检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Xinghao Liu, Xuefeng Niu, Jianwei Zhu, Guogang Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China Jindal School of Management University of Texas Dallas United States

Personalized federated learning (PFL) reduces the impact of non-independent and identically distributed (non-IID) data among clients by allowing each client to train a personalized model when collaborating with others. A key question in PFL is to decide which parameters of a client should be localized or shared with others. In current mainstream approaches, all layers that are sensitive to non-IID data (such as classifier layers) are generally personalized. The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration. However, we believe that this approach is too conservative for collaboration. For example, for a certain client, even if its parameters are easily influenced by non-IID data, it can still benefit by sharing these parameters with clients having similar data distribution. This observation emphasizes the importance of considering not only the sensitivity to non-IID data but also the similarity of data distribution when determining which parameters should be localized in PFL. This paper introduces a novel guideline for client collaboration in PFL. Unlike existing approaches that prohibit all collaboration of sensitive parameters, our guideline allows clients to share more parameters with others, leading to improved model performance. Additionally, we propose a new PFL method named FedCAC, which employs a quantitative metric to evaluate each parameter's sensitivity to non-IID data and carefully selects collaborators based on this evaluation. Experimental results demonstrate that FedCAC enables clients to share more parameters with others, resulting in superior performance compared to state-of-the-art methods, particularly in scenarios where clients have diverse distributions. The code is integrated into our FL training framework: https://***/kxzxvbk/Fling. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual Perception Framework for Unmanned Aerial Vehicles: Challenges and Approaches

A Novel Visual Perception Framework for Unmanned Aerial Vehi...

引用

2021 China Automation Congress, CAC 2021

作者： Li, Xuan Duan, Haibin Mo, Hong Wang, Fei-Yue Department of Mathematics and Theories Peng Cheng Laboratory Shenzhen518055 China The State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical Engineering Beihang University Beijing100083 China The School of Electrical and Information Engineering Changsha University of Science and Technology Changsha410114 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781665426473

Change detection (CD) is an important preprocessing process in visual perception. Due to the difficulties of collection and labeling images in water scnens, the design and validation of the change detection algorithm is more difficult than expected. In this paper, we present a novel visual perception framework based on parallel vision for unmanned aerial vehicle (UAV). The visual perception framework consists of artificial scenes, computational experiments and parallel execution. In artificial scenes, we construct a water scene and automatically generated pixel-level image annotation. Next, computational experiments are carried out on different domain dataset. The experiment results show that: 1) mixed images effectively improve the performance of change detection model;2) domain shift problems still greatly affect the algorithm performance. © 2021 IEEE

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic targets searching assistance based on virtual camera priority

引用

virtual reality & Intelligent Hardware 2021年第6期3卷 484-500页

作者： Zixiang ZHAO Quanwei ZHOU Xiaoguang HAN Lili WANG State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Biomedical Engineering Beihang UniversityBeijing 100191China Department of Mathematics and Theories Peng Cheng LaboratoryShenzhen 518052China The Chinese University of Hong Kong Shenzhen 999077China Shenzhen Research Institute of Big Data Shenzhen 999077China

Background When a user walks freely in an unknown virtual scene and searches for multiple dynamic targets,the lack of a comprehensive understanding of the environment may have a negative impact on the execution of virtual reality *** studies can help users with auxiliary tools,such as top view maps or trails,and exploration guidance,for example,automatically generated paths according to the user location and important static spots in virtual ***,in some virtual reality applications,when the scene has complex occlusions,and the user cannot obtain any real-time position information of the dynamic target,the above assistance cannot help the user complete the task more *** We design a virtual camera priority-based assistance to help the user search dynamic targets *** of forcing users to go to destinations,we provide an optimized instant path to guide them to places where they are more likely to find dynamic targets when they ask for *** assume that a certain number of virtual cameras are fixed in virtual scenes to obtain extra depth maps,which capture the depth information of the scene and the locations of the dynamic *** method automatically analyzes the priority of these virtual cameras,chooses the destination,and generates an instant path to assist the user in finding the dynamic *** method is suitable for various virtual reality applications that do not require manual supervision or *** A user study is designed to evaluate the proposed *** results indicate that compared with three conventional navigation methods,such as the top-view method,our method can help users find dynamic targets more *** advantages include reducing the task completion time,reducing the number of resets,increasing the average distance between resets,and reducing user task *** We presented a method for improving dynamic target searching efficiency in virtual scenes by virtual cam

关键词： Searching assistance virtual environment Path guidance Redirection

来源：评论

学校读者我要写书评

暂无评论

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decoding Model for BCI Human-Machine Interaction

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decodi...

引用

Chinese Control Conference (CCC)

作者： Weidong Yan Zhaoliang Xu Yang Li The Department of Automation Science and Electrical Engineering Beihang University Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China

In this study, a multi-degree-of-freedom (Multi-DOF) robot (MDR) system based on a LightGBM-driven electroencephalogram (EEG) decoding model is designed and developed to assist subjects with hand motor dysfunction in their daily activities and neurorehabilitation. The system mainly consists of a motor imagery electroencephalogram (MI-EEG) evoking layer, an intention decoding layer, and an interaction executive layer. The MI-EEG evoking layer initially displays a virtual reality (VR) motion imagination scenario, instructing the subjects to imagine a real hand gripping movement, simultaneously collecting the electrical EEG signals and preprocessing the EEG signals. Secondly, in the intention decoding layer, a network combining temporal-spectral feature fusion and LightGBM (TSFF-LightGBM) for MI-BCI classification is used to more effectively boost brain decoding accuracy and decrease decoding time. Finally, in the interaction executive layer, the Multi-DOF wearable robot is developed to offer hand grasp motion kinesthetic feedback and visual feedback synced with MI. The following are the key benefits of the proposed MDR system: (1) We propose a new lightweight network structure more suitable for brain computer interface (BCI) interaction systems, achieving more accurate decoding and shorter identification time in different data sets, which helps to improve the practicability of the system and promote the practical clinical application of BCI rehabilitation technology. (2) We integrate BCI, VR, a wearable Multi-DOF robot, motion kinesthetic feedback, and visual feedback to improve human-machine interaction. Compared to the most recent investigations, the average accuracy of the MDR system on the publicly accessible datasets BCI IV 2a and HGD reached 75.89% and 93.53%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Head Convolution Network with Attention Consistency for Facial Expression Recognition

A Multi-Head Convolution Network with Attention Consistency ...

引用

Chinese Control Conference (CCC)

作者： Wenkang Liu Mingyi Sun Yang Li the Department of Automation Science and Electrical Engineering Beihang University Beijing China the Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China

In recent years, the demand for facial expression recognition applications has increased rapidly, and its research has received extensive attention from researchers. However, the current recognition methods based on deep learning ignore the idea of multiple head attention and semantic consistency, resulting in the model only paying attention to the local area of the feature map. In addition, the model's inconsistent attention to the images before and after the flip, resulting the poor robustness, poor interpretation, and other shortcomings in the model. To address the above problems, we propose an Affinity Separation Loss (ASLoss), which improves the separability of samples through clustering. Moreover, a Separate Multi-head Attention block (SMA), and a Zonal Loss (ZLoss) are also designed to decentralize the model's attention. Experimental results demonstrate that our proposed MACNet method achieves competitive recognition performance on two public datasets RAF-DB and FERPlus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing planar cubic B-spline curves with monotonic curvature for curve interpolation

引用

Computational Visual Media 2020年第3期6卷 349-354页

作者： Aizeng Wang Chuan He Fei Hou Zhanchuan Cai Gang Zhao School of Mechanical Engineering&Automation Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology&Systems Beihang UniversityBeijing 100191China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

Monotonic curvature plays an important role in industrial design and styling of curves with aesthetic shapes,e.g.,in automobile and aircraft design[1].Used in conventional parametric CAD/CAM systems,general B-splines are not adequate for aesthetic *** for the straight line and circle,monotonic curvature distribution,associated with pleasing shape,is very difficult to achieve.

关键词： curvature monotonic curves

来源：评论

学校读者我要写书评

暂无评论

Markerless Visual Servoing Using virtual Face Tag and Image Moment Invariants 4

Markerless Visual Servoing Using Virtual Face Tag and Image ...

引用

4th International Conference on robotics and Computer Vision, ICRCV 2022

作者： Zubair, Arif Fu, Yili Sohail, Amjad Khadija, Anwar Harbin Institute of Technology State Key Laboratory of Robotics and Systems Mechanical Engineering Department Harbin City China Space and Upper Atmosphere Research Commission Divisional Head TandD Hr Directorate General Karachi Pakistan Ned University of Engineering and Technology Industrial and Manufacturing Department Karachi Pakistan

ISBN: (数字)9781665481700

ISBN: (纸本)9781665481700

A novel normalized-centered image moment invariant-based visual servoing scheme is presented. A fresh combination of the moments invariants is proposed for planar symmetrical objects that are parallel to the image plane at the desired position. The output of the face detection module in the image plane, that is a rectangle around the face is used as a virtual target, treated as a planar symmetrical object which always remains parallel to the image plane. The proposed method completely decouples the DoF and is 2D translation, rotation, and scaling invariant. It was experimentally validated on a real robotic arm using a haar cascade-based face detection system to accomplish visual servoing tasks for both 2D printed faces and actual 3D faces. Unlike traditional deep learning based visual servoing schemes, the proposed markerless visual servoing technique does not require a 3D model of the face or a reference image/pose at the desired position and it can also work with unfamiliar faces without prior training. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

VISUAL GROUNDING WITH TRANSFORMERS

arXiv

引用

arXiv 2021年

作者： Du, Ye Fu, Zehua Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University China

In this paper, we propose a transformer based approach for visual grounding. Unlike existing proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage detector by fusing textual embeddings, our approach is built on top of a transformer encoder-decoder and is independent of any pretrained detectors or word embedding models. Termed as VGTR - Visual Grounding with TRansformers, our approach is designed to learn semantic-discriminative visual features under the guidance of the textual description without harming their location ability. This information flow enables our VGTR to have a strong capability in capturing context-level semantics of both vision and language modalities, rendering us to aggregate accurate visual clues implied by the description to locate the interested object instance. Experiments show that our method outperforms state-of-the-art proposal-free approaches by a considerable margin on four benchmarks. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

arXiv

引用

arXiv 2021年

Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to generate more complete and precise pseudo masks for segmentation. In this study, we propose weakly-supervised pixel-to-prototype contrast that can provide pixel-level supervisory signals to narrow the gap. Guided by two intuitive priors, our method is executed across different views and within per single view of an image, aiming to impose cross-view feature semantic consistency regularization and facilitate intra(inter)-class compactness(dispersion) of the feature space. Our method can be seamlessly incorporated into existing WSSS models without any changes to the base networks and does not incur any extra inference burden. Extensive experiments manifest that our method consistently improves two strong baselines by large margins, demonstrating the effectiveness. Specifically, built on top of SEAM, we improve the initial seed mIoU on PASCAL VOC 2012 from 55.4% to 61.5%. Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70.8% to 73.6%, achieving new state-of-the-art. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A maintenance time prediction method based on modular arrangement of predetermined time standard and maintenance interfaces 30th

A maintenance time prediction method based on modular arrang...

引用

30th European Safety and Reliability Conference, ESREL 2020 and 15th Probabilistic Safety Assessment and Management Conference, PSAM15 2020

作者： Dai, Chao Zhou, Dong Fan, Yu Zhang, Huan Zhao, Dianxin State Key Laboratory of Virtual Reality Technology and Systems Beijing China School of Reliability and Systems Engineering Beihang University Beijing China ShenyangAircraftDesigned and Research Institute Shenyang China

ISBN: (纸本)9789811485930

As an important quantitative of the design of maintenance, maintenance time is of great importance for both military and civil products. On the one hand, long maintenance time will lead to the reduction of the rate of success for some military mission. On the other hand, it will result in the increase of the consumption of human and material resources, which contribute to high running cost of some commercial enterprise like airlines. Therefore, how to accurately predict the maintenance time of the product in design stage is a matter of cardinal significance. Currently, there are two main methodologies to predict the maintenance time in the design stage, the predictive method based on statistical and historical data, and the measurement method based on virtual reality and Predetermined Time System (PTS)(Dong, Le, and Chuan 2013)(Wu, Zhou, and Liu 2018). The first kind methods are mainly applicable to the maintenance time prediction of electronic products rather than mechanical products, due to the statistical data of the former is easier to obtain. The other kind of methods are available all kinds of products, on paper unfortunately. Because PTS originated from production line operation, and is unable to cope with complex maintenance operations. In this paper, we propose a new maintenance time prediction method, in which the maintenance time is divided into approach time, posture adjustment time and maintenance operation time. Further, we innovatively decompose specific maintenance operations into maintenance interfaces (fasteners, connectors, etc.). The approach and osture adjustment time are calculated by Modular arrangement of predetermined time standard (MODAPTS)(Heyde 1983), and the complex maintenance operation time is obtained by accumulating the standard time of maintenance interface. Then, considering the complexity of maintenance operation, we introduce four maintainability attributes to correct the maintenance time. At the end of the paper, an experimental

关键词： Ergonomics

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：