatGPT focused on its use in various domains. However, its potential for Sign Language Translation (SLT) is yet to be explored. This paper addresses this void. Therefore, we present GPT's evolution aiming a retrospective analysis of the improvements to its architecture for SLT. We explore ChatGPT's capabilities in translating different sign languages in paving the way to better accessibility for deaf and hard-of-hearing community. Our experimental results indicate that ChatGPT can accurately translate from English to American (ASL), Australian (AUSLAN), and British (BSL) sign languages and from Arabic Sign Language (ArSL) to English with only one prompt iteration. However, the model failed to translate from Arabic to ArSL and ASL, AUSLAN, and BSL to Arabic. Consequently, we present challenges and derive insights for future research directions. © 2023 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Social Enterprise Logic and the Sustainability of Community Networks in Sub-Sahara Africa: Lessons from the Zaria Community Network in Nigeria 28

Social Enterprise Logic and the Sustainability of Community ...

引用

28th Americas Conference on information systems, AMCIS 2022

作者： Tata, Auwal Alhassan Avemaria Utulu, Samuel C. Department of Information Systems School of Information Technology and Computing American University of Nigeria Adamawa State Yola Nigeria

ISBN: (纸本)9781958200001

Abstract: There are conflicting views about how social enterprise logic impacts community networks' sustainability (CNs). Some authors believe that running with the social enterprise logic spells doom on CNs. Conversely, some believe that it does not necessarily spell doom on CNs. However, CNs, particularly those implemented in sub-Saharan Africa, cannot be implemented with an alternative logic, such as the for-profit business logic. Consequently, there is a need to develop a framework for making CNs sustainable, although they run with the social enterprise logic. This research develops a framework that will enable those involved in CN implementation in sub-Saharan Africa to understand how to instil sustainability factors into every stage of CN implementation. The study uses the Zaria Community Network (ZCN), Zaria, Nigeria, as a case study and adopts the inductive approach. The study data were derived from the chat messages from a WhatsApp group used as a platform for communication by those implementing the ZCN and from secondary sources. The study findings revealed that sustainable participation was a primary factor that comes to bear in the sustainability of the ZCN. It also revealed how sustainable participation influences sustainable infrastructure, sustainable stakeholders' support, and sustainable funding. We conclude that the framework helps implement sustainable CNs in sub-Saharan Africa and other regions with similar socio-technical similarities. © 2022 28th Americas Conference on information systems, AMCIS 2022. All Rights Reserved.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Automatic Deployment to Kubernetes Cluster by Applying a New Learning Tool and Learning Processes 10

Automatic Deployment to Kubernetes Cluster by Applying a New...

引用

10th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Golis, Tomáš Dakić, Pavle Vranić, Valentino Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava842 16 4 Slovakia Faculty of Informatics and Computing Singidunum University Danijelova 32 Belgrade Serbia

The rapid growth and widespread adoption of containerization technologies, such as Docker, and the increasing popularity of Kubernetes as a container orchestration platform have significantly shaped the landscape of modern software development and deployment. Containers have created a paradigm shift in application packaging, offering a consistent and portable environment across diverse infrastructure setups. Meanwhile, Kubernetes has emerged as the dominant choice for managing containerized applications at scale, providing features such as automated scaling, load balancing, and fault tolerance. However, despite the numerous advantages containers and Kubernetes offer, deploying applications to a Kubernetes cluster often poses challenges due to the steep learning curve and complex configuration requirements. To address these challenges, this paper aims to introduce a comprehensive learning tool that automates and simplifies the deployment process on Kubernetes clusters. © 2023 Copyright for this paper by its authors.

关键词： CI/CD Container orchestration Docker image Kubernetes

来源：评论

学校读者我要写书评

暂无评论

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

arXiv

引用

arXiv 2024年

作者： Li, Jinhao Li, Haopeng Erfani, Sarah M. Feng, Lei Bailey, James Liu, Feng School of Computing and Information Systems University of Melbourne Australia Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

MSC Codes 68T45, 68T10It has recently been discovered that using a pretrained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting technique, designed to identify local visual areas within the query image. The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM. To determine how well a query image aligns with each category, we develop a score function based on the weighted similarities in this matrix. Extensive experiments demonstrate that our method significantly improves zero-shot performance across various datasets, achieving results that are even comparable to few-shot learning methods. The code is available at ***/tmlr-group/WCA. © 2024, CC BY.

关键词： Image enhancement

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：