检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Chen, Zhe Zhang, Jing Tao, Dacheng UBTECH Sydney Artificial Intelligence Centre School of Computer Science Faculty of Engineering and Information Technologies University of Sydney 6 Cleveland St DarlingtonNSW2008 Australia School of Software and Advanced Analytics Institute University of Technology Sydney 15 Broadway UltimoNSW2007 Australia School of Automation Hangzhou Dianzi University

Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises. However, the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR Adaptation-aided Road Detection (PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation;and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-the-art road detection models and is currently top of the publicly accessible benchmark leader-board. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Improving Referring Expression Comprehension by Suppressing Expression-unrelated Proposals

Improving Referring Expression Comprehension by Suppressing ...

引用

Electronic Information engineering and computer Technology (EIECT), International Conference on

作者： Qun Wang Feng Zhu Xiang Li Ruida Ye Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Faculty of Computer Science and Engineering Northeastern University Shenyang China Department of Aerospace Engineering and Technology Space Engineering University Beijing China

The prevailing referring expression comprehension (REC) method is based on two stages: 1) detecting multiple candidate proposals using an object detector and 2) aligning proposals with text descriptions. Existing two-stage models have achieved significant improvements with excellent alignment modules. However, their alignment modules treat each proposal equally without filtering expression-unrelated proposals. These expression-unrelated proposals may interfere with the alignment modules’ ability to accurately reason about the target proposal. These proposals also increase the difficulty of training alignment modules. To solve this problem, we propose a new framework, that can suppress expression-unrelated proposals for alignment modules. Specifically, we first design a suppression module, which calculates the relevance scores between the proposals and the expression by using the semantics in the expression. Then, these scores are integrated into three basic alignment modules, including subject, location, and relationship modules, to guide each module to focus on the expression-related proposals. We conduct extensive experiments on three benchmark datasets, and the results show the effectiveness of our suppression module and performance improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical super-resonances in dielectric microsphere particles

arXiv

引用

arXiv 2022年

作者： Wang, Zengbo Luk’yanchuk, Boris Wu, Baidong Yan, Bing Assel, Ahmetova Yaminsky, Igor Yu, Haibo Liu, Lianqing School of Computer Science and Electronic Engineering Bangor University Dean Street Gwynedd BangorLL57 1UT United Kingdom Faculty of Physics Lomonosov Moscow State University Moscow119991 Russia State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China

Extreme field localization and giant field enhancement are often achieved by using plasmonic nanostructures and metamaterials such as strongly coupled silver nanoparticles. Dielectric particles and structures can focus light beyond the diffraction limit (photonic nanojet effect), but with much weaker strengths. Recently, we showed that dielectric microspheres could support high-order Mie resonance modes (‘super-resonance modes’), that can generate similar level of electric field intensity enhancement as plasmonic structures on the order of 104- 107. In this work, we aim to further advance our understanding of the super-resonance modes. New results on the effects of size parameter and refractive index on optical super-resonances across a wide parameter range and with improved numerical accuracies is presented. The results suggest that the electric field intensity enhancement could reach a record high level of 109-1011 at specific conditions that surpass plasmonic enhancements. Moreover, super-resonance-enabled focusing by microsphere lens under different lighting sources (e.g., different color LEDs or lasers, halogen lamps) is investigated and compared for the first time. These results are important in understanding the super-resolution mechanism for microsphere nanoscopy and will find numerous potential applications in photonics. © 2022, CC BY.

关键词： Microspheres

来源：评论

学校读者我要写书评

暂无评论

The use of cognitive maps in product development

The use of cognitive maps in product development

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Robert Demeter Attila Kovari Jozsef Katona Ilona Heldal Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania CogInfoCom Based LearnAbility Research Team Institute of Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Faculty of Psychology and Educational Sciences Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The aim of this study is to view product traceability using graph-based simulation software, which gives us a cognitive map of a product's path. In this paper, we present a method for manufacturers to efficiently and automatically visualize all components of their products, allowing for multiple changes or fault event in the supply chain.

关键词： Conferences Cognition Education Tools Product development Informatics

来源：评论

学校读者我要写书评

暂无评论

Examination of Gaze Fixations Recorded during the Trail Making Test

Examination of Gaze Fixations Recorded during the Trail Maki...

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Attila Kovari Jozsef Katona Ilona Heldal Carsten Helgesen Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Robert Demeter CogInfoCom Based LearnAbility Research Team Institute of Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Faculty of Psychology and Educational Sciences Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The continuous visual tracking of activity performed in perception and action activities requires continuous eye motion. The visual computer monitoring, recording and evaluation of human motion provides many opportunities in the development of human-computer interfaces. In most activities performed by humans, eye-hand coordination plays a significant role. From the eye-hand coordination aspect, the fixation's direction is an essential factor, since before touching an object, the look is aimed at the object to be touched for a longer period. In this paper, the fixation playing a major role in eye-hand coordination is being analyzed during the Trail Making Test. The test primarily aims to measure visual searching or scanning, visual-spatial sequencing; however, the eye-hand coordination's speed plays a key role in the quick and accurate execution of the test. During the test, eye motion parameters were recorded and determined, where further analyses make certain human cognitive factors indirectly able to be analyzed.

关键词： Tracking Task analysis Conferences Visualization Software Testing Cognition

来源：评论

学校读者我要写书评

暂无评论

Synergy Analysis of Industrial, Research and University Training Centers Collaboration: A Case Study in Thailand's Eastern Economic Corridor

Synergy Analysis of Industrial, Research and University Trai...

引用

Portland International Conference on Management of engineering and Technology (PICMET)

作者： Udom Lewlomphaisarl Ukrit Pungjitwisut Wassana Pullpol Kumpee Suksomboon Arnuphap Dowrueng Industrial IoT and Automation Research Group (IIARG) Sustainable Manufacturing Center (SMC) Eastern Economic Corridor of Innovation (EECi) Rayong Thailand EEC Automation Park Faculty of Engineering Burapha University Chonburi Thailand Intelligent SCADA Technology Research Team (IST) Advanced Control and Electronics Research Group (ACERG) National Electronics and Computer Technology Center (NECTEC) Pathum Thani Thailand National Electronics and Computer Technology Center (NECTEC) National Science and Technology Development Agency (NSTDA) Pathum Thani Thailand

The Royal Thai Government has outlined a 20-year strategy to achieve high-income status by 2036. “Thailand 4.0” is guided by the concept of “Industry 4.0”, which aims to transform the country into an innovative, value-driven industry, with a focus on 12 areas such as automation & Robotics, Aviation & Logistics, Biofuel & Biochemicals, and Digital. The development of Eastern Economic Corridor (EEC) lies at the heart of Thailand 4.0 scheme. The EEC is an area-based development initiative aimed at revitalizing the prestigious East Coast, where numerous business developers have experienced a rewarding investment journey and exceptional success over the past 30 *** paper introduces a synergy analysis of the 3-phase collaboration approach between the EEC automation Park located on the campus of Burapha University as the main university in the EEC and the Sustainable Manufacturing Center (SMC) at automation Robotics and Intelligent System (ARIPOLIS) in Eastern Economic Corridor of Innovation (EECi) with strong partners from industry e.g. Mitsubishi Electric Factory automation (Thailand) Limited. This 3-phase approach:}{1. Build an island demonstrator, 2. Link production demonstration lines and 3. Transfer to 100 factories in the EEC helps managers realize possible difficulties and systematically prepare solutions in advance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Geometrical Features of Photospheric Bright Points in the Quiet-Sun Region

Analysis of the Geometrical Features of Photospheric Bright ...

引用

第三十二届中国控制会议

作者： Lan Yu Linhua Deng Song Feng Department of Information Engineering Yunnan Land and Resources Vocation College Key Laboratory of Modern Astronomy and Astrophysics(Nanjing University) Ministry of Education National Astronomical Observatories/ Yunnan Astronomical Observatory Chinese Academy of Sciences Graduate University of Chinese Academy of Sciences Computer Technology Application Key Lab of Yunnan Province and Faculty of Information Engineering and Automation Kunming University of Science and Technology

ISBN: (纸本)9781479900305

The Solar Granulation is an ubiquitous structure in the quiet *** brighter features called "Photospheric Bright Points(PBPs)" are found within inter-granules in G-band images *** are the small-scale feature on the solar *** their characteristics may reveal the significant problems such as coronal hearting,local dynamo theory and the relation of magnetic *** the presented paper,we utilized Laplacian and morphological dilation(LMD) technique to detect and extract PBPs within inter-granular lanes.A data set has been taken with the Dutch Open Telescope(DOT) on July 2, *** was employed to analyze the geometrical feature of *** statistical distributions of PBPs were obtained by the proposed *** diameter distribution of PBPs is consistent with lognormal *** peak diameter occurs at about *** histogram of geometrical features is derived from the PBPs *** distribution of eccentricity indicates that approximately 50%PBPs have a near circular,the average eccentricity occurs at *** distribution accords with an Exponential fit.

关键词： Photospheric Bright Points Laplacian morphological dilation eccentricity Sun

来源：评论

学校读者我要写书评

暂无评论

Optimizing Neural Network Image Classification with Fractional Order Gradient Methods

SSRN

引用

SSRN 2023年

作者： Zhao, Haiming Chen, Jiejie Jiang, Ping Zeng, Zhigang Fan, Rui Yang, Honggang School of Computer and Information Engineering Hubei Normal University Huangshi435000 China School of Automation Wuhan University of Technology Wuhan430000 China School of Computer Hubei PolyTechnic University Huangshi435000 China Faculty of Artificial Intelligence Education Central China Normal University Wuhan430000 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430000 China

As deep learning technology increasingly permeates various fields, the significance of optimization algorithms in neural network training has become more prominent. Typically, the training of deep learning networks relies on gradient descent optimizers based on calculus computations. Traditional integer-order calculus optimizers often fall short when dealing with complex and subtle data. To overcome these limitations, we innovatively utilized the Grünwald-Letnikov and Caputo definitions of fractional calculus to develop two new optimization algorithms: Fractional Order Adagrad (FAdagrad) and Fractional Order Adam (FAdam). These algorithms have been proven to converge to extremal points.A key advantage of our methods is their capability in handling complex, high-dimensional tasks, such as artistic painting image classification, where they exhibit exceptional performance in recognizing and processing subtle differences. The robustness and adaptability of these algorithms were further validated through experiments on the CIFAR-100 dataset. The results demonstrate the efficacy of fractional order optimizers in enhancing training efficiency and accuracy. © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A quantitative study of using Cisco Packet Tracer simulation software to improve IT students’ creativity and outcomes

A quantitative study of using Cisco Packet Tracer simulation...

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Robert Demeter Attila Kovari Jozsef Katona Ilona Heldal Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania CogInfoCom Based LearnAbility Research Team Institute of Engineering Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The continued development of ICT technologies has led to new ways of information communication. As is well known, the success of any new training or communication technology incorporates disseminating information, timeliness and efficiency and often incorporates simulation and virtual reality technologies. This paper presents the results of a quantitative study showing that simulation-based training strategies are more effective than traditional methods. The current case is for applying didactic teaching methodologies for learning ICT concepts for complex systems. The paper also compares the results of this study with previous studies and recommends strategies for using virtual reality elements to streamline learning process of engineering students.

关键词： computer networks Software Tools Education Hardware Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Robust visual tracking using multi-frame multi-feature joint modeling

arXiv

引用

arXiv 2018年

作者： Zhang, Peng Yu, Shujian Xu, Jiamiao You, Xinge Jiang, Xiubao Jing, Xiao-Yuan Tao, Dacheng School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan Hubei China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States State Key Laboratory of Software Engineering School of Computer Wuhan University Wuhan430072 China School of Automation Nanjing University of Posts and Telecommunications Nanjing210023 China UBTech Sydney Artificial Intelligence Institute and the School of Information Technologies Faculty of Engineering and Information Technologies at the University of Sydney DarlingtonNSW2008 Australia

It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal consistency across consecutive frames and multiple feature cues in a unified model. Motivated by this idea, we propose a novel correlation filter-based tracker in this work, in which the temporal relatedness is reconciled under a multi-Task learning framework and the multiple feature cues are modeled using a multi-view learning approach. We demonstrate the resulting regression model can be efficiently learned by exploiting the structure of blockwise diagonal matrix. A fast blockwise diagonal matrix inversion algorithm is developed thereafter for efficient online tracking. Meanwhile, we incorporate an adaptive scale estimation mechanism to strengthen the stability of scale variation tracking. We implement our tracker using two types of features and test it on two benchmark datasets. Experimental results demonstrate the superiority of our proposed approach when compared with other state-of-The-Art trackers. MATLAB code is available from our project homepage http://***/ project/***. Copyright © 2018, The Authors. All rights reserved.

关键词： MATLAB

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：