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

509 篇 会议
264 篇 期刊文献
1 册 图书

馆藏范围

774 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

501 篇 工学
- 325 篇 计算机科学与技术...
- 285 篇 软件工程
- 125 篇 信息与通信工程
- 93 篇 光学工程
- 81 篇 控制科学与工程
- 61 篇 生物工程
- 56 篇 电子科学与技术（可...
- 51 篇 机械工程
- 49 篇 生物医学工程（可授...
- 45 篇 电气工程
- 30 篇 化学工程与技术
- 25 篇 仪器科学与技术
- 16 篇 交通运输工程
- 15 篇 土木工程
- 14 篇 航空宇航科学与技...
- 13 篇 建筑学
- 9 篇 力学（可授工学、理...
- 9 篇 材料科学与工程（可...
314 篇 理学
- 178 篇 数学
- 105 篇 物理学
- 72 篇 生物学
- 65 篇 统计学（可授理学、...
- 28 篇 化学
- 23 篇 系统科学
121 篇 管理学
- 67 篇 管理科学与工程(可...
- 62 篇 图书情报与档案管...
- 12 篇 工商管理
30 篇 医学
- 24 篇 临床医学
- 18 篇 基础医学(可授医学...
- 16 篇 药学(可授医学、理...
8 篇 法学
6 篇 经济学
6 篇 艺术学
5 篇 教育学
5 篇 农学
4 篇 军事学
2 篇 文学
1 篇 哲学

主题

56 篇 feature extracti...
45 篇 pattern recognit...
42 篇 image processing
39 篇 image segmentati...
27 篇 training
22 篇 support vector m...
21 篇 laboratories
21 篇 computer vision
18 篇 object detection
18 篇 face recognition
18 篇 principal compon...
17 篇 neural networks
17 篇 shape
16 篇 algorithm design...
16 篇 image analysis
16 篇 image reconstruc...
16 篇 robustness
15 篇 histograms
15 篇 artificial intel...
15 篇 image recognitio...

机构

74 篇 image processing...
34 篇 institute of ima...
21 篇 school of inform...
18 篇 state key labora...
17 篇 key laboratory o...
17 篇 institute for pa...
15 篇 school of softwa...
13 篇 school of comput...
12 篇 key laboratory o...
11 篇 key laboratory o...
10 篇 key laboratory o...
10 篇 centre for visio...
9 篇 national laborat...
9 篇 institute of ima...
9 篇 institute of pat...
9 篇 laboratory of im...
9 篇 state key labora...
9 篇 university of ch...
9 篇 pattern recognit...
8 篇 national key lab...

作者

67 篇 ping guo
34 篇 yang jie
32 篇 zhang tianxu
27 篇 guo ping
25 篇 qian yin
23 篇 huang xiaolin
18 篇 jie yang
15 篇 zhou jie
15 篇 ding mingyue
14 篇 jinwen tian
14 篇 tian jinwen
14 篇 wu xiao-jun
14 篇 tianxu zhang
14 篇 liu jian
14 篇 kittler josef
12 篇 li qishen
12 篇 jian liu
12 篇 shen hong-bin
11 篇 meng fandong
11 篇 robi polikar

语言

738 篇 英文
22 篇 中文
14 篇 其他

检索条件"机构=Processing and Pattern Recognition Laboratory"

共 774 条记录，以下是281-290 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：

Generative Zero-shot Image Classification based on Generative Feature Constraint 10

Generative Zero-shot Image Classification based on Generativ...

引用

10th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2022

作者： Yu, Xiao Li, Qishen Huang, Hua Li, Qiufeng School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang China Jiangxi China

ISBN: (数字)9781665422079

ISBN: (纸本)9781665422079

Zero-shot learning (ZSL) utilizes semantic information that is auxiliary information to transfer knowledge from seen classes to unseen classes, thereby realizing the recognition of unseen classes. The generative methods train the model to generate pseudo image features for the unseen classes, thus transforming ZSL into a supervised learning problem. However, the classification performances of these methods still suffer from weak generalization. To address this issue, the paper proposes a novel Generative Adversarial Network based on Generative Feature Constraint (GFCGAN). First, based on the LsrGAN [1], a semantic constraint module is added to restrict the generated image features by keeping the semantic information consistent. Then, in the case of keeping the semantic relationships between classes consistent, the generated image features of unseen classes are farther away from the feature prototypes of their most similar classes in both semantic and feature space so as to train the generative model and generate high-quality pseudo image features. Finally, the trained classifier is used to classify images of unseen classes. Experiments on standard datasets verify the effectiveness of our model and achieve good results. © 2022 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Statistical Image Upsampling Method Based on CUDA

Statistical Image Upsampling Method Based on CUDA

引用

International Conference on Computational Intelligence and Security

作者： Xin Zheng Qingqing Xu Peipei Pan Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

In many application fields, an appropriate high-quality fast image upsampling method is required. Although many interpolation-based upsampling methods have been proposed, the quality of result images is not satisfactory. Some of them are very fast, but produce poor quality images, the others can produce high quality images, but the methods in them are slow. In our paper, we proposed a fast statistical image upsampling method based on CUDA, it can obtain high quality images based on reducing the input resolution-grids dependency artifacts. Thus, we can rebuild low resolution images' sharp edges fast and get high-quality upsampled images in real time. We have applied this method in the multi-resolution texture generation of large scale terrain rendering. Experiments prove that our method can receive ideal effects in real time.

关键词： Graphics processing units Mathematical model Image edge detection Image resolution Markov processes Standards Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Blind deconvolution of speech mixtures based on time-frequency processing and statistical analysis

Blind deconvolution of speech mixtures based on time-frequen...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Ke Hu Zengfu Wang Laboratory of Audio-visual Information Processing and Pattern Recognition University of Science and Technology Hefei Anhui China

来源：评论

学校读者我要写书评

暂无评论

Image Completion with Automatic Structure Propagation

Image Completion with Automatic Structure Propagation

引用

International Conference on Computational Intelligence and Security

作者： Peipei Pan Xin Zheng Qingqing Xu Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

In this paper, we propose a novel approach for image completion with automatic structure propagation. This method integrates two stages: Firstly, it extends the salient structure lines from the known regions to the unknown by following a local self-similarity assumption on natural images. Then guided by the structure information, it restores the missing region by patch-based texture synthesis. Experiment results demonstrate a better effect of our method than that of the previous patch-based texture synthesis image completion algorithm.

关键词： Image edge detection Image segmentation Image reconstruction Image resolution Filling Image restoration Sun

来源：评论

学校读者我要写书评

暂无评论

Adaptive nonlinear auto-associative modeling through manifold learning

引用

9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2005

作者： Zhang, Junping Li, Stan Z. Intelligent Information Processing Laboratory Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Beijing 100080 China

ISBN: (纸本)3540260765

We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Enabling Multi-scale Features and Double-Attention for Single-image 3D Urban Reconstruction

Enabling Multi-scale Features and Double-Attention for Singl...

引用

2021 China Automation Congress, CAC 2021

作者： Miao, Jun Shen, Ji Jiang, Ruixiang Chu, Jun Guo, Luanzheng The School of Aeronautical Manufacturing Engineering Nanchang Hangkong University Nanchang330063 China The Department of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China The Pacific Northwest National Laboratory WA99354 United States

ISBN: (纸本)9781665426473

3D reconstruction from a single RGB image for urban scenes has been a foundation for safety-critical applications such as autonomous driving and city planning. It is essential to develop 3D reconstruction models that are accurate for these applications. The most recent single-image 3D reconstruction models leverage representative neural networks to address the problem and have achieved promising results. However, these approaches cannot correctly calculate the segmentation map and reconstruct depth for ambiguous scene regions and when scene information gets lost going through down-sampling layers. To solve this problem, we propose EMERALD, an end-to-end single-image 3D reconstruction framework, in which we empower the fully convolutional networks (FCN) with multi-scale contextual features and a novel double-attention mechanism to advance its discrimination capability on ambiguous scene regions and loss of scene details. The evaluation results on two leading urban- scene data sets, Cityscapes (Segmentation Covering (SC)1 of 61.2%) and SYNTHIA (SC of 81.9%), demonstrate the optimized network architecture's effectiveness. © 2021 IEEE

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Object Detector based on Enhanced Multi-scale Feature Fusion Pyramid Network

Object Detector based on Enhanced Multi-scale Feature Fusion...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Luan Zhao Xiaofeng Zhang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Constructing the pyramidal architecture for the feature is currently a very effective way to obtain feature information of objects at different scales. Although the feature pyramid can realize the recognition and detection of multi-scale objects in the object detection task well, it still has some limitations. Since the feature information of different levels is often not from the same layer of the network, it is difficult to obtain the feature of different objects information at a certain scale from a certain level feature map of the pyramid network. To solve this problem, we present a novel object detection architecture, named Enhanced Multi-scale Feature Fusion Pyramid Network (EMFFPNet). Our network consists of Enhanced Multi-scale Feature Fusion Module (EMFFM) and Predictor Optimization Module (POM). In EMFFM, Features at different levels can be fused into the Enhanced features as outputs, which are more representative and deterministic. In order to enable the enhanced features to play their respective roles in the pyramid network, we assign different weights to fusion features of different levels in POM. We perform the experiments on the COCO detection benchmark. The experimental results indicate that the performance of our model is much better than the state-of-the-art model.

关键词： Object detection Predictive models Feature extraction Task analysis Information technology Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Gait recognition Algorithm GCGait based on Skeleton 3

Gait Recognition Algorithm GCGait based on Skeleton

引用

3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Ma, Ru Zhang, Jikai Jia, Mengyu Lv, Xiaoqi Inner Mongolia University of Science and Technology School of Information Engineering Baotou China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou China Inner Mongolia University of Technology School of Information Engineering Hohhot China

ISBN: (纸本)9781665490788

To solve the problem of low accuracy of gait recognition in complex scenes, a novel skeleton-based gait recognition algorithm, GCGait, is proposed. Taking human posture as the input of gait feature, the interference caused by wearing changes and other factors is reduced. To extract sufficient input features, multi-branch input is used in the early stage of the model. By introducing the multi-attention mechanism, the network can learn the semantic information of the non-directly connected joints, excavate the most discriminative features from complex videos, and further improve the recognition performance. In order to reduce the influence of cross view, the fusion loss function is used in the experiment. Experimental results show that the average recognition rate of the proposed algorithm on the CASIA-B dataset is improved by 5.2%, and the average recognition accuracy on the OU-MVLP dataset is increased by 66.3%, which proves the effectiveness of the proposed method. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Line-based cascade labeling algorithm for hyper-scale issue

Line-based cascade labeling algorithm for hyper-scale issue

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Zhao, Hualong Sang, Hongshi Zhang, Tianxu Fan, Yebin National Key Laboratory of Science and Technology on Multi-spectral Information Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China Department of Computer Science Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781612847740

A fast and efficient algorithm is presented to label the connected components for binary image, especially for very huge images or any image larger than the available memory. The cascading style scheme compresses the algorithm's workspace to only 2 rows of image, which makes it possible to process any scale image with very low memory requirement. Two techniques are also applied for improving the performance further: the search path compression;the image data prefetching. An extensive comparison with the state-of-art algorithms is proposed, both on random and real datasets. Our algorithm shows an impressive speedup as much as 10X, while the total memory cost is significantly reduced. © 2011 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

AN ACTIVE CONTOUR MODEL BASED ON MULTIPLE BOUNDARY MEASURES

AN ACTIVE CONTOUR MODEL BASED ON MULTIPLE BOUNDARY MEASURES

引用

IEEE International Conference on Image processing

作者： Yu Qiao Lei Zhou Jie Yang Yonghui Gao The Key Laboratory of Ministry of Education for System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University

ISBN: (纸本)9781479923427

Weak boundary contrast, inhomogeneous background and overlapped intensity distributions of the object and background are main causes that may lead to failure of boundary detection for many traditional active contour methods. In this paper, we propose a region-based active contour model to address these problems in both local and global ways. A localized active contour framework is developed, in which two local boundary measures are introduced for the evolution of the level set function. These measures are used to select the boundary candidates for boundary preservation such that the evolution of the contour is guided in a reasonable way. The object boundary is determined by a global boundary measure which evaluates the boundary completeness during the entire evolution process. The experiments demonstrate that our method works well against weak boundary contrast, inhomogeneous background and overlapped intensity distributions.

关键词： Region-based active contour model Level set method Local boundary measures Boundary preservation Global boundary measure contour Boundary boundary layer set method boundary contrast Comet Nucleus Tour Edge detection evolution evolution evolution intensity distribution

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78页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：