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

6,721 篇 会议
330 册 图书
117 篇 期刊文献

馆藏范围

7,167 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,792 篇 工学
- 3,971 篇 计算机科学与技术...
- 2,033 篇 软件工程
- 806 篇 电气工程
- 771 篇 信息与通信工程
- 592 篇 控制科学与工程
- 395 篇 生物工程
- 381 篇 生物医学工程（可授...
- 297 篇 光学工程
- 296 篇 机械工程
- 212 篇 仪器科学与技术
- 182 篇 电子科学与技术（可...
- 138 篇 化学工程与技术
- 127 篇 材料科学与工程（可...
- 120 篇 网络空间安全
- 108 篇 安全科学与工程
- 91 篇 动力工程及工程热...
1,627 篇 理学
- 809 篇 数学
- 493 篇 物理学
- 489 篇 生物学
- 273 篇 统计学（可授理学、...
- 189 篇 化学
- 141 篇 系统科学
843 篇 管理学
- 462 篇 管理科学与工程(可...
- 425 篇 图书情报与档案管...
- 181 篇 工商管理
679 篇 医学
- 604 篇 临床医学
- 254 篇 基础医学(可授医学...
- 145 篇 药学(可授医学、理...
- 100 篇 公共卫生与预防医...
122 篇 法学
- 115 篇 社会学
92 篇 教育学
58 篇 农学
52 篇 经济学
43 篇 艺术学
12 篇 文学
4 篇 军事学
1 篇 哲学

主题

927 篇 pattern recognit...
801 篇 artificial intel...
450 篇 machine learning
291 篇 feature extracti...
243 篇 deep learning
203 篇 accuracy
185 篇 support vector m...
134 篇 data mining
128 篇 training
126 篇 neural networks
126 篇 face recognition
104 篇 computer imaging...
103 篇 local binary pat...
102 篇 computer vision
88 篇 image processing...
87 篇 real-time system...
87 篇 convolutional ne...
85 篇 information syst...
83 篇 pattern matching
83 篇 computational mo...

机构

39 篇 chitkara univers...
33 篇 maharishi school...
27 篇 school of comput...
27 篇 indian stat inst...
25 篇 centre of interd...
25 篇 the islamic univ...
23 篇 department of ar...
23 篇 concordia univ c...
22 篇 national univers...
20 篇 school of comput...
19 篇 univ chinese aca...
18 篇 school of comput...
18 篇 univ waterloo de...
17 篇 vishwakarma inst...
16 篇 national laborat...
15 篇 school of artifi...
15 篇 institute of aut...
14 篇 lovely professio...
14 篇 uttaranchal inst...
14 篇 college of pharm...

作者

54 篇 suen ching y.
24 篇 suen cy
22 篇 kamel mohamed s.
18 篇 lu bao-liang
18 篇 karray fakhri
17 篇 de-shuang huang
17 篇 abraham ajith
14 篇 maji pradipta
13 篇 dash yajnaseni
12 篇 c.y. suen
10 篇 liu cheng-lin
10 篇 venkatesh svetha
10 篇 wong alexander
10 篇 chauhan rahul
10 篇 natarajan s.
10 篇 zheng wei-long
10 篇 liu wei
10 篇 vinay a.
9 篇 zhang lei
9 篇 gill kanwarparta...

语言

6,318 篇 英文
822 篇 其他
72 篇 中文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Pattern Recognition and Machine Intelligence"

共 7168 条记录，以下是1341-1350 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：

Modular StoryGAN with Background and Theme Awareness for Story Visualization 3rd

Modular StoryGAN with Background and Theme Awareness for Sto...

引用

3rd international conference on pattern recognition and Artificial intelligence, ICPRAI 2022

作者： Szűcs, Gábor Al-Shouha, Modafar Budapest University of Technology and Economics Műegyetem rkp. 3 Budapest1111 Hungary

ISBN: (纸本)9783031090363

Story visualization is a novel topic that intersects computer vision and natural language processing. In this task, given a series of natural language sentences that compose a story, a sequence of images should be generated that correspond to the sentences. Prior works have introduced recurrent generative models which outperform text-to-image models on this task;however, local and global consistency is a challenging attribute of these solutions. For the improvement, we proposed a new modular model architecture named Modular StoryGAN containing the best promising components of prior works. To measure the local and global consistency we introduced background and theme awareness, which are expected attributes of the solutions. Based on the human evaluation, the generated images demonstrate that Modular StoryGAN possesses background and theme awareness. Besides the subjective evaluation, the objective one also shows that our model outperforms the state-of-the-art CP-CSV and DuCo models. © 2022, Springer Nature Switzerland AG.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Improvement of Gaussian Kernel Function for Face recognition 3

Improvement of Gaussian Kernel Function for Face Recognition

引用

3rd international conference on Electronics and Communication;Network and Computer Technology (ECNCT)

作者： He, Lingxiao Li, Shangjun Zhang, Wenfei Shanghai Pinghe Sch Shanghai 201206 Peoples R China Univ Calif Davis Davis CA 95616 USA Shanghai Shangde Expt Sch Shanghai 201315 Peoples R China

ISBN: (数字)9781510652118

ISBN: (纸本)9781510652118;9781510652101

Face recognition has been widely used in information security, access control, financial payment, criminal investigation, and other aspects due to its stability, convenience, ease to forge, and other advantages. The Gaussian blur, a fuzzy algorithm, uses the Gaussian distribution to increase the efficiency of face detection. However, the data distribution of the Gaussian blur model is not effective enough for face recognition. In this paper, we improve the one-dimensional Gaussian kernel function to the two-dimensional Gaussian kernel function and use the Gaussian distribution to improve the accuracy of the recognition system. We improve the Model and adopt the Gaussian calculation method. According to the one-dimensional Gaussian function and two-dimensional Gaussian function to carry on the analysis and operation, the conclusion is drawn that the two-dimensional Gaussian function can enhance the efficiency of face recognition when applied to the designed face recognition system. To verify the effectiveness of our method, we compare the proposed method with Gaussian blur on three different datasets. The experimental results show that our method significantly outperforms Gaussian blur. Our analyses illustrate that the recognition degree and range of the improved model are more comprehensive and broader, decreasing the time used for recognition.

关键词： Artificial intelligence Face recognition Gaussian Blur Algorithm Performance

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Video Event Detection: An Efficient Approach Utilizing Temporal Convolutional Neural Networks Using Real-time Performance 3

Revolutionizing Video Event Detection: An Efficient Approach...

引用

3rd IEEE international conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Alzubaidi, Laith H. Kumar, Bura Vijay Alassedi, Zainab Hussein, A.H.A. Rajesh, N. The Islamic University Najaf Iraq School of Computer Science and Artificial Intelligence SR University Telangana Warangal India National University of Science and Technology Dhi Qar Iraq College of Pharmacy Ahl Al Bayt University Karbala Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350317022

Automatic detection, localization and interpretation of an unusual event in a sequence of video is a challenging task due to its ambiguous and complex nature. A key challenge with manual detection and sequential analysis lies in the fact that video analysis often demands an immense amount of time and resources. To address this challenge, we have adopted an approach that involved Temporal Convolutional Neural Networks (TCNNs) and Long Short-Term Memory (LSTM) methods. This methodology offers a more efficient way to detect activities in video data. Furthermore, our approach enhances the capture of contextual information within the video, leading to improved results in video content detection. TCNNs, in particular, stand out as they can process input sequences in parallel, resulting in faster training and inference when compared to Recurrent Neural Networks (RNNs) which process data sequentially. To evaluate the effectiveness of these models, we conducted experiments on a manually annotated dataset known as UCF101, which contains 101 different activities. This dataset comprises 1,200 videos representing various actions. Our experimental results demonstrate that TCNNs achieved an accuracy rate of 93.80%, surpassing other existing models are ResNet and Multiclass Support vector machine in overall performance. TCNN, in particular, exhibited exceptional accuracy, indicating its effectiveness in video event detection. © 2023 IEEE.

关键词： Deep Learning Histogram equalization Long Short-Term Memory Recurrent Neural Network Temporal Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Exploiting Deep Learning Architectures for Effective Real-Time Data Analysis in machine Learning 3

Exploiting Deep Learning Architectures for Effective Real-Ti...

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Shreenidhi, H.S. Rajarajeswari, S. Bhagwat, Suvarna R. Sharma, Khushboo Seth, Kanika Yadav, Rakesh Kumar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

This paper seeks to discover how deep state-of-the-art architectures can be leveraged for robust actual-time information evaluation in device studying packages. The paper begins by supplying a comprehensive assessment of contemporary the modern-day in deep brand new-based totally facts evaluation technology. It then examines case research state-of-the-art real-time records analysis programs to illustrate the viability and blessings of modern-day existing deep latest architectures. Programs encompass self-driving vehicle generation, laptop vision, natural language processing, and time-collection evaluation. This targeted evaluation is supplemented by assessing ultra-modern capability shortcomings and demanding situations associated with using these architectures in actual-time scenarios. Subsequently, the paper provides a set of modern-day pointers and first-rate practices to help practitioners efficiently leverage deep trendy architectures for actual-time information evaluation. With the aid of combining a comprehensive review of current deep-gaining knowledge state modern-based records evaluation technology, a detailed dialogue present day its utility guiding ideas, and a summary of the latest potential shortcomings and demanding situations, this paper offers a practical manual to the effective of deep learning architectures for real-time data analysis. © 2023 IEEE.

关键词： architectures challenges combining recommendations shortcomings

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Enhancing Content Retrieval 3

Deep Learning Approaches for Enhancing Content Retrieval

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Khurana, Saniya Singh, Shweta Ranganathaswamy, M.K. Renuka, G. Diwakar, Mandar P. Jain, Sandeep Kumar Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India

ISBN: (纸本)9798350319125

Deep learning strategies for content material retrieval have been explored and updated to cope with the want for accurate search effects. This machine up to date is used to date apprehend and examine text-up-to-date content material from sources, up-to-date webpages, or virtual up-todate motion pictures. As the quantity and complexity of online content will increase, so up-to-date have the want for higher up-to-date up to date those resources. Recent advancements in deep gaining knowledge have enabled better content retrieval structures that are up to date, updated correctly, and speedy to understand statistics from one-of-a-kind sources. Such structures include natural language processing (NLP), sentiment analysis, entity reputation, and up-to-date updated reputation. Those deep studying technologies have been used to decorate content material retrieval by enhancing search effects' accuracy, robotically updated extracting applicable statistics, categorizing information, and identifying patterns. Additionally, deep-getting, updated systems are up-to-date and quick to examine large volumes of data, generating and relevant consequences than up-to-date methods. In summary, deep up-to-date techniques can beautify the retrieval system of content material efficiently, enhancing the accuracy and pace of seek effects. © 2023 IEEE.

关键词： categorizing comprehend effectively learning techniques

来源：评论

学校读者我要写书评

暂无评论

3D Dynamic Hand Gesture recognition with Fused RGB and Depth Images 3

3D Dynamic Hand Gesture Recognition with Fused RGB and Depth...

引用

3rd international conference on Big Data and Artificial intelligence and Software Engineering, ICBASE 2022

作者： Ye, Qingshan Bai, Yong Chen, Lu Jiang, Wenjie Hainan University No. 58 Renmin Avenue Meilan District Haikou570208 China

With the advancing of dynamic gesture recognition technology, it is widely used in various interaction scenarios nowadays. However, the three-dimensional dynamic gesture recognition method is easily disturbed by the external environment, such as illumination, background and shadow. To address these problems, we propose a 3D Dynamic Gesture recognition network model, which use both CNN and LSTM networks and can fuse RGB and depth image information. We conduct experiments with Intel RealSense D415 depth camera and self-built gesture dataset, the results demonstrate that the recognition accuracy of the 3D-DGR model is 99.23%, which is 1.52% higher than the model using only RGB images. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0)

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IOT) Intrusion Detection Utilizing CNN and Fine Tuning It Using Various Optimization Parameters 3

Internet of Things (IOT) Intrusion Detection Utilizing CNN a...

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Kaushiv Gill, Kanwarpartap Singh Chauhan, Rahul Dangi, Sarishma Banerjee, Deepak Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350319125

The Internet of Things (IOT) has experienced significant expansion in recent years, resulting in the development of countless gadgets and systems aimed at improving everyday life. This study explores the fundamental aspects of security in the Internet of Things (IOT), including vulnerabilities, potential attack routes, and essential countermeasures. This study presents a novel intrusion detection methodology for the Internet of Things (IOT) by leveraging Convolutional Neural Networks (CNNs). The proposed method aims to improve the performance of the CNN model by fine-tuning it with different optimization parameters. The initial approach involves the building of a convolutional neural network (CNN) model for intrusion detection, capitalizing on its inherent capability to extract information in a hierarchical manner. The objective of the fine-tuning procedure is to optimize the model's accuracy, sensitivity and specificity, hence enhancing its capacity to reliably identify and categorize intrusions within the Internet of Things (IOT) network. We conduct tests on a benchmark IOT intrusion detection dataset, assessing the proposed approach's performance in terms of Accuracy and Loss Graphs and accuracy. The findings confirm the effectiveness of utilizing Convolutional Neural Networks (CNNs) in the context of Intrusion Detection Systems (IDS) for Internet of Things (IOT) environments. Furthermore, the study highlights the need of tweaking the parameters of the CNN model to enhance its detection capabilities and achieve higher performance. Moreover, the present study highlights the ever-evolving nature of security in the Internet of Things (IOT), placing significant emphasis on the need of continuous research, collaborative endeavours across several sectors, and the establishment of regulatory frameworks to foster a safe and reliable IOT environment. © 2023 IEEE.

关键词： Artificial intelligence Classification Data Science Deep Learning Internet of Things machine Learning

来源：评论

学校读者我要写书评

暂无评论

Implementing Artificial intelligence with IoT, Prolonging the Existence of Marine Animals 3

Implementing Artificial Intelligence with IoT, Prolonging th...

引用

3rd international conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Batra, Devyansh Sharma, Ashish Wasson, Vikas Chandigarh University Computer Science Department India Chandigarh University Electrical Engineering Department India

ISBN: (纸本)9798350330724

Fish in aquariums live shorter lives for a variety of reasons. To protect life during this research, a machine learning algorithm was created;the algorithm that was created would help fish live longer. Before the aquarium has developed with the proper composition to keep fish in good health, excessive amounts of nitrates and ammonium in the water might be detrimental. Until these toxins can be flushed out of the fish's bodies by the benign bacteria within, sudden deaths of fish may occur. Since much of the possibility for human error has already been minimized in this process, human involvement is not required. This teaching strategy will contain backup systems and temperature control that is automatic and accessible to the user when they need it. The contents of this aquarium may be changed whenever you choose by using the vacuum jets that are connected to the inlet and flow out. This research will make use of certain compounds as an alternate technique to protect the fluid's purity. With the use of the Q Cannon camera, users will be permitted to discharge food pellets into an aquarium once a certain amount of time has passed in this unique idea. In addition, chlorine will be used in this project as a backup chemical that will be used if the water change fails or dangerous viruses or bacteria quickly arise an aquatic ecosystem. This innovative attempt will also have two tagging systems that can help the user interpret extra information about the aquatic animals living in his aquarium. This effort will include proper hiding places and artificial foliage so that the aquatic creature will feel more at home in his preferred habitat. Thanks to polyurethane, the most recently constructed structure will additionally feature adequate insulation for temperature control, which is beneficial to maintain an appropriate temperature in the water of the aquarium. Additionally, this neural network system will have a forecasting algorithm that can tell the user how many days are le

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Moving Object Detection and recognition Algorithm Based on Deep Learning

Moving Object Detection and Recognition Algorithm Based on D...

引用

Information Technology,Big Data and Artificial intelligence (ICIBA), international conference on IEEE international conference on

作者： Jipan Li Keqiang Tian Shuzhi Jing Ke Xu Weiling Wang Dejian Liu Zhizhou Sun State Grid Heze Power Supply Company Heze China State Grid Intelligence Technology Co. Ltd. Jinan China

Aiming at the problem that the deep learning detection framework based on video moving object detection cannot make full use of the motion information of the upper and lower frames, and the computational complexity is high, an improved SSD detection algorithm is proposed. The algorithm uses the lightweight network MobileNet as the basic network in the SSD model to reduce the time and computation spent in extracting image features, and establish the correlation between frames. Based on the Tensorflow deep learning framework, training is carried out on COCO (Common Objects in Context) dataset, and comparative experiments on moving object recognition accuracy and recognition speed are carried out. Experimental results show that the algorithm has good performance in terms of detection accuracy and speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building Funding-Standardized Research Algorithms Based on Big Data Analysis 3

Building Funding-Standardized Research Algorithms Based on B...

引用

3rd international conference on Artificial intelligence, Big Data and Algorithms, CAIBDA 2023

作者： Jiang, Xiaolin Wang, Peng Ye, Caizeng Wang, Ruiyang Shandong Institute of Commerce and Technology Jinan250103 China Jinan Engineering Polytechnic Jinan250200 China Beijing Normal University-Hong Kong Baptist University United International College Zhuhai519087 China

ISBN: (纸本)9781643684444

In recent years, China's education standardization work has been continuously strengthened, and a series of educational standards have been formulated and implemented, which have played an important role in regulating, leading and guaranteeing *** the same time, Compared with the practice of education reform and development and the needs of education modernization, Education standardization work still exists the formulation of standards is not scientific and standard, the organization and implementation of standards are not used to often and other problems, The main performance is: the standard consciousness is not strong, The concept of standards has not yet been established, Has not yet formed everything has a standard, according to the standard of handling habits;The standard system is not yet perfect, There is still a gap in the standard supply, Lack of standards in some key areas;The standard formulation mechanism is not perfect, The standardization of standardization work should be further improved;The standard quality still needs to be improved, Dynamic adjustment mechanism is not sound, Some standards have aging problems;Implementation of the standards needs to be increased, The implementation mechanism is still not yet perfect;The international influence of educational standards is not yet strong, international recognition is not high, This paper uses deep learning algorithm to merge the basic information of college students, The accuracy prediction and analysis of the poor students, It plays a very good auxiliary role in the subsequent identification of poor students. © 2023 The Authors.

关键词： Students

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 << < 131 132 133 134 135 136 137 138 139 140 > >>

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：