检索结果-内蒙古大学图书馆

SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection

Information Fusion 2025年 124卷

作者： Wenhao Xu Shuchen Zheng Changwei Wang Zherui Zhang Chuan Ren Rongtao Xu Shibiao Xu School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing 100876 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 250014 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100190 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan 250014 China School of Software Microelectronics Peking University Beijing 100084 China

Infrared small target detection (ISTD) is vital for long-range surveillance systems, particularly in military defense, maritime monitoring, and early warning applications. Despite its strategic importance, ISTD remains challenging due to two fundamental limitations: targets typically occupy less than 0.15% of the image area and exhibit low distinguishability from complex backgrounds. While recent advances in deep learning have shown promise, existing methods struggle with information loss during downsampling and inefficient modeling of global context. This paper presents SAMamba, a novel framework that synergistically integrates SAM2’s hierarchical feature learning with Mamba’s selective sequence modeling to address these challenges. Our key innovations include: (1) Feature Selection Adapter (FS-Adapter) that enables efficient domain adaptation from natural to infrared imagery by employing a dual-stage selection mechanism, which includes token-level selection via a learnable task embedding and channel-wise refinement through adaptive transformations; (2) Cross-Channel State-Space Interaction (CSI) module that achieves efficient global context modeling through selective state space modeling with linear complexity; and (3) Detail-Preserving Contextual Fusion (DPCF) module that adaptively combines multi-scale features through learnable fusion strategies, utilizing a gating mechanism to balance contributions from high-resolution and low-resolution features. SAMamba effectively addresses the core challenges of ISTD by bridging the domain gap, maintaining fine-grained target details, and efficiently modeling long-range dependencies. Extensive experiments on NUAA-SIRST, IRSTD-1k and NUDT-SIRST datasets demonstrate that SAMamba significantly outperforms state-of-the-art methods, particularly in challenging scenarios with heterogeneous backgrounds and varying target scales. Code is available at https://***/zhengshuchen/SAMamba .

关键词： Feature fusion Infrared small object detection Segment Anything Model Vision Mamba

来源：评论

学校读者我要写书评

暂无评论

Disease transmission in dynamic social networks constructed by reinforcement learning-driven preventive game

引用

Chaos, Solitons & Fractals 2025年 199卷

作者： Yinuo Qian Dawei Zhao Chengyi Xia School of Control Science and Engineering Tiangong University Tianjin 300387 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 250014 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan 250014 China School of Artificial Intelligence Tiangong University Tianjin 300387 China

Reinforcement learning delves into the intrinsic behaviors of multi-agents, while complex networks reveal their interactive relationships. In real life, an individual can be considered as a sophisticated multi-agent, whose behavioral choices are influenced by a myriad of factors. When contagious diseases penetrate a population, the adoption of preventive measures represents a manifestation of behavioral selection. This paper introduces reinforcement learning into the multi-agent decision within the network, leveraging the Q-learning algorithm to train individual decision-making. At each time step, individuals select the next preventive strategy based on their utility and strategies, and these choices subsequently alter the network structure, thereby influencing the prevalence of the disease. In addition, the incorporation of additional government incentives prompts individuals to opt for advanced preventive strategies, effectively containing disease transmission within the population. The construction of this model not only showcases the co-evolutionary process between network structure and disease transmission but also validates its efficacy through theoretical analysis and applications in real-world networks, offering a novel perspective towards the epidemic control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Android Malicious Code Detection Based on Secondary Pruning Optimization 12

Android Malicious Code Detection Based on Secondary Pruning ...

引用

12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

作者： Yu, Qing Ma, Kuolang Wang, Zuohua Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China Tianjin Times Shengshi Technology Co. Ltd. No. 216 Hongqi Road Nankai District Tianjin300000 China

ISBN: (纸本)9781728148526

In this paper, we propose a detection algorithm for Android malicious code based on integrated multi-feature. By decompiling and processing APK files, the multi-class behavior features of Android application are extracted, and the classification is achieved through an integrated learning framework based on quadratic pruning optimization. The prototype system automatically detects the malicious code of the Android platform and analyzes the validity of the algorithm through experimental verification. © 2019 IEEE.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

A Format Protection Method of Greybox Fuzzing 19

A Format Protection Method of Greybox Fuzzing

引用

19th IEEE International Conference on Communication technology, ICCT 2019

作者： Zhao, Shibin Zhou, Tianyang Duan, Xiaoli Lin, Hongyang Ying, Xinlei Shi, Qibo Peng, Jianshan State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China China United Network Communications Group Co. Ltd Shanxi Yuncheng Branch Yuncheng044000 China Ant-financial Light-Year Security Lab hangzhou310000 China

ISBN: (纸本)9781728105352

Greybox fuzzing, which can fuzz without knowledge of the format, is one of the most advanced fuzzing techniques. However, the lack of format knowledge makes the test cases' format messy as the fuzzing proceeds and reduces the effectiveness of fuzzing. In this paper, we introduce a format protection method that can protect the format of test cases during greybox fuzzing. Based on prior knowledge, the Naive Bayes classifier is applied to achieve a format check method, which is used to improve the favourite seed selection process and induce the position of variation. The experiment results indicate that this method not only has a higher code coverage ratio and more unique crashes in less time than other fuzzers but also maintains the invalid format ratio at a low level. 24 previously unreported CVEs were exposed. © 2019 IEEE.

关键词： Classifiers

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Web Text Based on Deep Learning with a Attention Mechanism

Sentiment Analysis of Web Text Based on Deep Learning with a...

引用

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Qing Yu Hui Zhao Kaiwen Jiang Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China

The sentiment analysis of online commentary is a hot research topic in the field of network information mining. Traditional text sentiment analysis methods are mainly based on emotional dictionaries or machine learning. However, it relies on the structure of the sentiment dictionary and the artificial design and extraction features, which limits the generalization ability. In contrast, the deep learning model has a stronger ability to express complex mapping functions from data to emotional semantics. This paper proposes a model combining Bidirectional Gated Recurrent Unit(BGRU) neural network and Convolutional Neural network(CNN), and introduces attention mechanism for text sentiment analysis. The experimental results show that compared with the traditional method, the method effectively improves the accuracy of text sentiment classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation and Optimization of Temperature Field in Large-Sized MOCVD Reactor by Resistance Heating 4

Simulation and Optimization of Temperature Field in Large-Si...

引用

4th International Conference on Manufacturing, Material and Metallurgical Engineering, ICMMME 2019

作者： Zhao, Lili Li, Zhiming Guo, Runqiu Feng, Lansheng Lu, Ligen Fu, Xiaoqian Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Jinan Shandong250022 China State Key Discipline Laboratory of Wide Band-Gap Semiconductor Technology School of Microelectronics Xidian University Xi'an Shanxi710071 China

The effect of the number of layers and the length of the heat shields on the heating efficiency and temperature distributions in the substrate have been studied by establishing the model of a single-piece 18-inch MOCVD reactor. The results show that the number of layers of the heat shields is directly proportional to the heating efficiency, decreasing the length of the thermal shield can reduce the standard deviation(STD) of the substrate temperature. When the length of the heat shields is 56mm, the coefficient of substrate temperature STD is 21.41 °C and the STD is about 45% lower than the traditional susceptor. An area within substrate radius of 200mm, the coefficient of substrate temperature STD is 2.64 °C and the STD is about 93% lower than the traditional susceptor. The results obtained will provide theoretical basis for developing the heating structure of large-sized MOCVD reactor. © Published under licence by IOP Publishing Ltd.

关键词： Heat shielding

来源：评论

学校读者我要写书评

暂无评论

Velocity-Driven Particle Swarm Optimization 19

Velocity-Driven Particle Swarm Optimization

引用

Proceedings of the 2019 8th International Conference on computing and Pattern Recognition

作者： Wei Li Yaochi Fan Qiaoyong Jiang Qingzheng Xu School of Computer Science and Engineering Xi'an University of Technology and Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China School of Computer Science and Engineering Xi'an University of Technology Xi'an China College of Information and Communication National University of Defense Technology Xi'an China

ISBN: (纸本)9781450376570

Particle swarm optimization (PSO) is an efficient nature-inspired optimization algorithm, which has been widely applied in many engineering fields. The performance of particle swarm optimization (PSO) has been significantly influenced by velocity update strategy. Traditionally, each particle updates its velocity based on its historical best experience and the global best experience, which may make the swarm lose its diversity and lead to premature convergence. To strengthen the performance of PSO, this paper proposes an improved PSO with the velocity-driven strategy (VD-PSO). In VD-PSO algorithm, the particles whose velocities are driven by better velocities focus on exploitation. The historical velocities, such as better velocities, may effectively characterize the landscape information of the optimization problems. In addition, the particles focus on exploration through information exchange amongst velocities. To verify the effectiveness of the proposed algorithm, experiments are conducted with CEC2014 test problems. The experimental results demonstrate the effectiveness of the proposed algorithm for solving the global optimization problems.

关键词： Evolutionary algorithms Velocity-driven strategy Particle swarm optimization Optimization problems

来源：评论

学校读者我要写书评

暂无评论

A two-phase approach for locally differentially private fuzzy co-clustering

引用

Information Sciences 2025年 718卷

作者： Pengfei Zhang Jianlong An Xiang Cheng Youwen Zhu Ji Zhang Zhikun Zhang State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining No. 168 Shungeng Road Tianjiaan District 232001 Huainan China School of Computer Science and Engineering Anhui University of Science and Technology No. 168 Shungeng Road Tianjiaan District 232001 Huainan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics No. 237 Longquan Road Kunming 650221 Yunnan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) No. 3501 Daxue Road Jinan 255020 Shandong China Key Laboratory of Equipment Data Security and Guarantee Technology Guilin University of Electronic Technology No. 1 Jinji Road Guilin 541010 Guangxi China State Key Laboratory of Networking and Switching Technology No. 10 Xitucheng Road Haidian District 100876 Beijing China Beijing University of Posts and Telecommunications No. 10 Xitucheng Road Haidian District 100876 Beijing China College of Computer and Data Science Nanjing University of Aeronautics and Astronautics No. 29 Yudao Street Qinhuai District Nanjing 210016 Jiangsu China School of Mathematics Physics and Computing University of Southern Queensland West Street Toowoomba 4350 Queensland Australia College of Computer Science and Technology Zhejiang University No. 38 Zheda Road Xihu District 310027 Hangzhou China

Clustering analysis is important for providing personalized services across various user experience optimization. As an advanced clustering technique, Fuzzy Co-Clustering ( FCC ) excels at handling high-dimensional data by simultaneously grouping both samples and attributes while allowing objects to belong to multiple clusters. To alleviate the potential privacy risks posed by directly using raw data, researchers often employ local differential privacy (LDP) techniques for protection. However, current clustering studies under LDP either directly perform clustering on the high-dimensional data, which necessitates splitting the privacy budget heavily, leading to excessive noise injection, or fail to adequately address the impact of Laplacian noise on both objective function modeling and distance metric selection, resulting in reduced clustering accuracy. To address these limitations, we present a two-phase approach SONY , which allocates part of the privacy budget to evaluate attribute importance and perform dimensionality reduction accordingly, and then utilizes the remaining budget to conduct noise-aware clustering on the pruned data. Our key technical contributions include: (1) a Noise-aware Similarity Calculation method ( NSC ) that replaces traditional Euclidean distance with a specialized metric which accounts for the statistical properties of Laplacian noise; (2) an importance-driven dimension reduction and budget allocation method ( IDRBA ) which optimizes both attribute selection and privacy budget allocation; and (3) an outlier-aware objective function calculation method ( OOC ) which enhances robustness against potential noise-induced outliers. We provide theoretical guarantees for SONY 's convergence, privacy preservation, utility bounds, and computational complexity. Experimental evaluations conducted on two real-world datasets and one synthetic dataset, demonstrate that SONY outperforms the state-of-the-arts by at least 14% in F-Measure and 10% in Entrop

关键词： Fuzzy co-clustering Local differential privacy Privacy protection Two phase

来源：评论

学校读者我要写书评

暂无评论

An improved RL-based framework for multiple biomedical event extraction via self-supervised learning

An improved RL-based framework for multiple biomedical event...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yao Zhao Weizhong Zhao Xingpeng Jiang Tingting He Bianping Su Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan Hubei PR China School of Computer Central China Normal University Wuhan Hubei PR China National Language Resources Monitoring & Research Center for Network Media Central China Normal University Wuhan Hubei PR China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin PR China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin PR China Xi’an University of Architecture and Technology Xi’an Shanxi PR China

ISBN: (纸本)9781665429825

The main goal of biomedical event extraction is to structurally extract biomedical events from texts, however, the specificity of the domain makes both text modeling and data annotation very difficult. We propose a self-supervised learning-based data augmentation method in this paper and design specific augmentation strategies for biomedical entities and event triggers in biomedical texts, which solves the problem of sparse annotation data to some extent. In addition we improve the reinforcement learning-based event extraction method to improve the training efficiency of the model. The experiments on two datasets demonstrate the effectiveness of our method.

关键词： Training Annotations Conferences Biological system modeling Data models Data mining Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Velocity-driven particle swarm optimization 8

Velocity-driven particle swarm optimization

引用

8th International Conference on computing and Pattern Recognition, ICCPR 2019

作者： Li, Wei Fan, Yaochi Jiang, Qiaoyong Xu, Qingzheng School of Computer Science and Engineering Xi'An University of Technology China Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an710048 China School of Computer Science and Engineering Xi'An University of Technology Xi'an710048 China College of Information and Communication National University of Defense Technology Xi'an710106 China

ISBN: (纸本)9781450376570

关键词： Velocity

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：