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

4,593 篇 会议
498 册 图书
65 篇 期刊文献

馆藏范围

5,155 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,376 篇 工学
- 2,738 篇 计算机科学与技术...
- 1,816 篇 软件工程
- 722 篇 信息与通信工程
- 721 篇 光学工程
- 661 篇 电气工程
- 415 篇 生物工程
- 359 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 234 篇 机械工程
- 223 篇 电子科学与技术（可...
- 125 篇 仪器科学与技术
- 122 篇 化学工程与技术
- 116 篇 安全科学与工程
- 95 篇 交通运输工程
- 90 篇 材料科学与工程（可...
- 68 篇 建筑学
- 58 篇 土木工程
1,680 篇 理学
- 926 篇 物理学
- 721 篇 数学
- 452 篇 生物学
- 203 篇 统计学（可授理学、...
- 119 篇 化学
- 57 篇 系统科学
490 篇 管理学
- 269 篇 图书情报与档案管...
- 241 篇 管理科学与工程(可...
- 79 篇 工商管理
439 篇 医学
- 417 篇 临床医学
- 127 篇 基础医学(可授医学...
- 89 篇 药学(可授医学、理...
60 篇 法学
- 59 篇 社会学
54 篇 农学
35 篇 教育学
31 篇 艺术学
29 篇 经济学
11 篇 文学
11 篇 军事学

主题

811 篇 computer vision
622 篇 pattern recognit...
535 篇 image processing
355 篇 image processing...
347 篇 artificial intel...
336 篇 image segmentati...
269 篇 feature extracti...
202 篇 image recognitio...
171 篇 deep learning
155 篇 computer graphic...
149 篇 computer imaging...
137 篇 face recognition
122 篇 object recogniti...
121 篇 machine learning
117 篇 convolutional ne...
114 篇 image analysis
113 篇 object detection
108 篇 information syst...
105 篇 cameras
105 篇 shape

机构

25 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
14 篇 national center ...
14 篇 institute of ima...
10 篇 shanghai jiao to...
10 篇 tsinghua univers...
10 篇 university of ch...
10 篇 institute of aut...
9 篇 institute of ima...
9 篇 computer vision ...
8 篇 indian statistic...
8 篇 inria nancy gran...
8 篇 dalian universit...
8 篇 icube université...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 department of co...

作者

24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
24 篇 jordi pont-tuset
17 篇 de-shuang huang
14 篇 stefanie speidel
12 篇 wilfried philips
9 篇 paul scheunders
9 篇 h. bischof
9 篇 jie yang
9 篇 stéphane cotin
9 篇 dan popescu
9 篇 mohamed kamel
8 篇 umapada pal
8 篇 aurélio campilho
8 篇 yefeng zheng
8 篇 kok wai wong
8 篇 christian barill...
8 篇 ilias maglogiann...
8 篇 tieniu tan

语言

5,032 篇 英文
103 篇 其他
52 篇 中文

检索条件"任意字段=4th International Conference on Computer Vision, Pattern Recognition and Image Processing"

共 5156 条记录，以下是181-190 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：

Exploiting Attackability for Effective Textual Adversarial Attacks 4th

Exploiting Attackability for Effective Textual Adversarial A...

引用

4th international conference on Intelligent Systems and pattern recognition-ISPR

作者： Khemis, Salim Yacine, Amara Akrem, Benatia Mohamed Ecole Mil Polytech EMP BP 17 Bordj El Bahri Algiers 16046 Algeria

ISBN: (纸本)9783031821493;9783031821509

Deep learning models have achieved remarkable success across various domains, yet their susceptibility to adversarial attacks remains a pressing concern. While recent advancements in adversarial attacks have aimed to enhance model defenses, many existing techniques suffer from drawbacks such as higher perturbation rates, higher query count, reduced textual similarity, or lower success rates. this paper addresses this problematic by proposing a dynamic search strategy that leverages the concept of attackability to guide and optimise the generation of adversarial attacks. the method seeks to improve the quality of generated adversarial samples via minimizing perturbation rates, query count, and maintaining high success rates. Experimental results demonstrate its effectiveness compared to existing techniques, representing a significant advancement in the field of adversarial attack generation.

关键词： Adversarial attacks and defenses Natural Language processing (NLP) Attackability Deep learning robustness

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional feature fusion network with transformer for image super-resolution 4

Multi-dimensional feature fusion network with transformer fo...

引用

4th international conference on computer vision and pattern Analysis, ICCPA 2024

作者： Chen, Qiaochuan Zhong, Baoqi School of Computer Engineering and Science Shanghai University Shanghai China Key Laboratory of Silicate Cultural Relics Conservation Shanghai University Ministry of Education Shanghai China

ISBN: (纸本)9781510682528

In the context of deep learning applied to single-image super-resolution, the quality of the reconstructed images is largely contingent upon the intricacy of the convolutional neural networks employed. However, this complexity is limited by the static nature of the receptive fields within these networks. Transformers, distinguished by their self-attention mechanism, are capable of capturing global dependencies, a feature that is beyond the reach of conventional CNNs. However, integrating Transformers into CNN architectures poses a challenge. this paper introduces an innovative solution, a MultiDimensional Feature Fusion image Super-Resolution Network that harnesses Transformer's global representation capability. By utilizing the self-attention mechanism, our network achieves effective cross-feature extraction and establishes global dependencies throughout the feature map. A dedicated Multi-Dimensional Feature Fusion Module is employed to enhance feature fusion, further improving the reconstruction quality. Empirical evidence from experiments on the Set5 benchmark dataset reveals that our network outperforms existing state-of-the-art methods by 0.22dB in 4× super-resolution tasks, highlighting the efficacy of our approach. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Color Quality Classification Algorithms in computer Art Education 4

Research on Color Quality Classification Algorithms in Compu...

引用

4th international conference on computer vision and Data Mining, ICCVDM 2023

作者： Li, Xiaojing Shanghai Donghai Vocational and Technical College 6001 Hongmei South Road Minhang District Shanghai China

ISBN: (纸本)9781510674448

In the realm of art education, the assessment of color blending and color differences has traditionally been a manual process, often subject to human subjectivity and variations in visual acuity. this paper delves into the application of computer vision techniques, a significant branch of artificial intelligence, to address these challenges. By leveraging the high precision, objectivity, and fast processing speed of computer vision, this study aims to revolutionize color inspection in art education. the research encompasses various stages, including art image acquisition, preprocessing, color difference calculation, and feedback provision. A focal point of the study is the extraction of features from art images and the exploration of classification algorithms for online color difference assessment. through the application of a data modeling method based on the Morlet wavelet kernel SVM, the research achieves an accuracy rate of 88.67% in the classification of fine art images. While promising, the study also identifies areas for further research, including the quantification of color discrepancies in intricate art images and the enhancement of the classification algorithm's operational speed. © 2024 SPIE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Fourth international conference on computer vision and Data Mining, ICCVDM 2023

Fourth International Conference on Computer Vision and Data ...

引用

4th international conference on computer vision and Data Mining, ICCVDM 2023

ISBN: (纸本)9781510674448

the proceedings contain 106 papers. the topics discussed include: people recognition with foot pressure based on neural network;MVS-STRNet: cross-view space target recognition from multi-view stereo;video visibility prediction method for foggy weather based on spatio-temporal variation feature;comparison and improvement of some attention mechanisms in the video field;enhancing video quality assessment through brightness information;ERBNet: an automatic polyp image segmentation method to enhance receptive field and boundary;exposition and implementation of linear equation system reconstruction method in electromagnetic wave CT imaging;deep learning-based 3D face reconstruction method for video stream;and video anomaly detection via improved future frame prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information Extraction from Visually Rich Documents with Font Style Embeddings 26

Information Extraction from Visually Rich Documents with Fon...

引用

26th international conference on pattern recognition / 8th international Workshop on image Mining - theory and Applications (IMTA)

作者： Oussaid, Ismail Vanhuffel, William Ratnamogan, Pirashanth Hajaiej, Mhamed Mathey, Alexis Gilles, thomas BNP Paribas Paris France

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language processing and layout representation. We propose to challenge the usage of computer vision in the case where both token style and visual representation are available (i.e native PDF documents). Our experiments on three real-world complex datasets demonstrate that using token style attributes based embedding instead of a raw visual embedding in LayoutLM model is beneficial. Depending on the dataset, such an embedding yields an improvement of 0.18% to 2.29% in weighted F1-score with a decrease of 30.7% in the final number of trainable parameters of the model, leading to an improvement in both efficiency and effectiveness.

关键词： Visualization computer vision Computational modeling Layout Benchmark testing Information retrieval Portable document format

来源：评论

学校读者我要写书评

暂无评论

Research on the method of noise interference in brain information perception system 4

Research on the method of noise interference in brain inform...

引用

4th international conference on image processing and Intelligent Control, IPIC 2024

作者： Hong, Tiange Liu, Ying Zhao, Xiaochuan Jin, Leiming Feng, Yunduo Computer Application Technology Institute of China North Industries Group Corporation Haidian Beijing China

ISBN: (纸本)9781510682313

As an important hardware component in the process of EEG recognition, the brain information perception system undertakes the functions of accurate EEG signal acquisition, amplification, conversion, transmission and recognition. As the EEG signal shows the characteristics of weak in amplitude, low SNR, low frequency range and strong randomness, it can be easily affected by EMI in the environment. thus leads to a decrease in accuracy. therefore, the interference sources that interfere with the brain information perception process are sorted out, the simulation is carried out for different objective factors, in order to explore the influence of EMI in the environment on the brain information perception system. Finally, we provide reference and ideas for the interference of the brain information perception system. © 2024 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Segmentation Using image processing In MRI 4

Brain Tumor Segmentation Using Image Processing In MRI

引用

4th international conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Gurusubramani, S. Pranjna, B. Saranya, D. Priya, S. Kumar, D. Sathish Sri Sairam Engineering College Department of Computer Science & Engineering Chennai India

ISBN: (纸本)9798331508845

Brain tumors are a significant health concern in India, with an estimated 40,000 to 50,000 new cases diagnosed annually. the country's limited healthcare resources and infrastructure exacerbate the challenge, leading to delayed diagnosis and treatment. Improper or late segmentation of brain tumors can have devastating consequences, including increased morbidity, mortality, and reduced quality of life. Inaccurate segmentation can lead to incomplete tumor resection, resulting in recurrence and reduced survival rates. Furthermore, delayed diagnosis can cause irreversible damage, such as vision loss, cognitive impairment, and motor dysfunction, significantly impacting patients' daily lives and socioeconomic productivity. Many people are not able to afford for the treatment for this particular disease and this disease becomes fatal for them. therefore, in order to overcome this problem, an accurate and efficient segmentation method, vision Transformer (ViT) approach is crucial to improve patient outcomes and alleviate the burden on India's healthcare system. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Convolutional Neural Networks in Intelligent Editing for Short Video 4

Research on the Application of Convolutional Neural Networks...

引用

4th international conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： He, Luwen Lai, Zhenli Xiamen University of Technology School of Film Television and Communication Xiamen China

ISBN: (纸本)9798350373233

the emergence of short videos has led to the development of intelligent short video editing. this not only streamlines the intricate process of video editing but also empowers regular users to master editing skills. Intelligent editing, which relies on machine learning models and utilizes convolutional neural networks to process computer vision, natural language processing, speech processing, and other facets of editing, results in breakthrough achievements. therefore, short video intelligent editing, which is based on convolutional neural network holds promising prospects and research value. this paper briefly describes the principle of convolutional neural network, introduces its application in clips, and discusses the defects of short video clips and research directions in future. At the same time, a scheme application of short video clip is designed to provide new practical ideas for research in this field. © 2023 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection Based on YOLOv7 Network 4

Traffic Sign Detection Based on YOLOv7 Network

引用

4th IEEE international conference on Power, Electronics and computer Applications, ICPECA 2024

作者： Yang, Yuheng Liu, Haoxuan School of Information Engineering Wuhan University of Technology Wuhan China School of Computer and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798350359589

With the rapid advancement of intelligent driving technologies, target detection, particularly accurate identification of vehicles and pedestrians, becomes crucial. this study focuses on traffic sign detection using the YOLOv7 object detection algorithm, emphasizing efficiency and model architecture. the integration of Mosaic and Mixup techniques for image preprocessing enriches the dataset, enhancing the model's generalization capabilities. Utilizing an enhanced dataset, including traffic sign images under various weather and lighting conditions, the YOLOv7x network was trained and tested. the results indicate high accuracy and robustness in traffic sign detection. the deeper convolution layers and advanced YOLOv7x model demonstrate significant improvements in processing speed and detection accuracy. Moreover, minor adjustments to the network structure further enhance the model's ability to recognize small and partially obscured traffic signs. © 2024 IEEE.

关键词： Convolutional Neural Network Down-sampling image recognition YOLOv7

来源：评论

学校读者我要写书评

暂无评论

LDFUNet: Large-Kernel Convolution and Dynamic Fusion Network for Superpixel Segmentation 4

LDFUNet: Large-Kernel Convolution and Dynamic Fusion Network...

引用

4th international conference on computer vision, image and Deep Learning, CVIDL 2023

作者： Dang, Yuanyuan Wei, Junheng Zhang, Lijie Zhong, Zhaohao College of Computer Science and Engineering Changchun University of Technology Changchun China

ISBN: (纸本)9798350326444

Superpixel is an image preprocessing technique that combines adjacent pixels in an image to form smaller connected regions. It serves as the smallest unit for subsequent image-processing tasks. Reduced computational complexity and improved accuracy of image segmentation. the past superpixel segmentation algorithms need to compute the hard associate map between pixels and seeds, which results in a huge computation cost. To reduce the computation cost, we propose LDFUNet, Large-Kernel Convolution, and Dynamic Fusion Network. Large-Kernel Convolution extract superpixel feature efficiently. And dynamic can fuse the pixel and superpixel feature dynamic, which can capture the pixel-superpixel relationship information dynamic for the final prediction. the experiments show that our method achieves a good trade-off between computational speed and segmentation accuracy. © 2023 IEEE.

关键词： Superpixels

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 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：