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

581 篇 会议
306 篇 期刊文献
1 册 图书

馆藏范围

888 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

612 篇 工学
- 333 篇 计算机科学与技术...
- 296 篇 软件工程
- 198 篇 信息与通信工程
- 84 篇 生物工程
- 77 篇 电子科学与技术（可...
- 76 篇 光学工程
- 75 篇 电气工程
- 75 篇 控制科学与工程
- 74 篇 机械工程
- 61 篇 生物医学工程（可授...
- 43 篇 仪器科学与技术
- 35 篇 化学工程与技术
- 17 篇 材料科学与工程（可...
- 16 篇 安全科学与工程
- 14 篇 土木工程
- 13 篇 力学（可授工学、理...
- 13 篇 建筑学
- 13 篇 交通运输工程
361 篇 理学
- 188 篇 数学
- 140 篇 物理学
- 88 篇 生物学
- 69 篇 统计学（可授理学、...
- 34 篇 化学
- 33 篇 系统科学
93 篇 管理学
- 59 篇 管理科学与工程(可...
- 35 篇 图书情报与档案管...
56 篇 医学
- 52 篇 临床医学
- 25 篇 基础医学(可授医学...
- 20 篇 药学(可授医学、理...
14 篇 农学
12 篇 法学
- 11 篇 社会学
6 篇 经济学
3 篇 教育学
3 篇 军事学
2 篇 艺术学

主题

43 篇 feature extracti...
27 篇 image segmentati...
22 篇 visualization
22 篇 image reconstruc...
21 篇 image coding
19 篇 convolution
18 篇 training
17 篇 semantics
17 篇 image quality
14 篇 deep learning
14 篇 three-dimensiona...
14 篇 image color anal...
13 篇 image communicat...
13 篇 support vector m...
13 篇 psnr
13 篇 encoding
13 篇 robustness
12 篇 video coding
12 篇 image processing
12 篇 estimation

机构

82 篇 institute of ima...
63 篇 moe key lab of a...
18 篇 institute of ima...
14 篇 university of ch...
13 篇 shenyang institu...
10 篇 school of comput...
10 篇 school of scienc...
10 篇 shanghai key lab...
10 篇 peng cheng labor...
10 篇 institutes for r...
10 篇 shanghai key lab...
9 篇 nanjing general ...
9 篇 key lab of indus...
9 篇 zhejiang lab
8 篇 education minist...
8 篇 key laboratory o...
8 篇 shanghai key lab...
7 篇 key laboratory o...
7 篇 image processing...
7 篇 key laboratory o...

作者

47 篇 zhai guangtao
30 篇 guangtao zhai
30 篇 min xiongkuo
26 篇 xiaokang yang
23 篇 zhu xiuchang
21 篇 jun wang
21 篇 yang xiaokang
20 篇 song li
19 篇 yang hua
19 篇 fan zhun
17 篇 feng liu
17 篇 gan zongliang
16 篇 sun wei
16 篇 xiuchang zhu
15 篇 zhang wenjun
15 篇 xie rong
14 篇 hua yang
13 篇 dong hu
13 篇 hu dong
12 篇 wenjun zhang

语言

853 篇 英文
21 篇 中文
14 篇 其他

检索条件"机构=Key Lab of Image Processing and Image Communication"

共 888 条记录，以下是231-240 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：

Replaying Styles for Continual Semantic Segmentation Across Domains 7th

Replaying Styles for Continual Semantic Segmentation Across...

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Deng, Yao Xiang, Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031476365

In the context of Domain Incremental Learning for Semantic Segmentation, catastrophic forgetting is a significant issue when a model learns new geographical domains. While replay-based approaches have been commonly used to mitigate this problem by allowing the model to review past knowledge, they require additional storage space for old data, which may not be feasible in real-world applications. To address this limitation, we propose a style replay method that leverages the characteristics of low-level representations in CNN to require only one style feature for each domain, leading to a significant reduction in storage overhead. By fusing the style features of past domains with the semantic features of current data, our method enables style transfer for new domain data, thereby improving the model’s generalization ability to the domain. Through extensive experimental evaluations on various autonomous driving datasets, we demonstrate the efficacy of our proposed method in addressing the challenges of continual semantic segmentation under both label and domain shift, outperforming the previous state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Partial differential equation model method based on image feature for denoising

Partial differential equation model method based on image fe...

引用

International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping

作者： Zhang, Xiaohua Wang, Ran Jiao, L.C. Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424494040

For the special different nature images, we could hardly find particularly desirable approach, and there always exist Gibbs-type artifacts in the results of most methods. A novel Partial Differential Equation (PDE) model is proposed based on image feature for images denoising. The PDE model is adaptive within each region according to the details of the image feature to adjust the size of the diffusion coefficient. So it can be disposed the high gradient noise at the same time better to retain the edge information. We also analyze the performance of the PDE model method. Numerical results show that our algorithm competes favorably with state of the-art TV projection methods to eliminate noise and reduce Gibbs-type artifacts. ©2011 IEEE.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Unsupervised image segmentation based on nonsubsampled contourlet hidden markov trees model

Unsupervised image segmentation based on nonsubsampled conto...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Xin, Fangfang Jiao, LiCheng Wan, Honglin Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

Based on the shift invariance and multidirectional expansion properties of Nonsubsampled Contourlet Transform, a new image segmentation combining hidden Markov trees model with Bayesian approaches is proposed here. The training blocks can be got in pre-segmentation by using histogram approximation. To integrated use the information of different scales, we use the contextual model to segment raw segmentations and fuse them to get the final image. We compared our result with Wavelet domain HMTseg method and Contourlet domain HMTseg method, the result shows that our method has better performance in edges but lower missed classed probability. The simulation results of synthetic mosaic image, aerial image and SAR image are showed to prove the generalization of this method. ©2009 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Content-Adaptive Interpolation for Spatial Error Concealment

Content-Adaptive Interpolation for Spatial Error Concealment

引用

International Conference on Information and Computing Science, ICIC

作者： Hua-yan Luo Zong-liang Gan Xiu-chang Zhu Jiangsu Province Key Laboratory on Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing China

When transmitting encoded images over a communication channel, the reconstructed image quality can be substantially degraded by channel errors. This paper presents a spatial error concealment algorithm that utilizes variance of surrounding pixels, and then classifies each error block (EB) into two categories: uniform block and edge block. For uniform block, nearest border prior spatial interpolation is adopted to restore missing pixels. We use the Wiener interpolation algorithm and special interpolation sequence for edge block. Experimental results indicate the proposed algorithm can attain well restored quality of intra-frames both subjectively and objectively. Meanwhile, the computational cost of the proposed algorithm can be significantly reduced, compared to Lipsilas method. And the restored quality is almost the same, sometimes even much better.

关键词： Interpolation image reconstruction image quality image restoration Video compression Telecommunication computing Gallium nitride image processing image communication Electronic mail

来源：评论

学校读者我要写书评

暂无评论

A comparative study of radial basis function neural networks in dynamic clustering algorithm

A comparative study of radial basis function neural networks...

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhou, Peng Li, Dehua Wu, Hong Zeng, Jun Chen, Feng State Key Lab. for Image Processing and Intelligent Control Institute for Pattern Recognition and Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478078

This paper developed two learning procedure, respectively, based on the orthogonal least squares (OLS) method and the "Innovation- Contribution" criterion (ICc) proposed newly. The orthogonal use of the stepwise-regression algorithm of the ICc mages the model structure independent of the selected term sequence and reduces the cluster region further as compared with orthogonal least squares (OLS). as the Bayesian information criteria (BIC) method is incorporate into the clustering process of the ICc, except for the widths of Gaussian functions, it has no other parameter that need tuning ,but the user is required to specify the tolerance ρ, which is relevant to noises and will be difficult to implement in the real system, for the OLS algorithm. The two algorithms are employed to the Radial Basis Function Neural Networks (RBFNN) to compare its performance for different noise nonlinear dynamic systems. Experimental results show that they provide an efficient approximation to the required results for fitting models, but the clustering procedures of the ICc is substantially better solutions than does the OLS. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Change detection in SAR image based on multisacle product and PCA

Change detection in SAR image based on multisacle product an...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Wang, Guiting Zhang, Fengyu Jiao, Licheng Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

In this paper, we present a new method of change detection in SAR images based on multiscale product of wavelet transform and PCA algorithm. This method applied multiscale product of wavelet transform, in order to avoid the affect of speckle noise in SAR, enhance the changed information and weaken the effect of noise. The algorithm of PCA is used to merge every scale after the process of multiscale product. To show the effectiveness of the proposed technique, experiments are conducted on two SAR datasets. Results are compared with two methods which based on wavelet transform and PCA, and it is proved to be superior. ©2009 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Research on auto focusing algorithm of microscopic imaging system

Research on auto focusing algorithm of microscopic imaging s...

引用

2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications, AEECA 2022

作者： Lv, Meini Yang, Qiuhui Ma, Wenjing Huang, Zeqiong College of Wuzhou Wuzhou China Wuzhou University Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Wuzhou China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

In the intelligent microscopic imaging system, the focusing evaluation function is one of the important core links in the automatic focusing system. In order to solve the problem that the focusing curve loses the characteristics of the ideal curve caused by illumination change, an automatic focusing algorithm based on Robert and wavelet transform is proposed in this paper. The algorithm extracts the maximum value of the high-frequency component wavelet coefficients decomposed by the wavelet transform, and uses the extracted wavelet coefficients to weight the Robert evaluation value coefficients, increases the sensitivity factor of the algorithm, and makes an experimental analysis with five traditional focusing functions under the condition of different illumination intensity to verify the feasibility of the algorithm. The experimental results show that the algorithm can overcome the change of illumination, has strong anti noise, sensitivity and stability, and is suitable for the fine focusing process in the microscopic imaging system. © 2022 IEEE.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Road extraction in remote sensing images based on nonsubsampled contourlet transform

Road extraction in remote sensing images based on nonsubsamp...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Zhong, Hua Feng, Yingtao Jiao, Licheng Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

A new method for automated road extraction in remote sensing images is proposed based on Nonsubsampled Contourlet Transform (NSCT). Due to the advantages of multi-scale, multi-direction and translation invariance, NSCT is much efficient for the capture of linear singularity of road target. A pixel-wised feature extraction algorithm is given first based on the analysis of the NSCT coefficient responses for the road target. Final results can be achieved by the simple fuzzy C-means clustering and the postprocessing steps. Experimental results demonstrate that our method outperforms other methods such as Gabor wavelet in accuracy, localization and false detection. ©2009 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Video-Based Person Re-identification via Non-local Attention and Feature Erasing 16th

Large-Scale Video-Based Person Re-identification via Non-loc...

引用

16th International Forum on Digital TV and Wireless Multimedia communication, IFTC 2019

作者： Yang, Zhao Chang, Zhigang Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Key Labs of Digital Media Processing and Transmission Shanghai Jiao Tong University SEIEE Buildings 5-421 Shanghai200240 China

ISBN: (纸本)9789811533402

Encoding the video tracks of person to an aggregative representation is the key for video-based person re-identification (re-ID), where average pooling or RNN methods are typically used to aggregating frame-level features. However, It is still difficult to deal with the spatial misalignment caused by occlusion, posture changes and camera views. Inspired by the success of non-local block in video analysis, we use a non-local attention block as a spatial-temporal attention mechanism to handle the spatial-temporal misalignment problem. Moreover, partial occlusion is widely occurred in video sequences. We propose a local feature branch to tackle the partial occlusion problem by using feature erasing in the frame-level feature map. Therefore, our network is composed by two-branch, the global branch via non-local attention encoding the global feature and the local feature branch grasping the local feature. In evaluation, the global feature and local feature are concatenated to obtain a more discriminative feature. We conduct extensive experiments on two challenging datasets (MARS and iLIDS-VID). The experimental results demonstrate that our method is comparable with the state-of-the-art methods in these datasets. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

An unsupervised change detection based on clustering combined with multiscale and region growing

An unsupervised change detection based on clustering combine...

引用

International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping

作者： Zhang, Xiaohua Wang, Le Jiao, L.C. Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424494040

In this paper, a novel approach is proposed for unsupervised change detection of multitemporal remote sensing images. The proposed method is able to produce the change detection result on the difference image without a priori assumptions .Firstly, the difference image which is acquired from multitemporal images. Mean shift algorithm is used to reduce noise of difference image and fake change. Then stationary wavelet transform (SWT) is used to extract feature vector of each pixel .The final change detection map is achieved by k-means clustering combined with region growing. The comparisons with the state-of-the-art change detection methods are provided. ©2011 IEEE.

关键词： Change detection

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89页 << < 20 21 22 23 24 25 26 27 28 29 > >>

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：