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

151 篇 会议
51 篇 期刊文献
1 册 图书

馆藏范围

203 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

142 篇 工学
- 85 篇 计算机科学与技术...
- 82 篇 软件工程
- 53 篇 信息与通信工程
- 22 篇 电子科学与技术（可...
- 19 篇 机械工程
- 18 篇 光学工程
- 16 篇 控制科学与工程
- 14 篇 电气工程
- 13 篇 仪器科学与技术
- 9 篇 生物工程
- 5 篇 土木工程
- 5 篇 化学工程与技术
- 5 篇 安全科学与工程
- 4 篇 生物医学工程（可授...
- 3 篇 动力工程及工程热...
- 3 篇 建筑学
- 2 篇 力学（可授工学、理...
- 2 篇 轻工技术与工程
- 2 篇 航空宇航科学与技...
87 篇 理学
- 50 篇 数学
- 42 篇 物理学
- 21 篇 统计学（可授理学、...
- 10 篇 生物学
- 9 篇 系统科学
- 6 篇 化学
- 1 篇 地球物理学
24 篇 管理学
- 17 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
2 篇 法学
- 1 篇 法学
- 1 篇 社会学
2 篇 农学
1 篇 医学
1 篇 军事学

主题

9 篇 feature extracti...
6 篇 computational mo...
6 篇 image coding
6 篇 visualization
6 篇 signal processin...
5 篇 semantics
5 篇 accuracy
5 篇 image reconstruc...
5 篇 training
4 篇 deep learning
4 篇 image segmentati...
4 篇 signal processin...
4 篇 speech
4 篇 neural networks
4 篇 compressed video
4 篇 predictive model...
4 篇 quality assessme...
4 篇 interpolation
3 篇 image fusion
3 篇 signal detection

机构

14 篇 institute of ima...
10 篇 shanghai key lab...
7 篇 image processing...
7 篇 department of el...
7 篇 moe key lab of a...
7 篇 school of inform...
6 篇 jiangsu province...
5 篇 jiangsu provinci...
4 篇 image processing...
4 篇 school of comput...
4 篇 jiangsu province...
4 篇 institute of ima...
3 篇 key lab of broad...
3 篇 image processing...
3 篇 college of compu...
3 篇 shanghai key lab...
3 篇 indian institute...
3 篇 image and inform...
3 篇 jiangsu province...
3 篇 department of co...

作者

19 篇 zhu xiuchang
12 篇 yang hua
12 篇 gan zongliang
12 篇 xiuchang zhu
9 篇 hua yang
9 篇 zongliang gan
9 篇 priyanka kokil
8 篇 feng liu
8 篇 yang xiaokang
7 篇 xu yi
7 篇 ziguan cui
6 篇 cui ziguan
6 篇 xuelong hu
5 篇 li xin
5 篇 zhu xiu-chang
5 篇 ajay kumar reddy...
5 篇 liu feng
5 篇 zhou jun
4 篇 khare ashish
4 篇 zhang wenjun

语言

197 篇 英文
4 篇 中文
2 篇 其他

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

共 203 条记录，以下是71-80 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：

Network flow based collective behavior analysis

Network flow based collective behavior analysis

引用

2013 International Workshop on Behavior and Social Informatics and Computing, BSIC 2013

作者： Hu, Yuting Xie, Rong Zhang, Wenjun Institute of Image Communication and Network Engineering Shanghai Key Lab. of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783319040479

With the large-scale activities increasing gradually, the intelligent video surveillance system becomes more and more popular and important. The trajectory identification and behavior analysis are very important techniques for the intelligent video surveillance system. This paper focuses on the trajectory identification and behavior analysis framework for video surveillance system. The framework is implemented on footbridge video and queuing video of Shanghai World Expo 2010 video surveillance system. The experimental results show the efficiency of our proposed framework. © Springer International Publishing Switzerland 2013.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Interest point based tracking

Interest point based tracking

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Kloihofer, Werner Kampel, Martin Research and Development Image Processing Center Communication Systems GmbH Vienna Austria Computer Vision Lab. Vienna University of Technology Vienna Austria

ISBN: (纸本)9780769541099

This paper deals with a novel method for object tracking. In the first step interest points are detected and feature descriptors around them are calculated. Sets of known points are created, allowing tracking based on point matching. The set representation is updated online at every tracking step. Our method uses one-shot learning with the first frame, so no offline and no supervised learning is required. Following an object recognition based approach there is no need for a background model or motion model, allowing tracking of abrupt motion and with non-stationary cameras. We compare our method to MeanShift and Tracking via Online Boosting, showing the benefits of our approach. © 2010 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Biorthogonal wavelet transform based image fusion using absolute maximum fusion rule

Biorthogonal wavelet transform based image fusion using abso...

引用

2013 IEEE Conference on Information and communication Technologies, ICT 2013

作者： Prakash, Om Srivastava, Richa Khare, Ashish Image Processing and Computer Vision Lab Department of Electronics and Communication University of Allahabad Allahabad India Centre of Computer Education University of Allahabad Allahabad India

ISBN: (纸本)9781467357586

The objective of image fusion is to combine relevant information from two or more images of the same scene into a single composite image which is more informative and is more suitable for human and machine perception. In recent past, different methods of image fusion have been proposed in literature both in spatial domain and wavelet domain. Spatial domain based methods produce spatial distortions in the fused image. Spatial domain distortion can be well handled by the use of wavelet transform based image fusion methods. In this paper, we propose a pixel-level image fusion scheme using multiresolution Biorthogonal wavelet transform (BWT). Wavelet coefficients at different decomposion levels are fused using absolute maximum fusion rule. Two important properties wavelet symmetry and linear phase of BWT have been exploited for image fusion because they are capable to preserve edge information and hence reducing the distortions in the fused image. The performance of the proposed method have been extensively tested on several pairs of multifocus and multimodal images both free from any noise and in presence of additive white Gaussian noise and compared visually and quantitatively against existing spatial domain methods. Experimental results show that the proposed method improves fusion quality by reducing loss of significant information available in individual images. Fusion factor, entropy and standard deviation are used as quantitative quality measures of the fused image. © 2013 IEEE.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Yang, Jinhai Yang, Hua Shanghai Jiao Tong University Institution of Image Communication and Network Engineering China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

ISBN: (纸本)9781728163277

Few-shot learning aims for rapid adaptation with few samples. Recently, cross-granularity few-shot learning has emerged as a promising research area, where models observe coarse labels but target fine-grained recognition among novel classes. As coarse supervision tends to eliminate feature discrimination among underlying sub-classes, existing methods commonly utilize self-supervision as a complement to explore intra-class variation. However, current methods suffer from an intrinsic conflict between contrastive learning and coarse supervision. In this paper, we locate the root cause of the intrinsic conflict. Then, we resolve it by exploiting the similarity among augmented views while ignoring the unreasonable constraint between negative pairs. Besides, we decouple contrastive learning and coarse supervision into parallel branches to better regularize the latent space. Albeit simple, our approach consistently outperforms state-of-the-art methods across different benchmarks. © 2023 IEEE.

关键词： cross-granularity transfer Few-shot learning generalization image classification

来源：评论

学校读者我要写书评

暂无评论

Adaptive Mutation particle filter based on diversity guidance

Adaptive Mutation particle filter based on diversity guidanc...

引用

International Conference on Machine Learning and Cybernetics

作者： Yu, Jin-Xia Tang, Yong-Li Liu, Wen-Jing College of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9781424465262

Aimed at the deficiency of the resampling algorithm in PF, diversity measures ESS (effective sample size) and PDF (population diversity factor) are evaluated respectively. Combined with the estimation result, diversity measures PDF is used for adaptively tuning the resampling threshold. By integrating the operation of particle mutation after resampling into PF and using the above mechanism of diversity guidance, the AMPF algorithm (Adaptive Mutation PF) is presented so as to assure the diversity of particle sets. With the simulation program using matlab 7.0 to track a single target motion from a fixed visual observation points, the performance of diversity measures and AMPF are evaluated and the validity of the proposed method is verified. © 2010 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Simple and effective image quality assessment based on edge enhanced mean square error

Simple and effective image quality assessment based on edge ...

引用

International Conference on Wireless communications and Signal processing (WCSP)

作者： Ziguan Cui Zongliang Gan Guijin Tang Feng Liu Xiuchang Zhu Image Processing & Image Communication Lab Nanjing University of Posts & Telecommunications Nanjing China

ISBN: (纸本)9781479973408

Simple and effective image quality assessment (IQA) method is very desirable in many image and video processing applications, such as coding, transmission, restoration and enhancement. Classic pixel absolute error based objective IQA metrics such as mean square error (MSE) and corresponding peak signal to noise ratio (PSNR) are widely used for various applications due to low computation and clear physical meanings, but have also been criticized for poorly correlated with subjective evaluation. Inspired by that human visual system (HVS) is more sensitive to image local edge distortion than flat or texture areas, in this paper, we propose a novel edge enhanced MSE (EE-MSE) to emphasize edge distortion effects on IQA. Experimental results on LIVE database release 2 show that the proposed EE-MSE IQA metric is competitive with state-of-the-art HVS-based IQA metrics, while has lower computational complexity and is more suitable for optimization task.

关键词： Measurement image quality image edge detection PSNR Visualization Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A low complexity MB layer rate control algorithm based on motion similarity for H.264

A low complexity MB layer rate control algorithm based on mo...

引用

International Conference on Wireless communications and Signal processing (WCSP)

作者： Ziguan Cui Xiuchang Zhu Image Processing and Image Communication Lab Nanjing University of Posts and Telecommunications Nanjing China

This paper presents a simple but effective macroblock (MB) layer rate control (RC) scheme for H.264/AVC with low complexity. First, to reduce computation cost and inaccuracy of linear mean absolute difference (MAD) prediction at MB layer adopted in JVT-G012, MAD is computed directly according to the difference between current original MB and the reference blocks pointed by estimated MV using intensive motion similarity. Then, MB header bits are predicted based on spatial-temporal correlation because it is not constant due to complicated coding modes and high compression efficiency of H.264. Finally, MB target bit rate is allocated according to its complexity and the parameters of quadratic R-D model are updated using coded MBs with high spatial-temporal correlation and motion similarity not the last coded data points. Simulation results show that the proposed scheme achieves an average PSNR gain of 0.37 dB, meets better with target bit rate, produces more consistent quality for the MBs in a frame and thus improves visual quality compared to classic JVT-H017 RC algorithm, simultaneously has lower computation complexity and suits for real-time application.

关键词： Complexity theory Correlation Predictive models Bit rate Computational modeling Data models Accuracy

来源：评论

学校读者我要写书评

暂无评论

Improving HEVC Coding Perceptual Quality Using Saliency Guided CTU Layer QP Adjustment

Improving HEVC Coding Perceptual Quality Using Saliency Guid...

引用

Chinese Automation Congress (CAC)

作者： Ziguan Cui Mengnan Zhang Xiaopeng Jiang Zongliang Gan Guijin Tang Feng Liu Image Processing and Image Communication Lab Nanjing University of Posts and Telecommunications Nanjing China

Recently, improving the perceptual quality of video coding under bit rate constraint has attracted researchers' attention in video coding field. In this paper, we propose to improve the coding perceptual quality for the latest High Efficiency Video Coding (HEVC) standard using saliency guided coding tree unit (CTU) level quantization parameter (QP) adjustment scheme. Our work mainly includes two steps: first, a CTU layer saliency detection scheme with low complexity is proposed to measure the visual significance for each CTU in a frame. Then, a CTU layer QP adjustment scheme based on relative saliency is proposed to increase the bit rate resource for more salient regions and decrease the bit rate cost for less salient regions. Therefore, the proposed QP adjustment scheme obtains better bit rate allocation among CTUs and generates better coding perceptual quality. Experimental results show that the proposed method achieves better perceptual quality and rate distortion performance for HEVC video coding.

关键词： Saliency detection Encoding Visualization image coding Bit rate High efficiency video coding

来源：评论

学校读者我要写书评

暂无评论

Research on diversity measure in particle filter

Research on diversity measure in particle filter

引用

2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010

作者： Yu, Jinxia Tang, Yongli Liu, Wenjing College of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9780769540771

It is very important to find diversity measure when to perform a resampling step in particle filter. By analyzing the inherent deficiency in resampling algorithm of particle filter, some diversity measures including effective sample size, population diversity factor and particle swarm diversity measure are introduced. Then combined with the simulation program using matlab 7.0 to track a single target motion from a fixed visual observation points, the performance of diversity measures in resampling algorithm of PF are evaluated. © 2010 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Improved SAI Method using Non-local Spatial Constraint for image Interpolation

Improved SAI Method using Non-local Spatial Constraint for I...

引用

2011年无线通信与信号处理国际会议(WCSP 2011)

作者： Jueping Bian Zongliang Gan Mengcheng Zhang Xiuchang Zhu Jiangsu province key lab on image processing & image communication NUPT Nanjing China

This paper proposes an improved image interpolation method based on the soft-decision adaptive interpolation (SAI) algorithm. Natural images often contain repeatable patterns and structures throughout the image, which is called non-local property. We can use this non-local strategy to improve the interpolation quality by better estimating the model parameters and Lagrangian multiplier. There are two steps in our method. In the first step, similar patches of the given block are found in the initialized high resolution image, and the model parameters can be determined properly using the expanded piecewise auto regression (PAR) model and non-local spatial constraint. In the second step, the self-similarity of patches across the high and low resolution images is exploited to solve the Lagrangian multiplier λ, thus to make the data estimation robust. Experiments indicate that the improved method can achieve good results both subjectively and objectively.

关键词： image interpolation the SAI algorithm non-local self-similarity

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21页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：