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

18,313 篇 会议
212 册 图书
195 篇 期刊文献

馆藏范围

18,717 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

13,358 篇 工学
- 9,707 篇 计算机科学与技术...
- 6,578 篇 软件工程
- 3,574 篇 控制科学与工程
- 2,457 篇 信息与通信工程
- 2,299 篇 电气工程
- 1,724 篇 光学工程
- 1,510 篇 机械工程
- 1,119 篇 生物工程
- 905 篇 电子科学与技术（可...
- 859 篇 生物医学工程（可授...
- 782 篇 仪器科学与技术
- 571 篇 动力工程及工程热...
- 537 篇 交通运输工程
- 507 篇 安全科学与工程
- 502 篇 材料科学与工程（可...
- 454 篇 化学工程与技术
- 342 篇 土木工程
- 335 篇 网络空间安全
5,343 篇 理学
- 2,350 篇 物理学
- 2,276 篇 数学
- 1,230 篇 生物学
- 594 篇 统计学（可授理学、...
- 588 篇 系统科学
- 444 篇 化学
2,414 篇 管理学
- 1,719 篇 管理科学与工程(可...
- 822 篇 图书情报与档案管...
- 682 篇 工商管理
1,085 篇 医学
- 962 篇 临床医学
- 556 篇 基础医学(可授医学...
- 362 篇 药学(可授医学、理...
362 篇 法学
258 篇 经济学
249 篇 农学
216 篇 教育学
63 篇 军事学
25 篇 艺术学
20 篇 文学
3 篇 哲学

主题

1,581 篇 computer vision
361 篇 deep learning
314 篇 computer archite...
282 篇 cameras
254 篇 computational mo...
251 篇 object detection
239 篇 control systems
236 篇 computer science
217 篇 image segmentati...
212 篇 feature extracti...
209 篇 internet of thin...
187 篇 access control
172 篇 machine vision
158 篇 neural networks
137 篇 artificial intel...
131 篇 face recognition
130 篇 real-time system...
129 篇 data mining
129 篇 process control
128 篇 support vector m...

机构

47 篇 chitkara univers...
46 篇 school of comput...
45 篇 school of contro...
29 篇 maharishi school...
24 篇 karnataka bangal...
21 篇 school of comput...
19 篇 maharishi school...
17 篇 chitkara univers...
17 篇 college of compu...
15 篇 school of comput...
14 篇 south china univ...
14 篇 dept. of compute...
14 篇 department of co...
14 篇 chitkara univers...
14 篇 university of ch...
14 篇 college of compu...
13 篇 school of comput...
12 篇 school of comput...
12 篇 centre of interd...
12 篇 school of comput...

作者

19 篇 wang lei
18 篇 li yang
17 篇 wang wei
16 篇 yang yang
14 篇 liu yang
13 篇 wang hui
13 篇 ryszard tadeusie...
13 篇 marcin korytkows...
12 篇 wang ping
12 篇 wang jian
12 篇 sato jun
12 篇 jacek m. zurada
11 篇 zhang tao
11 篇 sakaue fumihiko
11 篇 zhang lei
11 篇 huang tinglei
11 篇 liu lei
10 篇 lei wang
10 篇 li xin
10 篇 wang jing

语言

18,165 篇 英文
448 篇 其他
115 篇 中文
16 篇 俄文
7 篇 西班牙文
2 篇 法文
2 篇 土耳其文
1 篇 德文

检索条件"任意字段=Proceedings of the 3rd International Conference on Control and Computer Vision"

共 18720 条记录，以下是4911-4920 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：

Drones in Defense: Real-Time vision-Based Military Target Surveillance and Tracking

Drones in Defense: Real-Time Vision-Based Military Target Su...

引用

international Symposium on Advanced Computing and Communication (ISACC)

作者： Sudip Chakrabarty Rajdeep Chatterjee Sorup Chakraborty Sourov Roy Shuvo Rajesh Chowdhury School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

In today’s world, with ongoing conflicts and increasing security challenges, the use of drones in defense has become critical for real-time surveillance, precise targeting, and ensuring personnel safety. This study introduces a novel dataset of drone-captured videos tailored for military surveillance, where carefully selected frames were used to optimize training and testing. We evaluated three YOLO deep learning models—YOLOv5, YOLOv8, and YOLOv11—and their nano and small variants to achieve a balance between detection accuracy and computational efficiency. The top-performing model, YOLOv11s, was further integrated with advanced tracking algorithms, including Byte-Track, BoT-SORT, and DeepSORT, to identify the most reliable combination for real-time tracking. Results show that YOLOv11s, paired with ByteTrack, delivers superior accuracy and efficiency in detecting and tracking enemy assets, enabling autonomous monitoring and engagement with minimal human intervention. This work demonstrates significant advancements in autonomous military surveillance.

关键词： Training Target tracking Accuracy Military computing Surveillance Computational modeling Radar tracking Real-time systems Drones Videos

来源：评论

学校读者我要写书评

暂无评论

J1F Tracking: Online Multi-Camera People Tracking In Just 1 Frame

J1F Tracking: Online Multi-Camera People Tracking In Just 1 ...

引用

Robotics, Artificial Intelligence and Intelligent control (RAIIC), international conference on

作者： Changbei Xie Ning Li Huimin Wu Huiyu Zhou Electronic Information School Nanjing University of Aeronautics and Astronautics Nanjing China School of Informatics University of Leicester Leicester UK

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

Multi-Camera People Tracking (MCPT) has become an increasingly important research field and has achieved rapid development, but there are still problems such as occlusion, ID change, and tracking loss. So far, most algorithms are offline algorithms that use the information of past frames and future frames to match and track using the re-identification method. We propose an online tracking algorithm that can online tracking using just the past 1 frame (named J1F). This method uses the position and appearance features of the target person to perform collaborative analysis between multiple cameras, and uses the majority camera voting method to track the same target person in the current frame. Improve the efficiency of Multi-Camera People Tracking by using a more efficient and robust method. The method was evaluated on the AI City 2024 dataset, and the HOTA reached $70.15 \%$, reducing the time consumption by $31.7 \%$.

关键词： Target tracking Urban areas Robot vision systems Collaboration Cameras Robustness Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Creative Writing Web Site 3.0 for 3rd Year General Education Students 13

Creative Writing Web Site 3.0 for 3rd Year General Education...

引用

13th international conference on computer Supported Education, CSEDU 2021

作者： Alomoto, Daniela Michelle Vilatuña Egas, Paúl Francisco Baldeón Prendes, Norma Molina Rivero, Ernesto Fernández Fundación Caminitos de Luz Escuela María Troncatti Quito Ecuador Universidad Tecnológica Israel Quito Ecuador

This work is the basis of a web 3.0 site to contribute to the process of Teaching and Learning of creative writing of third year students of Basic General Education of the "Mar37;a Troncatti" school, Quit... 详细信息

ISBN: (纸本)9789897585029

This work is the basis of a web 3.0 site to contribute to the process of Teaching and Learning of creative writing of third year students of Basic General Education of the "María Troncatti" school, Quito, Ecuador;which allows the student the use of web 2.0 tools, the integration of Google Classroom as a learning manager. Each academic block in the web 3.0 site develops communication skills for creative writing, in which the teacher can work processes of expression, communication and creation with students, awakening from the beginning the intrinsic motivation in the student through questions that generate both curiosity to learn and innovate. The proposal was evaluated by specialists with good results in a general sense. Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Research on Radar Emitter Identification Algorithm Based on Coupled Recurrent Network

Research on Radar Emitter Identification Algorithm Based on ...

引用

computer Science, Electronic Information Engineering and Intelligent control Technology (CEI), IEEE international conference on

作者： Mingyue Feng Fuqun Zhang Hongbin Jin Linxuan Huang Chunlai Yu Air Force Early Warning Academy Wuhan China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

This article analyzes the operational characteristics of two deep learning algorithms, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), and proposes a radar radiation source recognition method based on Coupled Recurrent Network (CRN). Its feasibility is verified through simulation experiments. When the signal-to-noise ratio of the test set signal is 3dB, the algorithm still has a recognition rate of 82.73% for the signal, while when the signal-to-noise ratio of the test set signal is greater than or equal to 5dB, the recognition rate of the algorithm for signals exceeds 94.70%.

关键词： Deep learning computer science Recurrent neural networks Radar Convolutional neural networks Character recognition Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Detection Of Counterfeit Images Through Deep Learning based Yolov3 Model

Detection Of Counterfeit Images Through Deep Learning based ...

引用

Advancement in Computation & computer Technologies (InCACCT), international conference on

作者： Jobez J. C Golden Nancy R Syed Rabiya Mohamed Ali Muthukumaran N Raghavan Sheeja Jasmine Gnana Malar A Department of AIML Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Artificial Intelligence and Data Science R.M.K. Engineering College Gummidipoondi Tamil Nadu India Department of ECE PSN College of Engineering and Technology Tirunelveli India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Image forgery is the procedure of analysing and detecting any fraudulent or unauthorised alterations made to digital images. The detection in images is difficult for achieving a high accuracy rate and the process is time-consuming. Researchers and forensic experts are developing tools for detecting fake images. The identification of computer-generated picture forgeries is a notable area of study, aiming to provide a comprehensive review of detection tools and techniques. In this work, a novel deep-learning model is proposed for detecting forgery in images. The images are pre-processed using an adaptive Gaussian bilateral (AGB) filter to enhance the quality of the images. The enhanced photos are fed into the Mobile Net for extracting the relevant features in the pictures. The modified Yolov3 is utilized for object detection in images and detecting the real and forgery images. According to the result, the proposed model attains 99.55% for forgery detection in images. The modified Yolov3 yields 99.55% accuracy as opposed to Mask RCNN, RCNN, and SSD's 0.68%, 0.65%, and 1.16% accuracy. CNN, ResNetV2 and DCNN are all outperformed the proposed model in terms of overall accuracy by 0.11%, 1.10%, and 5.55%, respectively.

关键词： YOLO Deep learning Adaptation models Accuracy Reviews Computational modeling Forensics Digital images Feature extraction Forgery

来源：评论

学校读者我要写书评

暂无评论

A More Efficient Way to control Traffic Lights Through AI-Led Smart City Management

A More Efficient Way to Control Traffic Lights Through AI-Le...

引用

Technological Advancements in Computational Sciences (ICTACS), international conference on

作者： Shilpa Choudhary Shaik Shabbir Ali N. Ramesh Babu Harshita Sharma Bhawna Kaliraman Yash Dhankhar Department of Computer Science and Engineering (AIML) Neil Gogte Institute of Technology Hyderabad India Department of Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Department of Mathematics Koneru Lakshmaiah Education Foundation Vaddeswaram India Department of Computer Science and Engineering DPG Institute of Technology and Management Gurugram India

Urban regions are nevertheless plagued by traffic congestion, which increases travel times, fuel use, and greenhouse gas emissions. To lessen traffic congestion and enhance the performance of traffic systems, effective traffic control is crucial. The ideal flow of traffic is not achieved by traditional traffic light control technologies, which are based on planned signal plans or fixed timings that do not adjust to real-time traffic circumstances. By dynamically changing signal timing based on real-time traffic data, artificial intelligence (AI) has emerged as a viable method to optimize traffic signal regulation. This paper suggests a real-time traffic signal timing optimization system that is powered by AI and leverages machine learning methods. This suggested work is a traffic light control system that uses artificial intelligence and offers a number of *** instance, a shorter trip distance, improved fuel economy, and lower pollutants. Additionally, the system is easily upgradeable with new data sources or algorithms and may be incorporated with current traffic management systems. It suggested using an artificial intelligence-based traffic light control system (TLCS) to greatly enhance traffic flow and relieve congestion in metropolitan areas. Real-time data and machine learning algorithms combined to enable dynamic and adaptive signal control, resulting in more effective traffic management and improved quality of life for city dwellers. This clarifies their potential to enhance urban transportation and lessen congestion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Detection of Digital Face Video Manipulation using Deep Learning

A Novel Framework for Detection of Digital Face Video Manipu...

引用

Computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Sanskriti Chandra Shivam Saxena Santosh Kumar Mithilesh Kumar Chaube Srinivas K G Saeed Hamood Alsamhi Edward Curry Abdu Saif Department of Data Science and Artificial Intelligence IIIT-Naya Raipur Chhattisgarh India Department of Computer Science and Engineering IIIT-Naya Raipur Chhattisgarh India Department of Mathematical Sciences IIIT-Naya Raipur Chhattisgarh India Insight SFI Research Centre for Data Analytics University of Galway Galway Ireland Faculty of Engineering & Information Technology Taiz Yemen

Digital face manipulation and classification have recently attracted the attention of academia and industry worldwide. Researchers have developed deep learning and computer vision techniques for detecting face manipulations, and it has become a challenging task to differentiate between authentic and manipulated face images manually. The challenge results in the decline of authenticity in digital media content. In this paper, we propose a framework for the classification of manipulating face images using the EfficientNet learning model. The proposed framework takes four digital facial forgeries: Face-Swap, Face-2-Face, DeepFakes, and neural textures. Multiple manipulation techniques are used to process manipulated faces, such as the Blaze-face tracking method, to determine the locations of the face images and pixel coordinates. The proposed framework is used first to identify the type of face manipulation and then to perform detection of the tampered regions in the face images. The proposed framework provided an automated benchmark that considers all four modification techniques in a realistic situation. The results show that the proposed framework outperforms existing approaches regarding accuracy and efficiency. Furthermore, the proposed framework is suitable for detecting digital face video manipulation in various applications, including forensics and security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Sports Online Multimedia Resource Sharing System Based on Data Clustering

Design of Sports Online Multimedia Resource Sharing System B...

引用

Power Electronics, computer Applications (ICPECA), IEEE international conference on

作者： Jian Xu Lingguang Zhu Department of General Physical Education China Academy of Art Hangzhou China

During the post-epidemic period, the construction of online resources for physical education courses in colleges and universities provides an important guarantee for realizing real-time conversion during the epidemic prevention and control period. Through the research of major online courses at home and abroad, the teaching reform of college physical education courses with "results as the center" as the core is put forward. The shared teaching system is researched on the success of students and designed according to the actual situation. Using data clustering technology, the information management of college physical education teaching is studied. Based on the overall functional requirements, the cloud computing architecture of the platform is analyzed in detail. Based on the data processing requirements, a data-based management system is established and data management is carried out. According to the APP architecture of student users, the requirements of integrated data collection and distribution of training tasks are carried out. Then, the specific realization of APP architecture is elaborated. At the same time, using the theory of output gain stability analysis, a linear analysis model for data analysis in sports industry is established. Using the combination of quadratic programming and linear integration, the integration of internal information and the regulation of parameters are carried out in the sports industry. Through the analysis of the sports industry, it is proved that the algorithm proposed in this paper has high accuracy and reduces the interference error in the sports industry.

关键词： Industries Training Cloud computing Clustering algorithms computer architecture Educational courses Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Psychological Test based on Large Language Model

Research on Psychological Test based on Large Language Model

引用

Robotics, Artificial Intelligence and Intelligent control (RAIIC), international conference on

作者： Zhengzheng Liu Yunfeng Kang Xinying Li Institute of Psychology Chinese Academy of Sciences Beijing China Department of Psychology University of Chinese Academy of Sciences Beijing China Dareway Software Co. Ltd Beijing China Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

Traditional questionnaire-based psychological tests have many drawbacks, such as the subjects’ inaccurate understanding of the questions, incomplete answers, disguised intentions, one-way communication, closed answers, etc. This paper proposes a psychological test system design scheme based on pre-trained large language model (LLM), which makes use of LLM’s ability to learn and understand natural language and generate output. Complete the psychological test with the subjects through natural language human-computer *** the Cattell 16 Personality Factors Test (16PF) as an example, a natural corpus for large model training of psychological test was researched and compiled, and the psychological test model of two factors in 16PF was developed. Through test comparison, the psychological test model is better than the traditional questionnaire test effect.

关键词： Training Large language models Natural languages Text categorization Psychology Process control System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Unconventional Risks and Prevention and control Strategies for Photovoltaic Distribution Grids Containing High Penetration Rates

Unconventional Risks and Prevention and Control Strategies f...

引用

Electrical Engineering and control Science (IC2ECS), international conference on

作者： Zhentao Han Qixiang Wang Zhuoran Song Peng Ye Jinhang Shan Wenyu Yang State Grid Liaoning Electric Power Co. Ltd. Economic and Technological Research Institute Shenyang Liaoning China State Grid Liaoning Electric Power Co. Ltd Shenyang Liaoning China School of Electric Power Shenyang Institute of Engineering Shenyang Liaoning China

With the vision of “double carbon”, China has begun to vigorously develop a clean, low-carbon, safe and efficient energy system, and build a new power system with new energy as the main body. With the high penetration of photovoltaic power supply into the distribution network, the coordination between traditional risk and protection can no longer meet the technical requirements of the new distribution network relay protection. Therefore, this paper focuses on the three aspects of the non-conventional risk of PV power supply, its analysis method and the distribution network protection scheme adapted to the access of PV power supply. Firstly, the general structure of PV power supply is introduced, and the working principle of inverter and grid-connected control strategy under normal state are analyzed, and then from the perspective of distribution grid, the method of analyzing the extraordinary risk of distribution grid is proposed, and the symmetrical and asymmetrical fault characteristics of distribution grid and the problems when PV power supply is connected to distribution grid are analyzed. In addition, for the method proposed in this paper, the equivalent model of PV power access to the distribution network is used as the basis to study the fault characteristics of PV power access to the distribution network, analyze the impact of PV power access to the existing current protection of the distribution network, and propose to classify the distribution network into three regions according to the location of PV power access, and then put forward the preventive and control strategies respectively. Finally, the feasibility of the protection scheme proposed in this chapter is verified by simulation.

关键词：

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500页 << < 488 489 490 491 492 493 494 495 496 497 > >>

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：