检索结果-内蒙古大学图书馆

DPT‐tracker:Dual pooling transformer for efficient visual tracking

CAAI Transactions on Intelligence technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Improved target detection algorithm based on YOLOv5s 24

Improved target detection algorithm based on YOLOv5s

引用

6th International Conference on control and Computer Vision, ICCCV 2024

作者： Chen, Boyang Han, Chunxiao Wu, Han Tianjin Key Laboratory of Information Sensing & Intelligent Control School of Automation and Electrical Engineering Tianjin University of Technology and Education China

ISBN: (纸本)9798400718045

Target detection is a research hotspot in the field of computer vision and machine learning, and the deep learning model greatly improves the efficiency of target detection and classification by obtaining feature information and classification through multi-layer neural networks, which is the mainstream algorithm for target detection at present. In this paper, YOLOv5s target detection algorithm is improved, and the SIoU loss function is chosen to replace the CIoU loss function used in the original model, while the SimAM attention mechanism is added to the Neck module of the YOLOv5s model, and it is proved through experiments that the improved model improves the average precision (mAP@0.5) by 0.2% over the original model, and the recall rate (Recall) is improved by 0.8%. The faster convergence and improved precision of the model further improves the performance of the model. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Automotive Parts Recognition Based on Improved YOLOv5 Algorithm

Research on Automotive Parts Recognition Based on Improved Y...

引用

2024 International Conference on Remote Sensing, Mapping, and Image Processing, RSMIP 2024

作者： Xu, Yu Hu, Shan Ming, Rui Zhang, Tianzhi School of Automation and Electrical Engineering Tianjin University of Technology and Education Key Laboratory of Information Sensing & Intelligent Control Tianjin China

ISBN: (纸本)9781510680012

With the continuous development of the automotive industry, the target detection and recognition of automotive parts have become crucial factors for automakers to enhance automation levels. In this paper, to ensure improved detection accuracy while meeting real-time detection requirements, we propose an enhanced YOLOv5 model for automotive parts recognition. This method optimizes candidate box parameters using the K-Means algorithm, addresses feature mismatch issues through variational convolution, and optimizes the loss function using GIOU instead of IOU. Experimental results show that the improved YOLOv5 algorithm achieves an average precision of 99.1%, representing a relative improvement of 1.72% over Fast R-CNN and 3.91% over the standard YOLOv5 algorithm. Furthermore, it demonstrates excellent real-time detection performance, meeting the demands of practical application scenarios. © 2024 SPIE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Approximating the Infinite-Horizon Value Function of the Discrete-Time Switched LQR Problem

引用

Journal of Systems Science & Complexity 2024年第1期37卷 22-39页

作者： HOU Tan LI Yuanlong LIN Zongli Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904-4743USA

This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value *** method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration,and thus,the proposed approach is capable of achieving a better approximation for a given computation time compared with the existing *** numerical examples are presented in this paper to illustrate the effectiveness of the proposed method.

关键词： Optimal control switched linear systems switched LQR problem.

来源：评论

学校读者我要写书评

暂无评论

Decentralized control in active distribution grids via supervised and reinforcement learning

引用

Energy and AI 2024年第2期16卷 137-149页

作者： Stavros Karagiannopoulos Petros Aristidou Gabriela Hug Audun Botterud Laboratory for Information and Decision Systems(LIDS) Massachusetts Institute of TechnologyCambridgeUSA EEH-Power Systems Laboratory ETH Zurichhysikstrasse 38092 ZurichSwitzerland Department of Electrical Engineering Computer Engineering&InformaticsCyprus

While moving towards a low-carbon, sustainable electricity system, distribution networks are expected to host a large share of distributed generators, such as photovoltaic units and wind turbines. These inverter-based resources are intermittent, but also controllable, and are expected to amplify the role of distribution networks together with other distributed energy resources, such as storage systems and controllable loads. The available control methods for these resources are typically categorized based on the available communication network into centralized, distributed, and decentralized or local. Standard local schemes are typically inefficient, whereas centralized approaches show implementation and cost concerns. This paper focuses on optimized decentralized control of distributed generators via supervised and reinforcement learning. We present existing state-of-the-art decentralized control schemes based on supervised learning, propose a new reinforcement learning scheme based on deep deterministic policy gradient, and compare the behavior of both decentralized and centralized methods in terms of computational effort, scalability, privacy awareness, ability to consider constraints, and overall optimality. We evaluate the performance of the examined schemes on a benchmark European low voltage test system. The results show that both supervised learning and reinforcement learning schemes effectively mitigate the operational issues faced by the distribution network.

关键词： Supervised learning Reinforcement learning Deep deterministic policy gradient Decentralized control Active distribution systems

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization and Scaling Design for Solving Sylvester Equations

引用

Journal of Systems Science & Complexity 2024年第6期37卷 2487-2510页

作者： CHENG Songsong YU Xin ZENG Xianlin LIANG Shu HONG Yiguang Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 201210China

This paper develops distributed algorithms for solving Sylvester *** authors transform solving Sylvester equations into a distributed optimization problem,unifying all eight standard distributed matrix *** the authors propose a distributed algorithm to find the least squares solution and achieve an explicit linear convergence *** results are obtained by carefully choosing the step-size of the algorithm,which requires particular information of data and Laplacian *** avoid these centralized quantities,the authors further develop a distributed scaling technique by using local information *** a result,the proposed distributed algorithm along with the distributed scaling design yields a universal method for solving Sylvester equations over a multi-agent network with the constant step-size freely chosen from configurable ***,the authors provide three examples to illustrate the effectiveness of the proposed algorithms.

关键词： Distributed optimization least squares solution linear convergence rate step-size interval Sylvester equation

来源：评论

学校读者我要写书评

暂无评论

Effect of radical scavenger on electrical tree in cross-linked polyethylene with large harmonic superimposed DC voltage

引用

High Voltage 2023年第4期8卷 739-748页

作者： Lewei Zhu Zhonglei Li Kai Hou Maritime College Tianjin Key Laboratory for Control Theory and Applications in Complicated Industry SystemsTianjin University of TechnologyTianjinChina Key Laboratory of Smart Grid of Ministry of Education School of Electrical and Information EngineeringTianjin UniversityTianjinChina

In this study,three kinds of radical scavenger Chimassorb 944,Tinuvin 622,and Tinuvin 770 are used to suppress the growth of electrical trees in cross-linked polyethylene(XLPE)with transient superimposed voltage under the temperature *** tree morphology,tree length,accumulated damage,and time to breakdown are used to investigate the effect of radical scavenger on the electrical treeing *** is found that under the temperature gradient caused by the temperature rise on the high voltage side,only Tinuvin 622 can always suppress the electrical tree as the temperature gradient *** the temperature gradient caused by the temperature rise on the ground side,the three radical scavengers can all suppress the electrical *** breakdown of electrical tree exhibits the strong DC polarity ***,energy levels of these three radical scavengers are calculated through quantum chemistry,and the results indicate that radical scavengers have greater electron affinity,smaller ionisation energy,and smaller energy gap than *** to the surface potential decay test results at 60℃,it is found that all three radical scavengers can introduce deep *** different performances of radical scavengers under different temperature gradients and voltages are determined by the trap distribution characteristics,the molecular structure and chemical reaction of the additives *** is concluded that Tinuvin 622 has potential for use in high voltage direct current XLPE cable application.

关键词： radical electrical harmonic

来源：评论

学校读者我要写书评

暂无评论

Radiative cooling for passive thermal management towards sustainable carbon neutrality

引用

National Science Review 2023年第1期10卷 87-97页

作者： Jun Liang Jiawei Wu Jun Guo Huagen Li Xianjun Zhou Sheng Liang Cheng-Wei Qiu Guangming Tao Wuhan National Laboratory for Optoelectronics and Optics Valley Laboratory Huazhong University of Science and Technology Department of Electrical and Computer Engineering National University of Singapore MOE Key Laboratory of Thermo-Fluid Science and Engineering School of Energy and Power Engineering Xi'an Jiaotong University Key Laboratory of Education Ministry on Luminescence and Optical Information Technology National Physical Experiment Teaching Demonstration CenterDepartment of PhysicsSchool of Physical Science and Engineering Beijing Jiaotong University State Key Laboratory of Material Processing and Die &Mould Technology School of Materials Science and Engineering Huazhong University of Science and Technology

Photonic structures at the wavelength scale offer innovative energy solutions for a wide range of applications,from high-efficiency photovoltaics to passive cooling,thus reshaping the global energy *** cooling based on structural and material design presents new opportunities for sustainable carbon neutrality as a zero-energy,ecologically friendly cooling *** this review,in addition to introducing the fundamentals of the basic theory of radiative cooling technology,typical radiative cooling materials alongside their cooling effects over recent years are summarized and the current research status of radiative cooling materials is outlined and ***,technical challenges and potential advancements for radiative cooling are forecast with an outline of future application scenarios and development *** the future,radiative cooling is expected to make a significant contribution to global energy saving and emission reduction.

关键词： photonic structures radiative cooling energy saving and emission reduction carbon neutrality

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5776-5790页

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： Adaptation models Transformers Data models Correlation Circuits and systems Electronic mail Robustness Uncertainty Training Complexity theory

来源：评论

学校读者我要写书评

暂无评论

M-segclip: Enhancing SegCLIP with RM-MLP for Open-Vocabulary Semantic Segmentation 2

M-segclip: Enhancing SegCLIP with RM-MLP for Open-Vocabulary...

引用

2nd International Conference on Algorithm, Image Processing and Machine Vision, AIPMV 2024

作者： Zhang, Yuhang Che, Yanqiu Li, Shanshan Wang, Ruofan School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing & Intelligent Control Tianjin China School of Information Technology Engineering Tianjin University of Technology and Education Tianjin China

ISBN: (纸本)9798350390254

With the emergence of large-scale visual language models represented by CLIP, we have broken the great divide between vision and language. It has become possible to project features from visual models to semantic space consisting of a large amount of text. At the same time, semantic segmentation has opened the door to transferring learned visual knowledge to open vocabulary semantic segmentation. In this paper we improve and optimize a model with open vocabulary segmentation capability based on the CLIP architecture, we design an RM-MLP module and insert this module after the semantic group module in the image encoder, which is used to optimize the semantic regions aggregated by the semantic group module, and then used to generate the final segmentation results. The final experimental results show that the optimized model achieves higher segmentation accuracy on PASCAL VOC 2012 (+1.14% mIoU), and COCO (+0.43% mIoU). © 2024 IEEE.

关键词： Semantic Segmentation

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：