检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

616 篇 会议
7 册 图书
5 篇 期刊文献

馆藏范围

628 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

380 篇 工学
- 326 篇 计算机科学与技术...
- 231 篇 软件工程
- 96 篇 信息与通信工程
- 64 篇 控制科学与工程
- 61 篇 生物工程
- 48 篇 生物医学工程（可授...
- 42 篇 电气工程
- 37 篇 仪器科学与技术
- 27 篇 光学工程
- 27 篇 石油与天然气工程
- 23 篇 化学工程与技术
- 20 篇 电子科学与技术（可...
- 19 篇 机械工程
- 13 篇 环境科学与工程（可...
- 13 篇 安全科学与工程
- 12 篇 交通运输工程
198 篇 理学
- 104 篇 数学
- 66 篇 生物学
- 46 篇 化学
- 32 篇 物理学
- 26 篇 统计学（可授理学、...
- 16 篇 系统科学
101 篇 管理学
- 71 篇 图书情报与档案管...
- 58 篇 管理科学与工程(可...
- 21 篇 工商管理
41 篇 医学
- 23 篇 临床医学
- 18 篇 基础医学(可授医学...
- 15 篇 药学(可授医学、理...
- 15 篇 特种医学
14 篇 法学
- 11 篇 社会学
9 篇 教育学
8 篇 农学
7 篇 经济学
1 篇 艺术学

主题

53 篇 pattern recognit...
23 篇 computer vision
16 篇 image segmentati...
16 篇 data mining
16 篇 layout
15 篇 optical computin...
15 篇 shape
14 篇 deep learning
14 篇 feature extracti...
12 篇 pattern matching
11 篇 concurrent compu...
11 篇 machine learning
10 篇 face recognition
10 篇 image motion ana...
10 篇 image analysis
9 篇 object detection
9 篇 neural networks
9 篇 cameras
9 篇 edge computing
9 篇 cloud computing

机构

32 篇 shenyang institu...
27 篇 university of ch...
21 篇 shenyang institu...
8 篇 chitkara univers...
7 篇 school of comput...
6 篇 fujian key labor...
6 篇 university of ch...
5 篇 engineering rese...
5 篇 the 54th researc...
5 篇 school of engine...
5 篇 school of comput...
4 篇 shenyang institu...
4 篇 faculty of infor...
3 篇 international in...
3 篇 guilin universit...
3 篇 graphic era hill...
3 篇 hebei key labora...
3 篇 school of comput...
3 篇 pattern recognit...
3 篇 shenyang casnc t...

作者

10 篇 hornegger joachi...
6 篇 yu bihui
5 篇 yihe zhang
5 篇 aiming wu
5 篇 zhou xiaolei
5 篇 baohua qiang
5 篇 tiwari raj gaura...
5 篇 da-han wang
5 篇 yongjie yang
5 篇 agarwal ambuj ku...
5 篇 shanshan tu
5 篇 wang ning
5 篇 xuetao bai
4 篇 comaniciu dorin
4 篇 maheshwari himan...
4 篇 shunzhi zhu
4 篇 zaharis zaharias...
4 篇 wang hongliang
4 篇 zhang yonghong
4 篇 jain vishal

语言

619 篇 英文
6 篇 其他
3 篇 中文

检索条件"任意字段=Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition"

共 628 条记录，以下是371-380 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Camera-Based Meal Type and Weight Estimation in Self-Service Lunch Line Restaurants

Camera-Based Meal Type and Weight Estimation in Self-Service...

引用

pattern recognition Systems (ICPRS), international conference on

作者： Teemu Sarapisto Lauri Koivunen Tuomas Mä kilä Arto Klami Pauliina Ojansivu Dept. of Computer Science University of Helsinki Helsinki Finland Dept. of Computing University of Turku Turku Finland

ISBN: (数字)9781665466943

ISBN: (纸本)9781665466950

Individuals, restaurant owners and health organizations are all interested in accurate information about food intake, but collecting the information in sufficiently automated way remains a practical challenge. In controlled environments, such as lunch line restaurants, the food intake can be estimated by measuring the portions upon purchase and separately monitoring the food waste, but even this requires often complicated setups such as repeated weighing of the plate after every meal component. In this work we explore the feasibility of using a combination of ceiling-mounted cameras and computer vision for estimating both the types and weights of individual food items the customers are taking in a lunch line restaurant. We describe the imaging system and weighing-based sensing for obtaining ground truth training data, and develop and evaluate deep learning models for the computer vision tasks. We demonstrate high accuracy especially in meal type identification and hence validate the feasibility of the approach. We release the annotated dataset for further development of improved methods.

关键词： Deep learning Weight measurement Training Computer vision Computational modeling Training data Data models

来源：评论

学校读者我要写书评

暂无评论

A Model robustness optimization method based on adversarial sample detection 22

A Model robustness optimization method based on adversarial ...

引用

proceedings of the 2022 5th international conference on Artificial Intelligence and pattern recognition

作者： Jiaze Sun Siyuan Long Xianyan Ma Yanmei Tang Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts & Telecommunications China Xi'an University of Posts & Telecommunications China

ISBN: (纸本)9781450396899

Deep neural networks are extremely vulnerable due to the existence of adversarial samples. It is a challenging problem to optimize the robustness of the model to protect deep neural networks from the threat of adversarial samples. To improve the model robustness, an integrated detection model of adversarial samples is designed to detect the existence of adversarial samples, which consists of a multi-classification detector and five single-classification detectors to perform double-layer detection of adversarial samples and intercept the adversarial samples finally sent to the image classification model. the detection experiments were conducted on the CIFAR-10 dataset for the adversarial samples generated by five attack algorithms: FGSM, BIM, DeepFool, JSMA, and C&W, and the detection success rate for all types of adversarial samples reached over 98.96%. After that, secondary attack experiments were conducted on the model, and the detection success rate of the model for the second attack adversarial samples reached over 92.36%. It provides an efficient and robust optimization method for deep neural network models in adversarial environments.

关键词： Adversarial samples Deep neural networks Integrated detection Model robustness

来源：评论

学校读者我要写书评

暂无评论

Robust Object Detection and Tracking Model for Visually Impaired People Using Deep Convolution Neural Network Model

Robust Object Detection and Tracking Model for Visually Impa...

引用

Sustainable Communication Networks and Application (ICSCNA), international conference on

作者： R. Priyanka K. Vivekrabinson A. Kathijanasreen W T Chembian Atharvaa Veerasundar Srimathi S Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Department of CSE Kalasalingam Academy of Research and Education Krishnankoil CSE department R.M.K College of Engineering and Technology Department of CSE Vel Tech High Tech Dr. Rangarajan Dr.Sakuntala Engineering College 12th Greenwood High International High School Bengaluru Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

Visual Impairment (VI) has become the most significant challenge over the past few years. Even to complete their day-to-day activities, visually impaired persons seek assistance. A currency recognition system and automated common object could enhance the safe movement and transaction people activity with a disability. A model is generated for an object detector that could identify items for people with a disability and other significant uses by identifying them at a certain distance. the present object detection techniques need a massive quantity of training dataset that take longer time, are difficult, and it is a more complicated process. therefore, in this work, a Robust Object Detection and Tracking for Visually Impaired People using Deep Convolution Neural Network (RODT-DCNN) model is developed. the main purpose of the RODT-DCNN model lies in the accurate identification and classification of objects for VIP. the RODT-DCNN technique comprises two stages of operations such as object detection and object classification. For object detection, YOLO-v5 approach was used. Next, Elman neural network (ENN) approach can be exploited for the effectual identification and classification of objects. At last, sine cosine algorithm (SCA) can be employed for adjusting the parameters of the ENN model. the performance analysis of the RODT-DCNN approach occurs on standard dataset and the outcomes demonstrated the improved detection results of the RODT-DCNN approach in terms of diverse measures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Handwritten Text Detection for Automatic Descriptive Answer Evaluation 22

Anomaly Handwritten Text Detection for Automatic Descriptive...

引用

proceedings of the 2022 11th international conference on computing and pattern recognition

作者： Nilanjana Chatterjee Palaiahnaakote Shivakumara Umapada Pal Tong Lu Yue Lu Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Faculty of Computer Science and Information Technology University of Malaya Malaysia National Key Lab for Novel Software Technology Nanjing University China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China

ISBN: (纸本)9781450397056

Although there are advanced technologies for character recognition, automatic descriptive answer evaluation is an open challenge for the document image analysis community due to large diversified handwritten text and answers to the question. this paper presents a novel method for detecting anomaly handwritten text in the responses written by the students to the questions. the method is proposed based on the fact that when the students are confident in answering questions, the students usually write answers legibly and neatly while they are not confident, they write sloppy writing which may not be easy for the reader to understand. To detect such anomaly handwritten text, we explore a new combination of Fourier transform and deep learning model for detecting edges. this result preserves the structure of handwritten text. For extracting features for classification of anomaly text and normal text, the proposed method studies the behavior of writing style, especially the variation at ascenders and descenders. therefore, the proposed work draws principal axis which is invariant to rotation, scaling and some extent to distortion for the edge images. With respect to principal axis, the proposed method draws medial axis using uppermost and lowermost points. the distance between the medial axis and principal axis points are considered as feature vector. Further, the feature vector is passed to Artificial Neural Network for classification of anomaly text. the proposed method is evaluated by testing on our own dataset, standard dataset of gender identification (IAM) and handwritten forgery detection dataset (ACPR 2019). the results on different datasets show that the proposed work outperforms the existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedded Real-time System Trusted Protection Technology for Supply Chain Scenarios 22

Embedded Real-time System Trusted Protection Technology for ...

引用

proceedings of the 2022 12th international conference on Communication and Network Security

作者： Jin Zhou Zhenhu Ning Qi Wang Yuchen Wang faculty of Information Technology Beijing University Of Technology China Trusted Computing Technology Co.LTD Shenzhen China

ISBN: (纸本)9781450397520

Embedded real-time operating systems are widely used in communication, industrial control and weapon intelligent control and other fields. However, due to the complex personnel and environment involved in the development of embedded systems, the development software is difficult to control independently, so it is extremely vulnerable to malicious code implantation attacks. Based on this, this paper focuses on the UCOS real-time operating system, analyzes the security threats faced by the UCOS development environment GCC in the process of precompiling, compiling, assembling and linking, and designs a plug-in-based GCC attack mode, which can implement malicious code implantation attacks on UCOS. . At the same time, a trusted protection framework for embedded real-time systems is proposed. By implementing active control and integrity measurement of firmware, operating systems and applications in embedded real-time systems, the trusted startup of embedded real-time systems is guaranteed and the supply chain stage is independently resisted. malicious code implantation attack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identity-based Linkable Blind Ring Signature Scheme on Lattice 22

Identity-based Linkable Blind Ring Signature Scheme on Latti...

引用

proceedings of the 2022 12th international conference on Communication and Network Security

作者： Xue Liao Yihua Zhou Jiawei Xu Shuaikun Xing Wei Zou Jin Zhou Qi Wang Zhenhu Ning faculty of Information Technology Beijing University of Technology China Trusted Computing Technology Co.LTD Shenzhen China

ISBN: (纸本)9781450397520

Identity-based link-ring signature schemes are widely used in e-commerce, e-voting, blockchain security and other *** link-ability of signature scheme ensures that the same user can only sign once with the same private key. Aiming at the requirements of question confidentiality, anonymity of the signature user identity, and one-time signature in the process of question signing in online exams, this paper proposes an identity-based linkable blind ring signature scheme. In this paper, the lattice delegation algorithm is used to generate the user's private key, a one-time random matrix is introduced, and the one-time signature key is generated by running the preimage sampling algorithm (SamplePre) based on the signed user's private key. Finally, this paper proves the unconditional anonymity, unforgeability and link-ability of the scheme under the random oracle model based on the small integer solution(SIS) difficulty assumption.

关键词： Reject Sampling Technology Linkable Ring Signature Lattice Based on Identity

来源：评论

学校读者我要写书评

暂无评论

VRGNet: A Robust Visible Region-Guided Network for Occluded Pedestrian Detection 22

VRGNet: A Robust Visible Region-Guided Network for Occluded ...

引用

proceedings of the 2022 11th international conference on computing and pattern recognition

作者： Xin Mao Chaoqi Yan Hong Zhang Jianbo Song Ding Yuan The 613th Research Institute of AVIC China Image Processing Center School of Astronautics Beihang University China

ISBN: (纸本)9781450397056

Pedestrian detection has made significant progress in both academic and industrial fields. However, there are still some challenging questions with regard to occlusion scene. In this paper, we propose a novel and robust visible region-guided network (VRGNet) to specially improve the occluded pedestrian detection performance. Specifically, we leverage the adapted FPN-based framework to extract multi-scale features, and fuse them together to encode more precision localization and semantic information. In addition, we construct a pedestrian part pool that covers almost all the scale of different occluded body regions. Meanwhile, we propose a new occlusion handling strategy by elaborately integrating the prior knowledge of different visible body regions with visibility prediction into the detection framework to deal with pedestrians with different degree of occlusion. the extensive experiments demonstrate that our VRGNet achieves a leading performance under different evaluation settings on Caltech-USA dataset, especially for occluded pedestrians. In addition, it also achieves a competitive of 48.4%, 9.3%, 6.7% under the Heavy, Partial and Bare settings respectively on CityPersons dataset compared with other state-of-the-art pedestrian detection algorithms, while keeping a better speed-accuracy trade-off.

关键词： Pedestrian detection CityPersons Part pool Occlusion scene

来源：评论

学校读者我要写书评

暂无评论

Activity Attribute-Based User Behavior Model for Continuous User Authentication 22

Activity Attribute-Based User Behavior Model for Continuous ...

引用

proceedings of the 2022 12th international conference on Communication and Network Security

作者： Luthfi Azhari Ari Moesriami Barmawi School of Computing Telkom University INA

ISBN: (纸本)9781450397520

In general, authentication using a username and password has been used to manage access to the system. this way, it can be arranged so that only authorized people can access a system. However, it does not rule out the possibility of several spoofing attacks. User behavior can be used instead of a password to solve this problem. Given that user behavior is unique, the behavior can be used for the authentication process. One of the authentication processes is to continuously use weblogs, as proposed by Leslie et al. However, the method used by Leslie et al. still has a drawback with the Leslie method. Only the user's role is identified. So, the attacker's identity cannot be known if an attack occurs. A continuous authentication method using weblogs and user attributes such as user id, DateTime, event, category, and products is used to overcome this problem. Using this method, the user's identity can be identified immediately after the role is known. In addition, using the proposed method, the accuracy of user identity authentication obtained is, on average, 95.08%, which means it is greater than the accuracy of user role authentication using the Leslie method, which is 46%..

关键词： identity weblog authentication attribute behavior

来源：评论

学校读者我要写书评

暂无评论

Attributes and Dimensions of Trust in Secure Systems 22

Attributes and Dimensions of Trust in Secure Systems

引用

proceedings of the 12th international conference on the Internet of things

作者： Matthew Bradbury Daniel Prince Victoria Marcinkiewicz Tim Watson School of Computing and Communications Lancaster University UK The Centre for Artificial Intelligence Robotics and Human-Machine Systems School of Psychology Cardiff University UK The Alan Turing Institute UK

ISBN: (纸本)9781450396653

What is it to be trusted? this is an important question as trust is increasingly placed in a system and the degree to which a system is trusted is increasingly being assessed. However, there are issues with how related terms are used. Many definitions focus on one attribute of trust (typically behaviour) preventing that definition from being used for other attributes (e.g., identity). this is confused further by conflating what trustors measure about a trustee and what conclusions a trustor reaches about a trustee. therefore, in this paper we present definitions of measures (trustiness and trustworthiness) and conclusions (trusted and trustworthy). these definitions are general and do not refer to a specific attribute allowing them to be used with arbitrary attributes which are being assessed (e.g., identity, behaviour, limitation, execution, correctness, data, environment). In addition, in order to demonstrate the complexities of describing if a trustee is designated as trusted or trustworthy, a set of dimensions are defined to describe attributes (time, scale, proactive/reactive, strength, scope, source). Finally, an example system is classified using these attributes and their dimensions in order to highlight the complexities of describing a system as holistically trusted or trustworthy.

关键词： limitations Trust dimensions attributes trustworthy

来源：评论

学校读者我要写书评

暂无评论

Exploration of Congestion Control Techniques on Dragonfly-class HPC Networks through Simulation 12

Exploration of Congestion Control Techniques on Dragonfly-cl...

引用

12th international Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems held as part of the 33rd ACM/IEEE international conference for High Performance computing, Networking, Storage and Analysis

作者： McGlohon, Neil Hemmert, K. Scott Brown, Kevin A. Levenhagen, Michael Chunduri, Sudheer Ross, Robert B. Carothers, Christopher D. Rensselaer Polytech Inst Troy NY 12180 USA Sandia Natl Labs POB 5800 Albuquerque NM 87185 USA Argonne Natl Lab Lemont IL USA

ISBN: (纸本)9781665411189

Ensuring optimal conununication latency in High Perfonnance computing (HPC) networks is of critical importance to the efficient operation of facilitated applications. Different application operations and types of tasks, such as 10 operations, can create a variety of traffic patterns across the system interconnect. Some conununication patterns, however, can be problematic for overall system performance. One traffic pattern of particular concern is the many-to-one or incast. When packets sent from many different endpoints target a singular, or small number of destinations, it can overwhelm the receiving endpoints' ability to process the traffic, resulting in a cascading effect of induced congestion. this can have broadreaching, detrimental effects to other applications as their data streams encounter induced congestion. the concept of congestion control has been explored in various HPC system technologies and is an important feature in stateof-the-art networks such as Infiniband and the Cray Slingshot interconnect. Because access to physical, full-scale interconnects of bleeding-edge design can be challenging and the exact mechanisms of operation not publicly known, we look to simulation to explore techniques for congestion control with a fine level of flexibility not available on real-world systems. We present and explore a mechanism for congestion control which seeks to detect network congestion, identify its cause, and abate it by throttling injection of identified aggressor endpoints. Our work proposes, discusses and evaluates two similar implementations of this mechanism for congestion control in two different network simulators and their capabilities at mitigating the effects of congestion on application communication performance and general system packet latencies.

关键词： Technological innovation Codes Computational modeling System performance High performance computing conferences Traffic control

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共63页 << < 34 35 36 37 38 39 40 41 42 43 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：