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

1,621 篇 会议
14 册 图书
12 篇 期刊文献

馆藏范围

1,647 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,161 篇 工学
- 889 篇 计算机科学与技术...
- 588 篇 软件工程
- 312 篇 光学工程
- 272 篇 信息与通信工程
- 258 篇 电气工程
- 174 篇 生物工程
- 148 篇 控制科学与工程
- 119 篇 机械工程
- 107 篇 生物医学工程（可授...
- 56 篇 电子科学与技术（可...
- 48 篇 材料科学与工程（可...
- 48 篇 化学工程与技术
- 47 篇 安全科学与工程
- 37 篇 仪器科学与技术
- 35 篇 交通运输工程
- 25 篇 网络空间安全
- 23 篇 建筑学
545 篇 理学
- 340 篇 物理学
- 196 篇 数学
- 175 篇 生物学
- 57 篇 化学
- 57 篇 统计学（可授理学、...
208 篇 医学
- 195 篇 临床医学
- 60 篇 基础医学(可授医学...
- 45 篇 药学(可授医学、理...
- 25 篇 公共卫生与预防医...
174 篇 管理学
- 96 篇 管理科学与工程(可...
- 80 篇 图书情报与档案管...
- 31 篇 工商管理
28 篇 农学
- 28 篇 作物学
19 篇 法学
17 篇 经济学
7 篇 教育学
5 篇 军事学
1 篇 文学

主题

307 篇 computer vision
228 篇 image processing
102 篇 image segmentati...
92 篇 feature extracti...
71 篇 deep learning
50 篇 object detection
42 篇 cameras
39 篇 image edge detec...
35 篇 convolutional ne...
34 篇 visualization
34 篇 image recognitio...
32 篇 machine learning
32 篇 image reconstruc...
31 篇 neural networks
30 篇 image color anal...
28 篇 computational mo...
28 篇 shape
28 篇 training
26 篇 image analysis
25 篇 face recognition

机构

6 篇 university of ch...
5 篇 comput & inf sci...
5 篇 department of co...
4 篇 chitkara univers...
4 篇 image processing...
4 篇 beijing institut...
4 篇 college of compu...
3 篇 shanghai jiao to...
3 篇 dept of electr &...
3 篇 south china univ...
3 篇 inria sophia-ant...
3 篇 school of comput...
3 篇 department of ma...
3 篇 shenyang institu...
3 篇 department of co...
3 篇 school of electr...
3 篇 school of comput...
3 篇 college of compu...
3 篇 dept of control ...
3 篇 department of in...

作者

6 篇 andayani u.
5 篇 syahputra m.f.
5 篇 mohana
5 篇 siregar b.
4 篇 yang yang
4 篇 hassan ghassemia...
4 篇 li hui
4 篇 shohreh kasaei
4 篇 e.j. delp
3 篇 luo haibo
3 篇 paul joseph sure...
3 篇 wang wei
3 篇 wang qian
3 篇 ying liu
3 篇 maryam imani
3 篇 saurav sumeet
3 篇 weickert joachim
3 篇 muchtar m.a.
3 篇 xin wang
3 篇 aggarwal j.k.

语言

1,615 篇 英文
26 篇 其他
9 篇 中文
1 篇 德文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Computer Vision and Image Processing, CVIP 2018"

共 1647 条记录，以下是111-120 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：

COMPACT image REPRESENTATION FROM MULTISCALE EDGES

引用

3rd international CONF ON computer vision

作者： ZHONG, S MALLAT, S Courant Inst of Math Sci New York Univ NY USA

ISBN: (纸本)0818620579

The edges of an image can be detected at different scales from the local maxima of its wavelet transform. An algorithm is described that reconstructs images from their edges at dyadic scales. The wavelet maxima representation is a novel reorganization of the image information that makes it possible to develop algorithms uniquely based on edges for solving image processing and computer vision problems. The evolution of the wavelet maxima across scales gives a precise characterization of the edge type which can be used for pattern recognition. A coding algorithm is described that selects the most important image edges in order to obtain a compact representation.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

An image caption generation method based on improved attention mechanism 3

An image caption generation method based on improved attenti...

引用

3rd international conference on computer vision, image and Deep Learning and international conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Su, Yingying Bian, Minjie Cheng, Chen Huang, Yuzhe Shanghai University Shanghai China

ISBN: (纸本)9781665459112

image captioning is a research hotspot in the field of image understanding. It spans the fields of computer vision and natural language processing. Most of the image captioning researches use deep learning technology, especially using Convolutional Neural Networks(CNN) as encoder-decoder structure for feature extraction. The existing captioning model is not of high quality, the important parts of the image are not sufficiently extracted features and the model is too complex. To address these problems, this paper introduces a new generation method based on attention mechanism. First, an efficient attention module is introduced to improve the feature extraction effect based on traditional attention mechanism. It reduces the model complexity and better extracts the important part of image features. The method uses convolutional features extracted from a pre-trained CNN model which integrate the features with the attention mechanism. Second, we also select the GRU language model as the decoder to construct descriptive sentences. Finally, experiments on the MSCOCO dataset and Flickr30k dataset show that the model proposed in this paper effectively improves the quality of descriptive sentences. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Aircraft Target Detection Based on Attention Mechanism and Faster R-CNN 3

Aircraft Target Detection Based on Attention Mechanism and F...

引用

3rd international conference on computer vision, image and Deep Learning and international conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lai, Yunqian Dong, Xinyue Tang, Yuan Chengdu University of Technology College of Computer and Network Security Chengdu China

ISBN: (纸本)9781665459112

Aircraft, as a special strategic target, has high value in both civil and military use, and it is especially important to achieve intelligent scientific aircraft target detection compared to traditional methods. Therefore, an aircraft detection method based on attention mechanism and Faster R-CNN target detection algorithm is proposed in this paper. The RSOD dataset is selected, and the VOC format dataset is used for pre-processing and data enhancement. The Faster R-CNN model is constructed, which uses ResNet50 as the backbone network for feature extraction and also adds the attention mechanism in the backbone network;the region proposal is obtained after convolving the feature extraction results using the RPN(Region Proposal Network);the prediction results are finally obtained by pooling using ROI Pooling. The experimental results show that the model can have good recognition effect and provide help for the intelligent recognition of aircraft. © 2022 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Distant Blurred Pedestrian Detection: Based on SSD Network with SRGAN image Super Resolution 3

Distant Blurred Pedestrian Detection: Based on SSD Network w...

引用

3rd international conference on computer vision, image and Deep Learning and international conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Zhang, Naifeng Beijing Institute of Technology School of Computer Science Beijing China

ISBN: (纸本)9781665459112

Traditional target detection methods have poor accuracy when processing lower resolution images with many pedestrians, particularly for small and blurry targets whose features are not manifested as significantly as the larger, clearer ones. This paper proposes an SSD pedestrian detection method with super-resolution image enhancement to address this problem. Because the small blurry pedestrians in the distance usually appear in the central part of the image, the model this paper proposed crops the central part of the screen and enhances it using SRGAN. After that, this paper use SSD to detect the enhanced image again. The detection results are fused with the normal detection results to obtain higher pedestrian detection accuracy. For the experiments, the AP of the proposed method reaches 0.693, and F1 comes to 0.709 in the street scene, which is 0.031 and 0.061 higher than the original SSD network. Meanwhile, the AP reaches 0.722 and F1 reaches 0.737 in the denser pedestrian scene, which is 0.044 and 0.085 more elevated than the original SSD network, reflecting the significant improvements in our proposed method's detection accuracy. © 2022 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

vision Mesh: A Novel Video Sensor Networks Platform for Water Conservancy Engineering

Vision Mesh: A Novel Video Sensor Networks Platform for Wate...

引用

3rd IEEE international conference on computer Science and Information Technology (ICCSIT)

作者： Zhang, Meiyan Cai, Wenyu Zhejiang Water Conservancy & Hydropower Coll Dept Elect Engn Hangzhou 310018 Zhejiang Peoples R China Hangzhou Dianzi Univ Sch Elect & Informat Hangzhou 310018 Zhejiang Peoples R China

ISBN: (纸本)9781424455379

Video is an important medium for the observation of a variety of phenomena in the physical world such as for water conservancy engineering. Video sensor networks (VSN) consists of a large number of sensor nodes with cheap CMOS cameras, therefore, it has the ability of large scale visual monitoring. However, a kind of powerful and scalable platform is urgent for simulation and development of VSN. This paper proposed a novel and scalable video sensor networks platform named as vision Mesh for water conservancy engineering. vision Mesh is composed of a mass of image or video sensor nodes - vision Motes, with which multi-view image or video information of FOV (Field of View) can be acquired simply. vision Mote is built with Atmel ARM9 CPU and operated on Linux operating system, with TI CC2430 Zigbee module taken as wireless transceiver. Furthermore, OpenCV machine vision lib is migrated to vision Mesh platform so as to improve video processing ability, therefore, vision Mesh has the ability of image and video processing and is of strong scalability to extend performance. In this paper, we provide an overview of vision Mesh architecture and provide an insightful platform for VSN.

关键词： Video sensor networks CMOS camera vision Mesh vision Mote Water Conservancy Engineering

来源：评论

学校读者我要写书评

暂无评论

An efficient post-processing approach for dimensionality reduction methods for face recognition 3

An efficient post-processing approach for dimensionality red...

引用

3rd international conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Abbad, Abdelghafour Abbad, Khalid Tairi, Hamid Fac Sci Dhar EL Mahraz Lab LIIAN Fes Morocco Fac Sci & Technol Lab ISA Fes Morocco

ISBN: (纸本)9781538605516

In this paper we propose a new post-processing approach for dimensionality reduction methods based on multidimensional ensemble empirical mode decomposition (MEEMD). In the proposed method, the features are decomposed into different components and then we maximize the dependency and the dispersion between classes thanks to Gaussian filter and Butterworth filter. The performance of the proposed algorithm is demonstrated in experiments by several dimensionality reduction techniques on two public databases.

关键词： computer vision dimensionality reduction techniques face recognition MEEMD pattern recognition post-processing

来源：评论

学校读者我要写书评

暂无评论

Unfeatured Weld Positioning Technology Based on Neural Network and Machine vision 3

Unfeatured Weld Positioning Technology Based on Neural Netwo...

引用

3rd IEEE international conference on image, vision and Computing (ICIVC)

作者： Cai, Chengtao Wang, Boyu Liu, Yue Yan, Yongjie Harbin Engn Univ Coll Automat Harbin Heilongjiang Peoples R China State Key Lab Air Traff Management Syst & Technol Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538649916

In machine vision, image processing technology is the basis of target recognition and positioning. When the background of the image is complex, especially when the background feature is similar to the target feature, the accuracy of the target recognition by traditional image processing methods cannot be guaranteed. In this paper, based on the background of automatic welding technology, proposing a new method of combining the neural networks and machine vision. Specifically, the image is preprocessed by using an improved convolutional auto-encoder to enhance the target features and remove the characteristics of the main interferers. Then, use the improved traditional image processing technology to extract the target and complete the processing of the featureless image. Finally, use a binocular camera to achieve accurate positioning of the target. This paper provides a new idea for the identification and positioning of the target.

关键词： neural networks machine vision weld positioning featureless image convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Tiny Electronic Component Detection Based on Deep Learning 3

Tiny Electronic Component Detection Based on Deep Learning

引用

3rd IEEE international conference on Cloud Computing and Internet of Things, CCIOT 2018

作者： Liu, Chun Liu, Shaoqian HuBei University of Technology School of Computer Wuhan China

ISBN: (纸本)9781538671412

Tiny electronic component detection mostly suffers from compact size and multiple interferences of environment. To solve this problem, this paper presents an object detection method based on convolutional neural networks (CNNs). This method combines residual blocks in residual networks with CNNs. The CNNs can reduce the dimensions of the image, and the residual block in the residual network can train deeper neural networks, and then use the successful application of CNNs in computer vision to improve the recognition rate of components and improve the efficiency of automated processing of tiny electronic components. After the hyper-parameter adjustment, this method achieved 95.63% accuracy on our test set. © 2018 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

3D objects descriptors methods: Overview and trends 3

3D objects descriptors methods: Overview and trends

引用

3rd international conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： H'roura, Jihad Bekkari, Aissam Mammass, Driss Bouzit, Ali Mansouri, Alamin Roy, Michael Le Goic, Gaetan Ibn Zohr Univ IRF SIC Lab Agadir Morocco Univ Bourgogne Franche Comte LE2I FRE CNRS ENSAM UBFC Lab 2005 Auxerre France

ISBN: (纸本)9781538605516

Object recognition or object's category recognition under varying conditions is one of the most astonishing capabilities of human visual system. The scientists in computer vision have been trying for decades to reproduce this ability by implementing algorithms and providing computers with appropriate tools. Hence, several intelligent systems have been proposed To act in this field, numerous approaches have been proposed In this paper we present an overview of the current trend in 3D objects recognition and describe some representative state of the art methods, highlighting their limits and complexity.

关键词： 3D objects Recognition computer vision skeleton Keypoints

来源：评论

学校读者我要写书评

暂无评论

3D Reconstructions with KinFu Using Different RGBD Sensors 3

3D Reconstructions with KinFu Using Different RGBD Sensors

引用

3rd IEEE international conference on image processing, Applications and Systems, IPAS 2018

作者： Patiño Mejia, Isabel C. Zell, Andreas University of Tuebingen Tuebingen Germany

ISBN: (纸本)9781728102474

RGBD sensors are widely used in robotics and computer vision. Since the Microsoft Kinect was launched, various other sensors, such as the Asus Xtion PRO LIVE and the Intel R200, have been developed. Among other applications, these sensors are useful for 3D reconstruction, which can be achieved with KinFu (an open-source implementation of KinectFusion). Reconstructions of objects and people are useful in multiple fields such as computer graphics and ergonomics. In this paper, we analyze if the 3D reconstructions generated by KinFu depend on the sensor used to record its input. The analysis comprehends qualitative and quantitative evaluations of reconstructions created from point clouds recorded with six well-known sensors. The results suggest that the reconstruction is sensor dependent and the selection of a determined sensor is conditioned to the requirements of each application. © 2018 IEEE.

关键词： image reconstruction

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165页 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：