检索结果-内蒙古大学图书馆

Modality-Specific Interactive Attack for Vision-Language Pre-Training Models

IEEE Transactions on Information Forensics and Security 2025年 20卷 5663-5677页

作者： Zhang, Haiqi Tang, Hao Sun, Yanpeng He, Shengfeng Li, Zechao Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China The Hong Kong Polytechnic University Centre for Smart Health Hong Kong Singapore Management University School of Computing and Information Systems Singapore

Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of crossmodal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSIAttack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms. 2005-2012 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

LATCHING CONTROL OF WAVE ENERGY CONVERTERS USING TUNABLE ELECTRICAL LOAD 42

LATCHING CONTROL OF WAVE ENERGY CONVERTERS USING TUNABLE ELE...

引用

ASME 2023 42nd International Conference on Ocean, Offshore and Arctic engineering, OMAE 2023

作者： Tahir, Uzair Bin Zhang, Jingxin Manasseh, Richard Swinburne University of Technology School of Science Computing and Engineering Technologies VIC Australia

ISBN: (纸本)9780791886908

Frequency of ocean waves varies over the time, and maximum power generation is only possible when wave energy converters (WECs) and incoming waves are at resonance. Adaptive control strategy is required for an optimal power absorption, which is impractical using available mechanical models. Electrical load control strategy can help to achieve the resonance condition without any structural change. WEC studied in this paper is a heaving bouy connected to the electrical power take off (PTO) having tunable passive load at the output. Electrical load based compensation has been presented to achieve the resonance during varying ocean wave frequencies. Many control strategies have been investigated in the past, but always required complex mechanical and electrical implementation. The only notable electrical control strategy is complex conjugate match, which is misleading as it requires external power to be implemented. Mechanical latching control is known for decades that can provide optimal tuning of excitation wave with WEC device for maximum power absorption. Electrical load based latching control has been used which regulates movement of the bouy according to the input wave force. An electromechanical mathematical model has been presented for the control conditions, and MATLAB/Simulink is used for the simulation of WEC’s operation under regular input waves. Results shows the use of passive electrical damping can control velocity, displacement, and improve power absorption compared to conventional latching control. Copyright © 2023 by ASME.

关键词： Water waves

来源：评论

学校读者我要写书评

暂无评论

DSAFF-Net:A Backbone Network Based on Mask R-CNN for Small Object Detection

引用

Computers, Materials & Continua 2023年第2期74卷 3405-3419页

作者： Jian Peng Yifang Zhao Dengyong Zhang Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India

Recently,object detection based on convolutional neural networks(CNNs)has developed *** backbone networks for basic feature extraction are an important component of the whole detection ***,we present a new feature extraction strategy in this paper,which name is *** this strategy,we design:1)a sandwich attention feature fusion module(SAFF module).Its purpose is to enhance the semantic information of shallow features and resolution of deep features,which is beneficial to small object detection after feature fusion.2)to add a new stage called D-block to alleviate the disadvantages of decreasing spatial resolution when the pooling layer increases the receptive *** method proposed in the new stage replaces the original method of obtaining the P6 feature map and uses the result as the input of the regional proposal network(RPN).In the experimental phase,we use the new strategy to extract *** experiment takes the public dataset of Microsoft Common Objects in Context(MS COCO)object detection and the dataset of Corona Virus Disease 2019(COVID-19)image classification as the experimental object *** results show that the average recognition accuracy of COVID-19 in the classification dataset is improved to 98.163%,and small object detection in object detection tasks is improved by 4.0%.

关键词： Small object detection classification RPN MS COCO COVID-19

来源：评论

学校读者我要写书评

暂无评论

Rail Transit Event Extraction based on the Fusion of Semantic and Local Dependency Features 15

Rail Transit Event Extraction based on the Fusion of Semanti...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Chen, Qiang Meng, Haining Bao, Yihao Yang, Mingsong Tong, Xinyu Zhao, Qin Khan, Muhammad Bilal Hei, Xinhong Xi'an University of Technology School of Computer Science and Engineering Xi'an China Xi'an University of Technology School of Computer Science and Engineering Shaanxi Key Laboratory of Network Computing and Security Technology Xi'an China Xi'an University of Technology School of Civil Engineering and Architecture Xi'an China

ISBN: (纸本)9798331508821

Event extraction in rail transit plays a vital role in all stages of design, construction, and final acceptance. Event extraction is a key part of building event logic graph (ELG). However, the difficulty in obtaining semantic features and event local dependencies poses a challenge to accurate event extraction, which hinders the informatization and intelligent development of rail transit projects. To address these challenges, we proposes an event extraction method that fuses semantic and local dependency features. The study initially preprocesses the rail transit design codes dataset and performs sequence labeling. Then, the event trigger words are mined by combining the term frequency-inverse document frequency (TF-IDF) and minimum edit distance (MED) algorithms. Based on the semantic similarity measurement method and the trigger word mining results, the features representation of event semantic information is enhanced by using the Bidirectional Encoder Representations from Transformers (BERT) model and Bi-directional Long Short-Term Memory (BiLSTM) model. At the same time, event arguments are mined and a local dependency graph is generated based on their mining results, and then the enhanced local dependency features are obtained by using the graph convolutional network (GCN). Finally, the event semantic features and local dependency features are fused, and the conditional random field (CRF) is used to predict the labels to obtain the event extraction results. Through the comparison with five baseline methods on the datasets of rail transit design codes, it is found that the Precision, Recall, and F1 score of the proposed method are improved, with an average improvement of 9.604% on Precision, 9.342% on Recall, and 9.730% on F1 score, respectively. The contribution of the sub-modules to the overall performance is further evaluated through ablation experiments, which confirms the effectiveness and feasibility of the proposed method. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Principled Design of Translation, Scale, and Rotation Invariant Variation Operators for Metaheuristics

引用

Chinese Journal of Electronics 2023年第1期32卷 111-129页

作者： TIAN Ye ZHANG Xingyi HE Cheng TAN Kay Chen JIN Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University School of Artificial Intelligence Anhui University School of Electrical and Electronic Engineering Huazhong University of Science and Technology Department of Computing The Hong Kong Polytechnic University Faculty of Technology Bielefeld University

A large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed,new operators are automatically designed in this work,which are expected to be search space independent and thus exhibit robust performance on different *** work first investigates the influence of translation invariance, scale invariance, and rotation invariance on the search behavior and performance of some representative operators. This work then deduces the generic form of translation, scale, and rotation invariant operators, and proposes a principled approach for the automated design of operators, which searches for high-performance operators based on the deduced generic form. The experimental results demonstrate that the operators generated by the proposed approach outperform state-of-the-art ones on a variety of problems with complex landscapes and up to 1000decision variables.

关键词： Deep learning Metaheuristics Reinforcement learning Benchmark testing Search problems Robustness Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1513-1528页

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Ma, Xingjun Qi, Peng Ding, Zhijun Jin, Jiong Tongji University School of Computer Science and Technology Shanghai201804 China Ant Group Shanghai200122 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Fudan University School of Computer Science Shanghai200438 China Tongji University Department of Control Science and Engineering Shanghai201804 China Swinburne University of Technology School of Science Computing and Engineering Technologies Melbourne3122 Australia

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this article, we propose a hypergraph learning framework named learning from heterogeneity (LFH) that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterward, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with twelve state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experimental results demonstrate a significant performance gain (an average of 12.9% in node classification and 12.8% in link prediction) compared with recent state-of-the-art methods. © 2020 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Smart Meter Data Encryption Scheme Basedon Distributed Differential Privacy

引用

Big Data Mining and Analytics 2024年第1期7卷 131-141页

作者： Renwu Yan Yang Zheng Ning Yu Cen Liang School of Electronic Electrical Engineering and PhysicsFujian University of TechnologyFuzhou 350118China Department of Computing Sciences at The College at Brockport State University of New YorkNew YorkNY 14420USA

Under the general trend of the rapid development of smart grids,data security and privacy are facing serious challenges;protecting the privacy data of single users under the premise of obtaining user-aggregated data has attracted widespread *** this study,we propose an encryption scheme on the basis of differential privacy for the problem of user privacy leakage when aggregating data from multiple smart ***,we use an improved homomorphic encryption method to realize the encryption aggregation of users’***,we propose a double-blind noise addition protocol to generate distributed noise through interaction between users and a cloud platform to prevent semi-honest participants from stealing data by colluding with one ***,the simulation results show that the proposed scheme can encrypt the transmission of multi-intelligent meter data under the premise of satisfying the differential privacy *** if an attacker has enough background knowledge,the security of the electricity information of one another can be ensured.

关键词： smart grid homomorphic encryption data aggregation differential privacy cloud computing

来源：评论

学校读者我要写书评

暂无评论

Koopman framework-based observer design for actuator fault identification in Quadrotor 10

Koopman framework-based observer design for actuator fault i...

引用

10th Indian Control Conference, ICC 2024

作者： Akumalla, Ravi Kiran Shukla, Amit Jain, Tushar The School of Mechanical and Materials Engineering Indian Institute of Technology HP Mandi India The Faculty of School of Mechanical and Materials Engineering Indian Institute of Technology HP Mandi India The Faculty of School of Computing and Electrical Engineering Indian Institute of Technology HP Mandi India

ISBN: (纸本)9798331517212

This paper investigates the implementation of the Koopman framework to quadrotor by numerical simulations. Initially, the nonlinear dynamics of a quadrotor is modelled in MATLAB/SIMULINK. The attitude and altitude control of the model is achieved using individual PID controllers. From this closed-loop model, the attitude data and angular torque data are collected. Using this data, a linear approximation of the attitude dynamics of the quadrotor is found by applying the Koopman framework. This identified Koopman linear model is leveraged as a predictor within the model predictive controller (MPC) to achieve inner loop attitude tracking of the quadrotor. Then, a loss of actuator effectiveness (LOE) fault is introduced in one of the actuators, which is successfully identified by designing a linear observer based on the identified Koopman linear model. Finally, the simulation results are provided, describing the attitude control and actuator fault identification in quadrotor using the Koopman framework. © 2024 IEEE.

关键词： Altitude control

来源：评论

学校读者我要写书评

暂无评论

Stationary wavelet transform and SpinalNet trained light spectrum Tasmanian devil optimization enabled DR detection using fundus images

引用

Multimedia Tools and Applications 2025年第4期84卷 1597-1626页

作者： Tamboli, Mubin Shoukat Dhumane, Amol Prasad, Rajesh Prasad, Jayashree Rajesh Ranjan, Nihar M. Computer Engineering Pimpri Chinchwad College of Engineering Pradhikaran Maharashtra Pune411044 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune India Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Diabetes is a common disease that causes complications in the eyes known as Diabetic Retinopathy (DR). It aids in discovering the DR and tends to be the main cause behind people’s blindness amidst the previous decades. For prevent the complications of DR and to control the level of blood Glucose, the timely and crucial diagnosis is essential. A model is provided for detecting the DR. Here, Light Spectrum Tasmanian Devil Optimization (LSTDO) is utilized with SpinalNet for DR detection. The method undergoes an adaptive median filter and Region of interest mining process to generate a pre-processed image. The Sparse Fuzzy C-Means (FCM) is adapted for segmenting the optic disks followed by feature extraction. Then, the Hough line transformation with Tyler Coye algorithm (HLTCA) is used for blood vessel segmentation. Concurrently, the Stationary Wavelet Transform (SWT) is adapted to input image to overwhelm the deficiency of translation-invariance issue and then the feature mining is done. The feature vector is generated by unifying the outputs of the three-feature extraction phases and is employed to detect DR. The accuracy, sensitivity, and specificity obtained by the LSTDO-based SpinalNet are 91.6%, 89.9% and 92.1%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Impact of Environmental Changes on Optimized Robotics Collective Motion for Multi-objective Coverage Tasks 13th

Impact of Environmental Changes on Optimized Robotics Coll...

引用

13th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2025

作者： Ghanem, Reda Ali, Ismail M. Kasmarik, Kathryn Garratt, Matthew School of Systems and Computing University of New South Wales Canberra Australia School of Engineering and Technology University of New South Wales Canberra Australia

ISBN: (纸本)9789819635054

Coverage tasks have garnered significant interest in recent years due to their applications in fields such as environmental monitoring, search and rescue, and robotic exploration. Swarm robotics has emerged as a promising approach to tackle these challenges, leveraging collective behaviors to enhance efficiency. However, the effectiveness of swarm algorithms often hinges on the careful tuning of parameters, which can be influenced by varying environmental features. This study investigates the impact of these features on the performance of optimized collective motion in swarm robotics for solving multi-objective coverage problems. Through a comprehensive sensitivity analysis, we evaluate how changes in parameters-such as arena size, number of robots, obstacle density, and obstacle structure-affect swarm performance in solving coverage problems. The analysis focuses on key performance metrics across multiple objectives: coverage percentage, coverage time, robot connectivity, and collision rates. Our findings provide critical insights into the adaptability of swarm algorithms, highlighting the importance of environmental context in optimizing swarm efficacy across competing objectives. These results contribute to the development of more robust and adaptive swarm-based solutions for multi-objective coverage tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic algorithms

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：