检索结果-内蒙古大学图书馆

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang Nanjing University of Posts and Telecommunications (NJUPT) School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan 430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Co-saliency features modeling Diverse Co-saliency features Mining Text-based person retrieval

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Authenticated Solution (CAS) for 6G-Enabled Artificial Intelligence of Medical Things (AIoMT)

引用

IEEE Internet of Things Journal 2024年第13期11卷 23977-23984页

作者： Mahmood, Khalid Obaidat, Mohammad S. Shamshad, Salman Alenazi, Mohammed J. F. Kumar, Gulshan Anisi, Mohammad Hossein Conti, Mauro National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Jordan King Abdullah II School of Information Technology Amman11942 Jordan University of Science and Technology Beijing School of Communication and Computing Engineering Beijing100083 China Amity University Amity School of Engineering and Technology Noida201301 India University of Lahore Department of Software Engineering Lahore54590 Pakistan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh12311 Saudi Arabia University of Padua Department of Mathematics Padua35131 Italy Lovely Professional University Department of Computer Science and Engineering Phagwara144411 India University of Essex School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom

The Internet of Things (IoT) is a network of interconnected objects, which congregate and exchange gigantic amounts of data. Usually, predeployed embedded sensors sense this massive data. Soon, several applications of IoT are anticipated to exploit emerging 6G technology. Healthcare is one of them, where the 6G-inspired paradigm may facilitate the users to exchange information through hundreds of sensors under the assumption of Artificial Intelligence of Things (AIoT). Integration of medical sensors with AIoT is known as Artificial Intelligence of Medical Things (AIoMT). The secure and seamless interactions among 6G-enabled AIoMT users should be the primary challenge. Furthermore, resource-constrained wearable sensing devices, with their inability to execute complex security solutions, provide an ideal attraction for malicious entities to launch diverse attacks. These challenges have motivated us to design a cost-effective authenticated solution (CAS) for 6G-enabled AIoMT healthcare applications. Our CAS protocol not only prevents cyber threats like impersonation session key secrecy but it can also prevent physical threats like hardware tampering. We observe formal and informal security validations to endorse its robustness and effectiveness. Performance comparison reveals that the CAS protocol offers maximum security enrichment. Moreover, CAS is cost-effective as it has achieved 33% and 60% reduction in computation and communication overheads, respectively, compared to contemporary competing related protocols. © 2014 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A noval approach for dual probabilistic linguistic multi-criteria decision making based on prioritized Maclaurin symmetric mean operators and VIKOR

引用

Journal of Intelligent and Fuzzy Systems 2025年第4期48卷 447-462页

作者： Guo, Jing Zhu, Xianjun Li, Wenfeng Li, Hui School of Software Engineering Jinling Institute of Technology Nanjing China School of Engineering Management Nanjing University Nanjing China Reproductive Medicine Center Jinling Hospital Nanjing China Research Center for New Technology in Intelligent Equipment Nanjing University Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

The evolving landscape of decision-making, especially in complex scenarios, poses a challenge in accurately capturing decision-makers’ cognitive information. This challenge becomes even more intricate in group decision-making situations due to the diverse cognitive perspectives of the participants. In response to these complexities, this study delves into the realm of dual probabilistic linguistic 2-tuple sets, an extension of dual-hesitant fuzzy sets known for their effectiveness in handling perplexing data. Dual probabilistic linguistic 2-tuple sets introduces a nuanced approach, considering multiple linguistic memberships, non-membership degrees, and their associated probabilistic and deviation information. We have devised diverse mechanisms aimed at augmenting the comprehension and utilization of dual probabilistic linguistic 2-tuple sets. These mechanisms encompass transformation functions, scoring methodologies and accuracy metrics. In this study, we introduce two aggregation operators for dual probabilistic linguistic 2-tuple sets based on prioritized averaging and Maclaurin symmetric mean principles. These operators serve as the cornerstone for a pioneering hybrid approach meticulously crafted for multiple criteria decision making within the framework of dual probabilistic linguistic 2-tuple sets. To demonstrate the practicality and efficacy of our approach, we present a real-world case study. The subsequent analytical comparison and discussion underscore the effectiveness of our methodology. The outcomes of this study not only showcase the excellent performance of our proposed method but also offer valuable practical implications for decision-makers navigating complex and diverse decision environments. Our work stands as a significant stride toward enhancing decision-making processes amid contemporary challenges. © 2025 – IOS Press. All rights reserved.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

Improving Event Coreference Resolution Using Prompt Learning and U-shaped Module 4

Improving Event Coreference Resolution Using Prompt Learning...

引用

4th International Conference on computer science and Blockchain, CCSB 2024

作者： Zhang, Mengyao Long, Jun Huang, Wenti School of Software Xinjiang University Urumqi China Institute of Big Data Central South University Changsha China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China

ISBN: (纸本)9798350356502

Event Coreference Resolution (ECR) focuses on clustering event mentions that allude to identical actual events. Previous research primarily focuses on encoding event mentions without incorporating human interpretations, making it difficult to integrate human-summarized rules for guiding the ECR task. Furthermore, the semantic relations between event mentions have not been thoroughly explored, which impacts coreference judgment. To address these issues, we first utilize the powerful Longformer to acquire event representations at the document level. In addition, we introduce a prompt learning template to better emphasize event types and parameters, enhancing the interaction between event modeling and coreference judgment. Ultimately, we create matching vectors for event mentions using tensor matching and incorporate a U-shaped module to effectively identify the semantic relationships among these mentions, which enhances coreference discrimination. DPTU surpasses other ECR models on the KBP2017 dataset in cause of some experiments. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on model validation of routing protocol for UAV swarm cooperative disaster relief system

Research on model validation of routing protocol for UAV swa...

引用

2023 International Conference on computer Application and Information Security, ICCAIS 2023

作者： Wei, Tonghao Liu, Jie Yang, Fei Han, Wenxing Jiang, Wei School of Computer Science/Software University of South China Hunan Hengyang China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Sichuan Chengdu China

ISBN: (纸本)9781510675032

In recent years, with the continuous expansion of unmanned aerial vehicle (UAV) swarm applications and the rapid development of the UAV self-organizing network system, the related security threats have also increased. In this paper, we conduct the communication model of the UAV swarm cooperative disaster relief system by verifying the security attributes of the UAV swarm cooperative disaster relief system based on the dynamic source routing (DSR) protocol and we also analyze and verify their security attributes. Finally, we propose a novel scheme to model, characterize, and verify the security attributes of the UAV swarm communication networks. It provides a formal analysis and verification method for verifying the security attributes of self-organized network systems, simplifying a series of challenging verification processes that come with demonstrating the security attributes of the system through simulation experiments. © 2024 SPIE.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Sensitive Information Protection Model Based on Bayesian Game

引用

computers, Materials & Continua 2022年第10期73卷 883-898页

作者： Yuzhen Liu Zhe Liu Xiaoliang Wang Qing Yang Guocai Zuo Frank Jiang School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411201China Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan411201China College of computer and information engineering Hunan University of Technology and BusinessChangshaChina School of Computer Science and Information Engineering Guangzhou Maritime UniversityGuangzhouChina Hunan Software Vocational and Technical University XiangtanChina School of Engineering and IT University of New South WalesNSWAustralia

A game measurement model considering the attacker’s knowledge background is proposed based on the Bayesian game theory aiming at striking a balance between the protection of sensitive information and the quality of *** quantified the sensitive level of information according to the user’s personalized sensitive information protection *** on the probability distribution of sensitive level and attacker’s knowledge background type,the strategy combination of service provider and attacker was analyzed,and a game-based sensitive information protection model was *** the combination of strategies under Bayesian equilibrium,the information entropy was used to measure the leakage of sensitive ***,in the paper the influence of the sensitive level of information and the attacker’s knowledge background on the strategy of both sides of the game was considered *** on,the leakage of the user’s sensitive information was ***,the feasibility of the model was described by experiments.

关键词： Sensitive information game theory Bayesian equilibrium sensitive level information entropy

来源：评论

学校读者我要写书评

暂无评论

An Air Quality Oriented Convolutional and Interaction Network for Traffic Flow Prediction in VANET 16

An Air Quality Oriented Convolutional and Interaction Networ...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Cheng, Hanlin Li, Xuan Zhou, Tianqing Yao, Yu Wang, Kan Zhou, Momiao School of Information and software Engineering East China Jiaotong University Nanchang China School of Information and Communication Engineering Hainan University Haikou China School of Computer Science and Engineering Xi'an University of Technology Xi'an China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798350390643

To accurately predict traffic flow, it is necessary to take into account not only the volume of road traffic, but also external urban factors. Particularly, the correlations between urban air quality and traffic flow is particularly strong, However, due to the complexity of air composition and its nonlinear characteristics in spatial and temporal sequences, it remains underexplored in current research efforts. In this paper, we propose an air quality oriented convolutional and interaction network for traffic flow prediction in Vehicular ad-hoc network, AQCInet, which captures feature information from both types of data using convolutional block, integrates this feature information with interaction networks, and effectively represents the long-term and short-term dependencies in the sequential data, ulti-mately outputting short-term traffic flow prediction results. The experimental results show that AQCInet can effectively model traffic flow sequences with complex time dynamics by aggregating rich features from multiple resolutions. Compared with existing model, our proposed model significantly improves RMSE, MSE, and MAE through jointly considerations of the relationship between air quality, various air component concentrations, and traffic flow. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Feature Generalization Approach for Privacy Protection in Location Based Service

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第4期7卷 862-877页

作者： Wang, Hui Zhang, Hai-Yang Shen, Zi-Hao Liu, Pei-Qian Liu, Kun Zhen, Wei School of Software Henan Polytechnic University Jiaozuo454000 China School of Computer Science and Technology Henan Polytechnic University Jiaozuo454000 China

With the rapid development of mobile devices, rapid positioning has become one of the most popular services in mobile online social networks. In the fast location service, users can enjoy a better social experience by updating their real-time location information. However, the accuracy of the query results and the leakage of personal information may hinder the further development of the service. Hence, a location privacy protection method based on feature generalization is proposed for the existing problems. In this method, an algorithm called dynamic clustering is constructed to improve the con-struction efficiency of clusters in the anonymous region and simultaneously enable each cluster to meet the needs of K anonymity. Then, using the captain election algorithm and query algorithm, while meeting the user’s mobility and flexible privacy protection requirements, accurate query results can be quickly returned to the user. Through the-oretical analysis and experiments, it is verified that this method is a safe and effective privacy protection solution. © 2022 ISSN 2414-8105 (Online).

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning

引用

Frontiers of computer science 2024年第1期18卷 77-91页

作者： Yang YANG Jinyi GUO Guangyu LI Lanyu LI Wenjie LI Jian YANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Computing Hong Kong Polytechnic UniversityHong Kong 100872China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing 210094China 14th Research Institute of China Electronics Technology Group Corporation Nanjing 210094China guangyu.li2017@***

Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent representations of heterogeneous modalities,thereby to search similar instances in one modality according to the query from another modality in *** basic assumption behind these methods is that parallel multi-modal data(i.e.,different modalities of the same example are aligned)can be obtained in *** other words,the image-sentence cross-modal retrieval task is a supervised task with the alignments as ***,in many real-world applications,it is difficult to realign a large amount of parallel data for new scenarios due to the substantial labor costs,leading the non-parallel multi-modal data and existing methods cannot be used *** the other hand,there actually exists auxiliary parallel multi-modal data with similar semantics,which can assist the non-parallel data to learn the consistent ***,in this paper,we aim at“Alignment Efficient Image-Sentence Retrieval”(AEIR),which recurs to the auxiliary parallel image-sentence data as the source domain data,and takes the non-parallel data as the target domain *** single-modal transfer learning,AEIR learns consistent image-sentence cross-modal representations of target domain by transferring the alignments of existing parallel ***,AEIR learns the image-sentence consistent representations in source domain with parallel data,while transferring the alignment knowledge across domains by jointly optimizing a novel designed cross-domain cross-modal metric learning based constraint with intra-modal domain adversarial ***,we can effectively learn the consistent representations for target domain considering both the structure and semantic ***,extensive experiments on different transfer scenarios validate that AEIR can achieve better retrieval results comparing with the baselines.

关键词： image-sentence retrieval transfer learning semantic transfer structure transfer

来源：评论

学校读者我要写书评

暂无评论

Adaptive Motion Detection for Enhanced Video Surveillance 6

Adaptive Motion Detection for Enhanced Video Surveillance

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Brown, Mpofu Jabulani Li, Chenglong Gao, Xinyan Su, Xinxin Shandong Jianzhu University School of Computer Science and Technology Shandong China Shandong Hoteam Software Co. Ltd. Jinan China

ISBN: (纸本)9798350316520

The field of video surveillance demands precision and operates within strict constraints. In particular, object detection models must strike a delicate balance between accuracy and efficiency to run effectively on edge devices with limited resources. An effective approach to enhancing model performance in dynamic scenarios involves the integration of motion detection techniques. This paper introduces an innovative motion detection method featuring several novel mechanisms. Notably, the proposed technique incorporates an adaptive learning rate, determined by the intensity of motion within the scene, and an adaptive threshold, based on the mean intensity of each frame. These adaptations render the algorithm highly responsive to variations in motion and lighting conditions. Furthermore, the algorithm employs HSV color space to detect shadows, effectively distinguishing them from actual objects, and a simple Gaussian Blur method for background model initialization. This approach yields an algorithm that is both robust and efficient, a critical requirement for real-time performance on resource-constrained edge devices deployed in dynamic environments. © 2024 IEEE.

关键词： Object detection

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：