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

489 篇 会议
60 册 图书
8 篇 期刊文献

馆藏范围

557 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

323 篇 工学
- 269 篇 计算机科学与技术...
- 204 篇 软件工程
- 53 篇 电气工程
- 50 篇 信息与通信工程
- 38 篇 光学工程
- 26 篇 生物工程
- 23 篇 电子科学与技术（可...
- 20 篇 控制科学与工程
- 19 篇 生物医学工程（可授...
- 14 篇 机械工程
- 14 篇 仪器科学与技术
- 14 篇 建筑学
- 12 篇 交通运输工程
- 12 篇 安全科学与工程
- 11 篇 化学工程与技术
- 9 篇 动力工程及工程热...
- 8 篇 环境科学与工程（可...
- 7 篇 城乡规划学
116 篇 理学
- 51 篇 物理学
- 49 篇 数学
- 27 篇 生物学
- 14 篇 系统科学
- 11 篇 统计学（可授理学、...
- 10 篇 化学
- 7 篇 地理学
58 篇 医学
- 57 篇 临床医学
- 10 篇 基础医学(可授医学...
32 篇 管理学
- 19 篇 管理科学与工程(可...
- 14 篇 图书情报与档案管...
8 篇 法学
- 8 篇 社会学
4 篇 农学
3 篇 教育学
2 篇 经济学
1 篇 军事学

主题

76 篇 computer vision
47 篇 image processing
44 篇 artificial intel...
37 篇 image processing...
32 篇 image segmentati...
27 篇 pattern recognit...
25 篇 computer graphic...
20 篇 deep learning
18 篇 information syst...
17 篇 computer imaging...
17 篇 layout
16 篇 computer science
16 篇 computer archite...
15 篇 graphics process...
15 篇 shape
12 篇 application soft...
12 篇 image analysis
11 篇 object detection
11 篇 image reconstruc...
10 篇 machine vision

机构

6 篇 indian statistic...
6 篇 indian institute...
6 篇 indian inst tech...
6 篇 indian inst tech...
5 篇 indian inst tech...
5 篇 indian institute...
4 篇 institute of aut...
4 篇 school of intera...
4 篇 indian inst tech...
4 篇 microsoft resear...
4 篇 wrocław universi...
3 篇 indian stat inst...
3 篇 indian institute...
3 篇 indian institute...
3 篇 indian institute...
3 篇 tongji universit...
3 篇 indian institute...
3 篇 national key lab...
3 篇 indian inst tech...
3 篇 university of so...

作者

9 篇 mukherjee jayant...
8 篇 chaudhuri subhas...
7 篇 subhasis chaudhu...
7 篇 balasubramanian ...
6 篇 harit gaurav
5 篇 das sukhendu
5 篇 sural shamik
4 篇 yasuyuki matsush...
4 篇 banerjee biplab
4 篇 james m. rehg
4 篇 ngoc thanh nguye...
4 篇 kyoung mu lee
4 篇 bogdan trawiński
4 篇 sukhendu das
4 篇 zhanyi hu
4 篇 jayadeva jayadev...
3 篇 wilfried philips
3 篇 ryszard tadeusie...
3 篇 ravindra hegadi
3 篇 j. kittler

语言

550 篇 英文
4 篇 中文
3 篇 其他

检索条件"任意字段=Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing"

共 557 条记录，以下是101-110 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：

Multi-scale Attention-Based Feature Pyramid Networks for Object Detection 11th

Multi-scale Attention-Based Feature Pyramid Networks for Obj...

引用

11th International conference on image and graphics, ICIG 2021

作者： Zhao, Xiaodong Chen, Junliang Liu, Minmin Ye, Kai Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

ISBN: (纸本)9783030873547

Feature pyramid network (FPN) is widely used for multi-scale object detection. While lots of FPN based methods have been proposed to improve detection performance, there exists semantic difference between cross-scale features. therefore, simple connections bring spatial or channel information loss, while excessive connections bring extra parameters and inference cost. Besides, the fusion of too many features may lead to the information decay and feature aliasing. To deal with the above problems, we propose the Multi-scale Attention-based Feature Pyramid Networks (MAFPN), to fully exploit spatial and channel information and generate a better feature representation for each level from multi-scale features. Taking scale, spatial and channel information into consideration at the same time, MAFPN can process multi-scale input more comprehensively than most conventional methods. the experimental results show that our MAFPN can improve the detection performance of both two-stage and one-stage detectors with an acceptable increase of inference cost. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Generating Description with Multi-feature and Saliency Maps of image 11

Generating Description with Multi-feature and Saliency Maps ...

引用

11th International conference on graphics and image processing (ICGIP)

作者： Liu, Lisha Tian, Chunna Zhang, Ruiguo Ding, Yuxuan Xidian Univ Sch Elect Engn China Elect Technol Grp Corp Res Inst 38 Xian Peoples R China Xidian Univ Taiyuan Satellite Launch Ctr Xian Peoples R China

ISBN: (纸本)9781510635241

Automatically generating the description of an image is a task that connects computer vision and natural language processing. It has gained more and more attention in the field of artificial intelligence. In this paper, we present a model that generates description for images based on RNN (recurrent neural network) with multi-feature weighted by object attention to represent images. We use LSTM (long short term memory), which is a RNN model, to translate multi-feature of images to text. Most existing methods use single CNN (convolution neural network) trained on imageNet to extract image features which mainly focuses on objects in images. However, the context in the scene is also informative to image captioning. So we incorporate the scene feature extracted with CNN trained on Places205. We evaluate our model on MSCOCO dataset based on standard metrics. Experiments show that multi-feature performs better than single feature. In addition, the saliency weight on images emphasizes the salient objects in images as the subject in image descriptions. the results show that our model performs better than several state-of-the-art methods on image captioning.

关键词： Significant object detection multi-feature LSTM (long short term memory) normalization

来源：评论

学校读者我要写书评

暂无评论

Learning Local Neighboring Structure for Robust 3D Shape Representation 35

Learning Local Neighboring Structure for Robust 3D Shape Rep...

引用

35th AAAI conference on Artificial Intelligence / 33rd conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence

作者： Gao, Zhongpai Yan, Junchi Zhai, Guangtao Zhang, Juyong Yang, Yiyan Yang, Xiaokang Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China Univ Sci & Technol China Sch Math Sci Hefei Peoples R China

ISBN: (纸本)9781577358664

Mesh is a powerful data structure for 3D shapes. Representation learning for 3D meshes is important in many computer vision and graphics applications. the recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insight from CNN for 3D shapes. However, 3D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this paper, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each node according to the local neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in the random synthesizer - a new Transformer model for natural language processing (NLP). Comprehensive experiments demonstrate that our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Complex Spatial Region Representation and Similar Matching for Multi-Object image Retrieval 11

Complex Spatial Region Representation and Similar Matching f...

引用

11th International conference on graphics and image processing (ICGIP)

作者： Liu, Dong Wang, Shengsheng Li, Weiqing Li, Shanglin Liu, Yaohui Fang, Fang Xiangnan Univ Sch Software & Commun Engn Chenzhou 423300 Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

ISBN: (纸本)9781510635241

Spatial relationship and structure models play an important role in various computer vision tasks. Many spatial models focus on global relationship modeling and ignore the detail of the internal structure. this will cause a poor performance in capturing discriminative features for a complex multi-object image. In this paper, we present a novel spatial structure model for complex regions with explicit similar measure. three aspects of our method should be noted in comparison to the previous approaches. First, we propose a detailed layered graph model for representing complex regions, which has complete description performance and even the slight differences among the local objects can be also recognized. We further provide similar matching algorithms for topological structures based on the detailed layered graph model. Finally, an effective retrieval framework is proposed and applied to multi-object image retrieval. Rigorous experimental evaluations on two datasets demonstrate that the proposed method outperforms other prevailing approaches.

关键词： image retrieval feature representation spatial structure similarity matching graph similarity

来源：评论

学校读者我要写书评

暂无评论

Eleventh International conference on graphics and image processing, ICGIP 2019

Eleventh International Conference on Graphics and Image Proc...

引用

11th International conference on graphics and image processing, ICGIP 2019

ISBN: (纸本)9781510635234

the proceedings contain 115 papers. the topics discussed include: evaluating the influence of separated RGB channels with ensemble learning;channel convolution residual block for person re-identification;a plug-and-play LSTM-based attention module for person reidentification;light field camera based automatic algorithm for optimal face search;research on still image activity recognition based on deep learning;a novel approach for blind recognition of shortened RS codes;learning local descriptors with latent hard sample mining;and code-aided carrier phase synchronization algorithm for non-binary LDPC-CPM system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre- and Post-processing Strategies for Generic Slice-wise Segmentation of Tomographic 3D Datasets Utilizing U-Net Deep Learning Models Trained for Specific Diagnostic Domains 15

Pre- and Post-processing Strategies for Generic Slice-wise S...

引用

15th International Joint conference on computer vision, Imaging and computer graphics theory and Applications (VISIGRAPP) / 15th International conference on computer vision theory and Applications (VISAPP)

作者： Zwettler, Gerald A. Backfrieder, Werner Holmes, David R., III Mayo Clin Dept Physiol & Biomed Engn Biomed Analyt & Computat Engn Lab Coll Med Rochester MN 55905 USA Univ Appl Sci Upper Austria Dept Software Engn Res Grp Adv Informat Syst & Technol AIST Softwarepk 11 A-4232 Hagenberg Austria Univ Appl Sci Upper Austria Dept Software Engn Med Informat Softwarepk 11 A-4232 Hagenberg Austria

ISBN: (纸本)9789897584022

An automated and generally applicable method for segmentation is still in focus of medical image processing research. Since a few years artificial inteligence methods show promising results, especially with widely available scalable Deep Learning libraries. In this work, a five layer hybrid U-net is developed for slice-by-slice segmentation of liver data sets. Training data is taken from the Medical Segmentation Decathlon database, providing 131 fully segmented volumes. A slice-oriented segmentation model is implemented utilizing deep learning algorithms with adaptions for variable parenchyma shape along the stacking direction and similarities between adjacent slices. Both are transformed for coronal and sagittal views. the implementation is on a GPU rack with TensorFlow and Keras. For a quantitative measure of segmentation accuracy, standardized volume and surface metrics are used. Results DSC=97.59, JI=95.29 and NSD=99.37 show proper segmentation comparable to 3D U-Nets and other state of the art. the development of a 2D-slice oriented segmentation is justified by short training time and less complexity and therefore massively reduced memory consumption. this work manifests the high potential of AI methods for general use in medical segmentation as fully- or semi-automated tool supervised by the expert user.

关键词： Deep Learning U-Net Model-based Segmentation in Medicine Computed Tomography

来源：评论

学校读者我要写书评

暂无评论

Performance of Single Board computers for vision processing

Performance of Single Board Computers for Vision Processing

引用

IEEE Annual Computing and Communication Workshop and conference (CCWC)

作者： Curtis Manore Pratheek Manjunath Dominic Larkin United States Military Academy West Point New York

ISBN: (数字)9781665414906

ISBN: (纸本)9781665430586

With the increasing complexity of machine vision algorithms and growing applications of image processing, how do computers without a dedicated graphics processor perform? this research discusses the computational abilities of two low-cost single board computers (SBCs) by subjecting them to various Visual Inertial Odometry (VIO) algorithms. the end goal of this research is to identify a SBC which meets the requirements of being employed on an Unmanned Aerial System for autonomous navigation.

关键词： computers Visualization Architecture Random access memory computer architecture Complexity theory Sensors

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis on different degrees of jpeg compression used in CBIR systems 11

Comparative analysis on different degrees of jpeg compressio...

引用

11th National conference with International Participation, ELECTRONICA 2020

作者： Marinov, Miroslav University of Ruse Department of Computer Systems and Technologies Ruse7000 Bulgaria

ISBN: (数字)9781728175317

ISBN: (纸本)9781728175317

Content-based image retrieval systems (CBIR) use computer vision methods for organizing, analyzing, processing, and searching of million graphic files uploaded on the Internet daily. For that reason, the retrieval process is a key element of CBIR applications. the best system performance is based on accurate and complete search which must be finished in a reasonable amount of time. It is directly related to extracting, storing, and indexing all necessary metadata from the examined image set. this paper gives information about JPEG compression and how it is used in some of the most widespread CBIR systems. It reveals how different degrees of that compression influence the generated results from custom developed CBIR application. Furthermore, it shows various similarities between the same image set but examined in two different ways - with non-compressed and compressed data retrieved by the system. In the end, conclusions are made on the basis of the results obtained from developed and tested CBIR application which was made for these purposes. © 2020 IEEE.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

3D Object Reconstruction from a Single 2D image: Performance of Two Novel Frameworks Based on Lightweight CNN Architectures and Free-Form Deformation of Meshes 11

3D Object Reconstruction from a Single 2D Image: Performance...

引用

11th International conference on graphics and image processing (ICGIP)

作者： Pradhan, Saurabh Madhusudhanan, Kiran Munoz-Giraldo, Leandro Faruq, MohiUddin Jomaa, Hadi Stiftung Univ Hildesheim Informat Syst & Machine Learning Lab Hildesheim Germany

ISBN: (纸本)9781510635241

In computer vision, object reconstruction is the task of inferring the 3D shape of an object based on a single or multiple 2D images. For such purpose, most common frameworks use voxel grids and point clouds. However, both of these approaches have strong limitations. On one hand, the computational cost of using voxels grows cubically as the resolution of the voxels increases. therefore, 3D object reconstructions are usually set to low resolution. On the other hand, point clouds are unstructured in nature and the proper definition of surfaces and contours is complex. In this study, 3D object reconstruction is carried out applying free-form deformations on pre-existent 3D meshes, through two basic learning processes: template selection and template deformation. From this approach, it is possible to generate high-quality 3D object reconstructions with a lower computational cost. Concretely, two novel lightweight CNNs models are developed and tested: a multi-target learner (Model A) and depth information learner (Model B). According to the results, the performance of the multi-target learner regarding the template selection was around three times better (lower error) than in the baseline architecture, which improved the quality of the 3D reconstructions, whereas the depth-information learner showed promising results in the reconstruction of objects with complex geometry. the inherent issue of using chamfer distance as a loss measure is also examined.

关键词： Free-Form Deformation Convolutional Neural Networks 3D reconstruction 3D meshes Chamfer loss

来源：评论

学校读者我要写书评

暂无评论

Single image dehazing using image boundary constraint and nearest neighborhood optimization 18

Single image dehazing using image boundary constraint and ne...

引用

proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Sidharth Gautam Tapan Kumar Gandhi B. K. panigrahi Indian Institute of Technology New Delhi India

ISBN: (纸本)9781450366151

Single image dehazing is an ill-posed problem that requires assumptions, priors and constraints to solve. In this paper, boundary constraint utilizing median filter has been proposed on the image radiance for the rough estimation of transmission-map in haze images. Furthermore, for the refinement of estimated transmission-map, the proposed method use a multi-dimensional feature space that uses nearest neighborhood optimization under the framework of non-local principle. Experimental results manifest that proposed method is effective and results in visually appealing dehaze images that can be useful for subsequent user or computer based application.

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56页 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：