检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yan Huang Zhang Zhang Qiang Wu Yi Zhong Liang Wang Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Chinese Academy of Sciences Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences (UCAS). School of Electrical and Data Engineering University of Technology Sydney Australia School of Information and Electronics Beijing Institute of Technology China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In various domains such as surveillance and smart retail, pedestrian retrieval, centering on person re-identification (Re-ID), plays a pivotal role. Existing Re-ID methodologies often overlook subtle internal attribute variations, which are crucial for accurately identifying individuals with changing appearances. In response, our paper introduces the Attribute-Guided Pedestrian Retrieval (AGPR) task, focusing on integrating specified attributes with query images to refine retrieval results. Although there has been progress in attribute-driven image retrieval, there remains a notable gap in effectively blending robust Re-ID models with intra-class attribute variations. To bridge this gap, we present the Attribute-Guided Transformer-based Pedestrian Retrieval (ATPR) framework. ATPR adeptly merges global ID recognition with local attribute learning, ensuring a co-hesive linkage between the two. Furthermore, to effectively handle the complexity of attribute interconnectivity, ATPR organizes attributes into distinct groups and applies both inter-group correlation and intra-group decorrelation regularizations. Our extensive experiments on a newly estab-lished benchmark using the RAP dataset [32] demonstrate the effectiveness of ATPR within the AGPR paradigm.

关键词： Couplings Pedestrians Correlation Surveillance Image retrieval Focusing Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

A Swing-Up and Stable Control Strategy for Pendubot Based on Nonlinear Model Predictive Method

A Swing-Up and Stable Control Strategy for Pendubot Based on...

引用

Chinese Automation Congress (CAC)

作者： Lejun Wang Yiqin Liu Ruihuan Zhang Zixin Huang Zhen Cai School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China School of Information Engineering Wuhan City Polytechnic Wuhan China

The control objective of Pendubot is to stabilise the system in a vertically upward position by swinging up from a vertically downward position. Facing various physical constraints in practical applications, this paper proposes a swing-up stabil-isation control strategy based on a nonlinear model prediction method to accomplish the above control objective. On the basis of the system dynamics model, the forward Euler method is used to construct a nonlinear prediction model of the system. According to the control objectives and physical constraints of the system, the performance index function is designed, and then the control inputs of each sampling cycle are obtained through rolling optimisation and feedback correction, so that the system state gradually converges to the target trajectory, thus achieving the motion control objective. Based on the simulation results, it can be seen that the strategy proposed in this paper is efficient and robust under external disturbances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?

arXiv

引用

arXiv 2024年

作者： Lin, Ziqin Li, Heng Li, Zinan Fu, Huazhu Liu, Jiang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Institute of High Performance Computing Agency for Science Technology and Research Singapore Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues. Copyright © 2024, The Authors. All rights reserved.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning

arXiv

引用

arXiv 2024年

作者： Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaiane, Osmar Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China Amii University of Alberta EdmontonAB Canada

Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art (SOTA) methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24%. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Motion Control Strategy Based on Integrated Trajectory for the Pendubot

Motion Control Strategy Based on Integrated Trajectory for t...

引用

European Control Conference (ECC)

作者： Lejun Wang Xuzhi Lai Pan Zhang Min Wu School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

The control objective of a Pendubot is always to swing its endpoint up from the vertical downward equilibrium point (VDEP) and to stay it at the vertical upward equilibrium point (VUEP). This paper proposes a motion control approach based on the integrated trajectory to achieve the above control objective with only one controller. First, an integration trajectory with two parts is designed for the Pendubot. We plan the first part trajectory with variable parameters, and optimize these variable parameters by applying the genetic algorithm (GA) to make all links move simultaneously from their starting states to their target states. We plan the second part trajectory to make all links remain at the target states. Then, we build the linear time-varying error system based on the integration trajectory, and design a global tracking controller by using the linear system control method to track the integration trajectory. By this way, the control objective of the Pendubot is realized. Finally, the simulations illustrate the validity and superiority of the proposed method.

关键词： Linear systems Target tracking Torque Simulation Europe Control systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Extended Kalman Filter for UAV Monitoring System

Event-triggered Extended Kalman Filter for UAV Monitoring Sy...

引用

Data Driven Control and Learning systems (DDCLS)

作者： Yunge Zang Yan Li Yuting Duan Xiangyu Li Xi Chang Zhen Li Beijing Aerospace Automatic Control Institute Beijing P. R. China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing P. R. China Beijing Aerospace Institute for Metrology and Measurement Technology Beijing P. R. China Key Laboratory for Intelligent Control … Decision on Complex Systems School of Automation Beijing Institute of Technology Beijing China

To facilitate ground station monitoring and command uploading, unmanned aerial vehicles (UAVs) need to frequently exchange individual state data between units. However, this results in a significant usage of communication bandwidth. To address this issue, on the basis of an event-triggered strategy, this paper proposes an Extended Kalman Filter (EKF). aimed at reducing the communication burden of UAVs while maintaining high accuracy. Specifically, a state measurement triggered by an event is selected for filtering only if it contains innovation, thereby reducing the amount of data that needs to be communicated. Since UAV systems are nonlinear, EKF is adopted to fully utilize the information obtained from event-triggered strategies, thereby enhancing the estimation performance. In this paper, a physical UAV was used to verify the proposed algorithm, and it proved to have robust dynamic performance and to effectively reduce the communication rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Based and Data-Driven Control of Event- and Self-Triggered Discrete-Time LTI systems

arXiv

引用

arXiv 2022年

作者： Wang, Xin Berberich, Julian Sun, Jian Wang, Gang Allgöwer, Frank Chen, Jie The Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing10081 China The Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China The University of Stuttgart Institute for Systems Theory and Automatic Control Stuttgart70550 Germany The Department of Control Science and Engineering Tongji University Shanghai201804 China The State Key Lab of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

The present paper considers the model-based and data-driven control of unknown linear time-invariant discretetime systems under event-triggering and self-triggering transmission schemes. To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived. Combining the model-based condition with a recent data-based system representation, a data-driven stability criterion in the form of linear matrix inequalities (LMIs) is established, which also offers a way of co-designing the ETS matrix and the controller. To further alleviate the sampling burden of ETS due to its continuous/periodic detection, a self-triggering scheme (STS) is developed. Leveraging pre-collected input-state data, an algorithm for predicting the next transmission instant is given, while achieving system stability. Finally, numerical simulations showcase the efficacy of ETS and STS in reducing data transmissions as well as of the proposed co-design methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Research on Attention-Based Predictive Model in Multi-Agent Reinforcement Learning

Research on Attention-Based Predictive Model in Multi-Agent ...

引用

Chinese Automation Congress (CAC)

作者： Weixin Hong Huaiyu Wu Zhen Shen Gang Xiong Bin Hu Xisong Dong Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Agent actions planning is a challenging problem in multi-agent reinforcement learning. Recent methods typically build their predictive models by full connection layers, but the shortage of utilizing action and observation information in complex multi-agent environment limits the performance of those methods. To address this issue, we propose a novel predictive model based on self-attention mechanism which can effectively use information in the environment. Specifically, we use the MADDPG algorithm to make a dataset where the input is the observations and actions and the output is the predicted observations and rewards. We also introduce the multi-head attention mechanism into the predictive model so that the predictive model can better combine different information for prediction. We perform extensive experiments to assess the proposed method and compare it with the representative baseline approach. Results demonstrate that our method outperforms competitors with higher accuracy in different tasks. Our implementation will be publicly available.

关键词： Automation Reinforcement learning Predictive models Prediction algorithms Planning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Research on robot path planning based on multi-strategy genetic ant colony optimization algorithm

引用

Information Sciences 2025年 718卷

作者： Li, Zheng Du, Mingyuan Qin, Jinlei Chen, Xuechao Department of Computer North China Electric Power University Baoding071003 China Hebei Key Laboratory of Knowledge Computing for Energy & Power Baoding071003 China Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education Baoding071003 China

The ant colony optimization (ACO) algorithm is commonly used for path planning but faces issues like slow convergence, a tendency to get trapped in local optima, and instability in performance. This paper presents the multi-strategy genetic ant colony optimization (MSGACO) algorithm, which enhances ACO through several innovations: adaptive pheromone distribution initialization, a three-level node selection mechanism, a direction heuristic function, a selective crossover mechanism, and an elitist selection strategy. The adaptive pheromone distribution initialization, combined with the three-level node selection mechanism and direction heuristic function, increases the selection probability for nodes nearer to the destination. Additionally, the selective crossover mechanism and elitist selection strategy optimize the searched paths, resulting in more high-quality solutions and allocating pheromones to them. The main parameters of these strategies are optimized, and their effectiveness is verified. To showcase the benefits of MSGACO, experiments are performed utilizing five exemplary environmental models, with comparisons made to existing methodologies. The results showed a reduction of approximately 60.7% in path length and 52% in convergence iterations compared to the traditional ant colony optimization algorithm. © 2025 Elsevier Inc.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Dual-mode FMF to SOI chip edge coupler

Dual-mode FMF to SOI chip edge coupler

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Weilun Zhang Mengyuan Ye Yunlong Li School of Automation China University of Geosciences Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

Dual-mode edge coupler for few mode fiber (FMF) to silicon chip is proposed. LP 01 and LP 11 d coupler in simulation.

ISBN: (纸本)9781665410953

Dual-mode edge coupler for few mode fiber (FMF) to silicon chip is proposed. LP 01 and LP 11 d coupler in simulation.

关键词： Multiplexing Couplings Simulation Optical fiber couplers Crosstalk Couplers Silicon

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：