检索结果-内蒙古大学图书馆

Group-wise co-salient object detection via multi-view self-labeling novel class discovery

Frontiers of Computer Science 2024年第2期18卷 259-261页

作者： Yang WU Gang DONG Lingyan LIANG Yaqian ZHAO Kaihua ZHANG Inspur Electronic Information Industry Co. Ltd.Beijing 100080China Jiangsu Key Laboratory of Big Data Analysis Technology and Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

1 Introduction Co-salient object detection(CoSOD)aims to extract the salient object(s)that are common across a group of relevant images[1].Group-wise clue plays a crucial role in accurately predicting the co-salient ***,numerous groupwise deep models have been proposed by exploring consistency across images in unsupervised clustering manners[2-4]or the semantic connections guidance information[5].

关键词： consistency Group semantic

来源：评论

学校读者我要写书评

暂无评论

Opponent-aware Order Pricing towards Hub-oriented Mobility Services 39

Opponent-aware Order Pricing towards Hub-oriented Mobility S...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Wu, Zuohan Zheng, Libin Zhang, Chen Jason Zhu, Huaijie Yin, Jian Jiang, Di Sun Yat-sen University Guangzhou China Hong Kong Polytechnic University Hong Kong WeBank Co. Ltd Shenzhen China The Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9798350322279

Hub-oriented mobility services have gained great developments in recent years, enabling riders to simultaneously call vehicles from multiple mobility-supply companies (agents) on a single APP (which we call "hub"). Competing with others on such a hub, to obtain an order, an agent company first needs to get admitted by the requester, which is in turn affected by its quotation. The quotation needs to be attractively low compared to those of the opposing agents. Thus, an opponent-aware pricing strategy is needed for an agent to play well in the hub scenario, which is rarely discussed in existing works. To address the aforementioned issue, in this work, we first propose a quotation prediction model, which employs a neural network with a customized loss function to predict the opponents' quotations. Based on the predictions, we then propose multi-arm bandit based methods to decide a proper quotation for the agent, in order to obtain orders while retaining profits. We finally conduct extensive experiments on real data, where the quotation-determining method integrated with the prediction model has achieved a remarkable profit improvement up to 85.5% compared to baseline methods, demonstrating their effectiveness. © 2023 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

A video archive management method based on blockchain technology 11

A video archive management method based on blockchain techno...

引用

Optoelectronic Imaging and Multimedia Technology XI 2024

作者： Wu, Rongteng College of Computer and Big Data Minjiang University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

ISBN: (纸本)9781510682061

Video archives play a crucial role in various industries, from media and entertainment to security and surveillance. Managing these archives efficiently and securely is a growing challenge due to the increasing volume of video data being generated. In this paper, a video archive management method is presented to solve security and sensibility of the video files on blockchain. By encrypting video files and generating cryptographic hashes, the presented method can protect the integrity of the data and prevent unauthorized modifications. The method based on blockchain technology offers a compelling solution to the challenges faced in managing video archives. By combining the inherent security and transparency of blockchain with innovative data management algorithms, organizations can ensure the integrity, security, and accessibility of their video archives. © 2024 SPIE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

E-Commerce Personalized Recommendation System in big data Based on Three-Way Concept Lattices 3

E-Commerce Personalized Recommendation System in Big Data Ba...

引用

3rd International Conference on Artificial Intelligence and Autonomous Robot Systems, AIARS 2024

作者： Xu, Hongsheng Gu, Jing College of Electronic and Commerce Luoyang Normal University Luoyang China Luoyang Normal University Henan key Laboratory for Big Data Processing & Analytics of Electronic Commerce Luoyang China

ISBN: (纸本)9798350376173

The e-commerce recommendation system can automatically judge the preferences of users according to the browsing situation, and recommend relevant products to customers based on this basis to reduce the time wasted by customers in looking for products. The e-commerce recommendation system is to use the e-commerce big data platform to provide consumers with product information and relevant suggestions, to recommend consumers to buy their favorite types of products, and to imitate the salesman to help consumers to complete the purchase behavior. The paper presents e-commerce personalized recommendation system in big data based on three-way concept lattices. Finally, the method experimentally proves that the proposed method achieves accurate personalized recommendation results and showing better prediction accuracy, which has strong scalability. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Grouped Graph Neural Networks for Anomaly Detection in Time Series

Grouped Graph Neural Networks for Anomaly Detection in Time ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziyu Guo Weiyang Kong Yubao Liu Sun Yat-Sen University GuangZhou China Guangdong Key Laboratory of Big Data Analysis and Processing GuangZhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Anomaly detection in time series data (e.g., sensor data) is becoming a fundamental research problem that has various applications. Due to the complex inter-sensor relationships, it is challenging to detect anomalous events such as system faults and attacks hidden the high-dimensional time series. Recent advancements in deep learning approaches such as Graph Neural Networks (GNN) have greatly improved anomaly detection performance in time series data. However, existing methods do not learn the dependence relationships between sensors and groups of sensors and may not efficiently detect anomalous events in time series. In this paper, we propose a novel approach GGNN (short for Grouped Graph Neural Networks) that combines a structure learning approach with graph neural networks. In particular, GGNN learns the graph structure containing groups of sensors, which are represented by virtual nodes. In addition, we use the learned graph structure and attention weights to explain the detected anomalies. The experiments on three real world datasets show our superiority in detection accuracy, anomaly diagnosis, and model interpretation compared with state-of-the-art methods.

关键词： Training Deep learning Accuracy Soft sensors Time series analysis Graph neural networks Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent Service Cluster Construction Method Based on Remote Sensing Application 6

Intelligent Service Cluster Construction Method Based on Rem...

引用

6th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2022

作者： Zhou, Liming Yang, Wencheng Du, Ying Liu, Cheng Li, Heng Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781665431859

The production of remote sensing products needs to go through various links of evaluation and deploy a variety of software and hardware resources. It is necessary to study how to improve the efficiency of service cluster deployment, simplify the evaluation process, and optimize its structure. This paper designs an intelligent service cluster construction method based on remote sensing applications, which realizes the accurate and efficient deployment of various complex network structures and equipment on the visual interface. The method is convenient and simple to operate. It can set various types of resource information according to the needs of users, can choose a more reasonable server cluster deployment plan, improve the efficiency of data storage and processing of remote sensing products, better serve users, and greatly promote The development of related industries. © 2022 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

The Program Testing Ability of Large Language Models for Code

The Program Testing Ability of Large Language Models for Cod...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Xiong, Weimin Guo, Yiwen Chen, Hao National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Tencent Security Big Data Lab China UC Davis United States

ISBN: (纸本)9798891761667

Recent development of large language models (LLMs) for code like CodeX and CodeT5+ shows promise in achieving code intelligence. Their ability of synthesizing program targeting a pre-defined algorithmic coding task has been intensively tested and verified on datasets including HumanEval and MBPP. Yet, evaluation of these LLMs from more perspectives (than just program synthesis) is also anticipated, considering their broad scope of applications. In this paper, we explore their ability of automatic test cases generation. We show intriguing observations and reveal how the quality of their generated test cases can be improved. Following recent work which uses generated test cases to enhance program synthesis, we further leverage our findings in improving the quality of the synthesized programs and show +11.77% and +4.22% higher code pass rates on HumanEval+ comparing with the GPT-3.5-turbo baseline and the recent state-of-the-art, respectively. Our code is publicly available at https://***/asdasxzxcq/TestCaseGen. © 2024 Association for Computational Linguistics.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

Placement of Deep Reinforcement Learning in Service Function Chain of Network Function Virtualization 2

Placement of Deep Reinforcement Learning in Service Function...

引用

2nd International Conference on data Science and Information System, ICDSIS 2024

作者： Xu, Hongsheng Huang, Kaifeng Luoyang Normal University College Of Electronic And Commerce Luoyang China Luoyang Normal University Henan Key Laboratory For Big Data Processing & Analytics Of Electronic Commerce Luoyang China

ISBN: (纸本)9798350381665

Reinforcement learning is a goal-oriented algorithm. The core goal of the algorithm is to learn to make decisions during the interaction between intelligent agents and the environment. Deep Reinforcement Learning is an algorithm that combines the perception ability of deep learning and the powerful decision-making ability of reinforcement learning. It can directly understand the network and task from experience, thus improving the accuracy and reducing repeated modeling, and is widely used to solve complex problems. A Network Service in NFV can be represented as a Service Function Chain (SFC), which consists of a series of Virtual network functions (VNF) in a given order. In order to provide efficient services, SFCS are deployed in a number of different servers and direct traffic through a set of VNFS in a specific order. This paper proposes SFC placement in NFV based on deep reinforcement learning model. Finally, it is found that the deep learning model can effectively improve the efficiency of SFC placement. © 2024 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Efficient Position Determination Using Low-Rank Matrix Completion 2

Efficient Position Determination Using Low-Rank Matrix Compl...

引用

2nd IEEE International Conference on Signal, Information and data processing, ICSIDP 2024

作者： Zhang, Zehui Pu, Wenqiang Zhou, Rui You, Mingyi Wang, Wei Yan, Junkun Shenzhen Research Institute of Big Data Shenzhen China National Key Laboratory of Electromagnetic Space Security Jiaxing China National Key Laboratory of Radar Signal Processing Hangzhou Institute of Technology Xidian University Xi'an China National Key Laboratory of Radar Signal Processing Hangzhou Institute of Technology Xidian University Hangzhou China

ISBN: (纸本)9798331515669

In increasingly complex electromagnetic environments, distributed systems are crucial for passive target localization. These systems, consisting of spatially dispersed sensing nodes, collaboratively enhance the localization of target signals. Particularly in blind localization tasks within low signal-to-noise ratio (SNR) settings, distributed passive localization offers improved positioning performance. Traditional passive localization methods typically follow a two-step process: initially extracting parameters, such as the direction of arrivals (DOA), from raw data, followed by localizing the target. This approach often requires a high SNR. In contrast, Direct Position Determination (DPD) methods directly leverage all the received raw data, thus overcoming the constraints of the two-step process. However, DPD methods involve a time-consuming grid search within the area of interest. To address this challenge, we propose a radiation source localization method that utilizes random sampling. This method capitalizes on the low-rank properties of the grid search matrix used in DPD methods. By integrating random sampling with low-rank matrix completion algorithms, our approach efficiently localizes the radiation source. Simulation results demonstrate that this random sampling-based method significantly reduces computational demands while preserving high localization accuracy. © 2024 IEEE.

关键词： Direction of arrival

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：