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

ACP- based Circular target image Rotation normalization system 4

ACP- based Circular target image Rotation normalization syst...

引用

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： He, Jichang Zhang, Zhijia Zhao, Huaici Yang, Jiale School of Artificial Intelligence Shenyang Key Laboratory of Information Perception and Edge Computing Shenyang University of Technology Liaoning Shenyang China Shenyang Institute of Automation Liaoning Provincial Key Laboratory of Optoelectronic Information and Simulation Technology Liaoning Shenyang China

ISBN: (纸本)9798350326444

In certain visual detection tasks that focus on circular objects, especially for those with less distinctive features, the rotation of the circular object in the image often leads to significant errors in the detection results or even task failure. To adaptively locate the stable rotation normalization position of circular object images, this paper designs a circular object image rotation normalization system based on the Adaptive Circle Projection (ACP) algorithm, which can adaptively detect and rotate any circular object image to this position regardless of the rotation angle. Experimental results on multiple types of different objects show that the system can adaptively detect stable rotation normalization positions for 10 circular objects with any rotation angle. This paper also designs an image operation interface for the system to demonstrate its portability. © 2023 IEEE.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

A practical PID variable stiffness control and its enhancement for compliant force-tracking interactions with unknown environments

引用

Science China(Technological Sciences) 2023年第10期66卷 2882-2896页

作者： ZHANG Xin ZHOU Hao LIU JinGuo JU ZhaoJie LENG YuQuan YANG ChenGuang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China School of Computing University of PortsmouthPortsmouth PO13HEUK Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy EngineeringSouthern University of Science and TechnologyShenzhen 518055China Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Compliant interaction control is a key technology for robots performing contact-rich manipulation *** design of the compliant controller needs to consider the robot hardware because complex control algorithms may not be compatible with the hardware performance,especially for some industrial robots with low bandwidth *** paper focuses on effective and easy-to-use compliant control algorithms for position/velocity-controlled *** by human arm stiffness adaptation behavior,a novel variable target stiffness(NVTS)admittance control strategy is proposed for adaptive force tracking,in which a proportional integral derivative(PID)variable stiffness law is designed to update the stiffness coefficient of the admittance function by the force and position ***,its stability and force-tracking capability are theoretically *** addition,an impact compensator(Impc)is integrated into the NVTS controller to enhance its disturbance-suppression capability when the robot is subjected to strong vibration disturbances in complicated surface polishing *** proposed controllers are validated through four groups of experimental tests using different robots and the corresponding results demonstrate that they have high-accuracy tracking capability and strong adaptability in unknown environments.

关键词： compliant interaction control force tracking PID variable stiffness impact compensator unknown environments

来源：评论

学校读者我要写书评

暂无评论

Band engineering of valleytronics WSe_(2)–MoS_(2)heterostructures via stacking form,magnetic moment and thickness

引用

Chinese Physics B 2023年第10期32卷 45-49页

作者：吴彦玮张宗源马亮刘涛郝宁吕文刚龙明生单磊 Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Structure and Functional Regulation of Hybrid Materials of Ministry of EducationInstitutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China State Key Laboratory of Metastable Materials Science&Technology and Key Laboratory for Microstructural Material Physics of Hebei Province School of ScienceYanshan UniversityQinhuangdao 066004China Anhui Province Key Laboratory of Condensed Matter Physics at Extreme Conditions High Magnetic Field LaboratoryChinese Academy of SciencesHefei 230031China Beijing National center for Condensed Matter Physics Beijing Key Laboratory for Nanomaterials and NanodevicesInstitute of PhysicsChinese Academy of SciencesBeijing 100190China

Spin-valley polarization and bandgap regulation are critical in the developing of quantum ***,by employing the density functional theory,we investigate the effects of stacking form,thickness and magnetic moment in the electronic structures of WSe_(2)–MoS_(2)*** show that spin-valley polarization maintains in all *** thickness of 2H-MoS_(2)not only tunes the bandgap but also changes the degeneracy of the conduction band minimums(CBM)at K/K_(1) *** increase of micro magnetic moment tunes the bandgap and raises the valence band maximums(VBM)atΓ*** addition,the regulation of band gap by the thickness of 2H-MoS_(2)and introduced magnetic moment depends on the stacking *** suggest that WSe_(2)–MoS_(2)heterostructure supports an ideal platform for valleytronics *** methods also give new ways of optical absorption regulation in spin-valley devices.

关键词： valleytronics thickness stacking magnetic moment

来源：评论

学校读者我要写书评

暂无评论

Self-Evaluation of Large Language Model based on Glass-box Features

Self-Evaluation of Large Language Model based on Glass-box F...

引用

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

作者： Huang, Hui Qu, Yingqi Liu, Jing Yang, Muyun Xu, Bing Zhao, Tiejun Lu, Wenpeng Faculty of Computing Harbin Institute of Technology Harbin China Baidu Inc. Beijing China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China

ISBN: (纸本)9798891761681

The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods. Existing works primarily rely on external evaluators, focusing on training and prompting strategies. However, a crucial aspect - model-aware glass-box features - is overlooked. In this study, we explore the utility of glass-box features under the scenario of self-evaluation, namely applying an LLM to evaluate its own output. We investigate various glass-box feature groups and discovered that the softmax distribution serves as a reliable quality indicator for self-evaluation. Experimental results on public benchmarks validate the feasibility of self-evaluation of LLMs using glass-box features. © 2024 Association for Computational Linguistics.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

An approach for formation design and flight performance prediction based on aerodynamic formation unit:Energy-saving considerations

引用

Chinese Journal of Aeronautics 2024年第3期37卷 77-91页

作者： Nanxuan QIAO Tielin MA Xiangsheng WANG Jie WANG Jingcheng FU Pu XUE School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China Institute of Unmanned System Beihang UniversityBeijing 100191China Key Laboratory of Advanced Technology of Intelligent Unmanned Flight System Ministry of Industry and Information TechnologyBeijing 100191China School of Transportation Science and Engineering Beihang UniversityBeijing 102206China Beijing Institute of Space Long March Vehicle Beijing 100076China

The performance improvement of swarm drones through aerodynamic shape optimization may be challenging due to folded size constraints imposed by the specific launch ***,fixed-wing aircraft swarms can benefit from formation flight in terms of energy *** study introduces the concept of the"aerodynamic formation unit",which consists of two or three aircraft that form an inseparable unit of the *** the Unmanned Aerial Vehicle(UAV)distribution and wingtip vortex interference in the formation,two typical aerodynamic formation units are optimized by the variable-fidelity aerodynamic optimization method based on space *** aerodynamic characteristics of the formation UAVs that affect flight performance,such as lift-to-drag ratio(L/D ratio)and static stability are analyzed by Computational Fluid Dynamics(CFD)*** L/D ratio(cruising condition)of the following aircraft can be increased by 22.8%and 57.5%in the optimal units that involve two and three aircraft ***,this study conducts several CFD simulations for multi-aircraft formations formed by the units,which show that the average L/D ratio of the formation can be improved by more than 19%.These results verify the feasibility and effectiveness of the"aerodynamic formation unit"concept and the optimization framework for formation parameters.

关键词： Formation flight CFD Aerodynamic formation unit Wingtip vortices Foldable tandem-wing aircraft

来源：评论

学校读者我要写书评

暂无评论

Application Analysis and Development Recommendations for the Generative Adversarial Networks in Enhancing Automobile Data Security 5

Application Analysis and Development Recommendations for the...

引用

5th International Conference on Computer Engineering and intelligent Control, ICCEIC 2024

作者： Ji, Haojie Yao, Yuchi Chen, Yupeng He, Peng Wang, Jingyan Wang, Jiangyue Tian, Liangliang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China Ministry of Education Beijing Information Science & Technology University Key Laboratory of Modern Measurement & Control Technology Beijing China China Automotive Engineering Research Institute Co. Ltd Chongqing China

ISBN: (纸本)9798331507992

The security of data generated by vehicles during operation is critically important, especially as the number of intelligent and connected vehicle users continues to rise, leading to the rapid increase of automobile communication data. In response, researchers have employed GAN s to address data security challenges within this domain, achieving significant outcomes. This paper primarily focuses on personal information identification, data desensitization, and secure transmission of data within the framework of automobile data security. The latest research on GAN s is reviewed and analyzed to assess the feasibility, strengths, and limitations for automotive data security, and the insights into future development recommendations are also provided in this domain. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Global Mean Square Error Separation Loss 4

Global Mean Square Error Separation Loss

引用

2022 4th International Conference on Artificial Intelligence and Computer Science, AICS 2022

作者： Hou, Yun Key Laboratory of Agile Intelligent Computing Southwest China Institute of Electronic Technology Sichuan Chengdu China

Class imbalance problem greatly affects the accuracy of deep-learning-based object detectors. To weaken its influence, this paper proposes a global mean square error separation loss (GMSES Loss). GMSES Loss assigns a factor to each example, and then enhances the learning of hard-to-learn examples by reducing the factors of easy-to-learn examples. Meanwhile, the global mean square error separation method is introduced to enhance the learning of foreground classes. To verify the effectiveness of our algorithm, experiments are conducted with YOLOv4 and RetinaNet as the baselines, respectively. The results have shown that our loss function can improve the performance of one-stage object detectors without adding any extra hyperparameters. © 2022 institute of Physics Publishing. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

An Improved RRT Algorithm Based on Heuristic Function Strategy for Manipulator Path Planning

An Improved RRT Algorithm Based on Heuristic Function Strate...

引用

第43届中国控制会议

作者： Guoyu Zuo Haishan Guan Banggui Zheng Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computing Intelligence and Intelligent Systems

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Manipulator path planning refers to planning the movement trajectory of a manipulator through algorithms and techniques to realize accurate and efficient *** is widely used in industrial production lines,medical surgeries,and other *** sampling-based rapid exploration random tree(RRT) algorithm has been widely used in high-dimensional manipulators due to its probabilistic completeness and outstanding ***,the algorithm is purely random in the sampling session,which leads to the existing RRT planning algorithms still having low planning efficiency and poor path *** solve these problems,this paper proposes a new and improved method,which assigns a cost value to the sampling points and bases the selection of sampling points on the cost value,so that the growth of the path tree can be oriented to the goal point more quickly.A new evaluation metric,i.e.,the average angle of each node in the path,is also designed to evaluate the quality of the path,and the smoother the path is,the more the metric converges to 180°.By comparing our improved RRT algorithm with the original algorithm in several different scenarios,the results show that our improvement possesses shorter running time,shorter path length,and larger average angle of path.

关键词： Path planning RRT algorithm Heuristic function

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：