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

4,557 篇 会议
66 篇 期刊文献
21 册 图书
2 篇 学位论文

馆藏范围

4,646 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,608 篇 工学
- 1,808 篇 计算机科学与技术...
- 1,162 篇 信息与通信工程
- 1,044 篇 软件工程
- 627 篇 电气工程
- 332 篇 光学工程
- 143 篇 控制科学与工程
- 137 篇 电子科学与技术（可...
- 135 篇 生物工程
- 109 篇 生物医学工程（可授...
- 106 篇 仪器科学与技术
- 84 篇 机械工程
- 44 篇 化学工程与技术
- 35 篇 网络空间安全
- 27 篇 动力工程及工程热...
- 27 篇 安全科学与工程
- 22 篇 建筑学
1,141 篇 医学
- 1,123 篇 临床医学
- 42 篇 基础医学(可授医学...
- 37 篇 药学(可授医学、理...
- 29 篇 特种医学
1,138 篇 理学
- 827 篇 物理学
- 391 篇 数学
- 143 篇 生物学
- 96 篇 统计学（可授理学、...
- 46 篇 化学
- 41 篇 系统科学
226 篇 管理学
- 124 篇 管理科学与工程(可...
- 111 篇 图书情报与档案管...
- 27 篇 工商管理
38 篇 法学
- 30 篇 社会学
12 篇 军事学
10 篇 教育学
9 篇 经济学
9 篇 文学
8 篇 农学
2 篇 艺术学

主题

553 篇 image processing
535 篇 image coding
353 篇 visual communica...
315 篇 visualization
263 篇 image segmentati...
263 篇 feature extracti...
173 篇 image reconstruc...
171 篇 image compressio...
158 篇 cameras
158 篇 humans
152 篇 video coding
139 篇 image color anal...
131 篇 training
130 篇 image analysis
128 篇 image quality
127 篇 image edge detec...
123 篇 image enhancemen...
110 篇 image retrieval
104 篇 deep learning
103 篇 motion estimatio...

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
24 篇 school of electr...
20 篇 university of sc...
19 篇 shanghai jiao to...
19 篇 school of electr...
18 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
11 篇 ieee
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
11 篇 institute of ima...
10 篇 univ sci & techn...
10 篇 peking univ inst...
10 篇 xidian univ sch ...
9 篇 institute for in...
9 篇 zhejiang univers...
9 篇 tsinghua univ de...

作者

34 篇 zhai guangtao
26 篇 song li
26 篇 sumei li
22 篇 li sumei
21 篇 guangtao zhai
19 篇 li song
18 篇 li li
18 篇 min xiongkuo
17 篇 andré kaup
17 篇 yang xiaokang
16 篇 dong liu
16 篇 shan liu
14 篇 chen zhibo
14 篇 b. macq
13 篇 xie rong
13 篇 xiongkuo min
12 篇 gao wen
11 篇 m. vetterli
11 篇 heming sun
11 篇 zhibo chen

语言

4,403 篇 英文
148 篇 其他
82 篇 土耳其文
53 篇 中文
1 篇 俄文

检索条件"任意字段=Conference on Visual Communications and Image Processing 2005"

共 4646 条记录，以下是1121-1130 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：

Secure image Restoration and Contrast Enhancement Using Wavelet Transform and Thresholding Technique

Secure Image Restoration and Contrast Enhancement Using Wave...

引用

International conference on VLSI, communications, and Signal processing (VCAS)

作者： Singh, Kumari Suniti Mishra, Yogesh Kumar Singh, Harsh Vikram KNIT Sultanpur Dept Elect Engn Sultanpur India

ISBN: (纸本)9789813297753;9789813297746

The paper represents a methodology which involves the use of Satellite images taken from Satellite Imaging Corporation and Google Earth. This technique proposes a satellite image enhancement system in two steps which consists of restoration and contrast enhancement. The work represents a methodology for enhancement of Satellite images using wavelet transform such as Discrete wavelet transform (DWT) and Stationary wavelet transform (SWT), thresholding and contrast enhancement using equalization based on absolute difference. The result of the evaluation indicates that the technique obtains good PSNR value of satellite images. The results also strengthen that the technique fares well in preserving the information content of the satellite images and also improve the visual quality of images.

关键词： Satellite images DWT SWT DWT with SWT Thresholding and equalization

来源：评论

学校读者我要写书评

暂无评论

Research on transformer condition recognition based on acoustic signal and one-dimensional convolutional neural networks

Research on transformer condition recognition based on acous...

引用

2021 International conference on Information Technology and Intelligent Control, CITIC 2021

作者： Ma, Yuchao Wang, Xin Zhou, Wenjin Li, Xiang Mo, Juan Zheng, Zhongyuan China Electric Power Research Institute Beijing100055 China Research and Development Center of Smart Information and Communications Technologies Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai201210 China State Grid Tianjin Electric Power Research Institute Tianjin300191 China

To solve the problem of transformer condition recognition, this paper propose a transformer condition recognition method based on acoustic signal and One-dimensional Convolutional Neural Networks(1D-CNN). In order to verify the effectiveness of 1D-CNN algorithm in the field of transformer condition recognition, a platform for acquisition of acoustic signals from a 500 kV transformer is built to carry out the acoustic signal acquisition test for four conditions of the transformer. The acoustic signal data sets are also made, and the 1D-CNN algorithm is used to calculate the recognition accuracy of the transformer conditions. According to test results, 1D-CNN algorithm, as a new structure of deep-learning algorithm, can properly classify acoustic signals of the transformer, and its classification accuracy is higher than those of FFT-BP, SVM, FFT-SAE and other algorithms. In order to explore the internal mechanism of 1D-CNN algorithm, in this paper, a t-SNE visual analysis is also conducted to reveal the performance of 1D-CNN algorithm. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Medical image Fusion Based on Weighted Least Square Optimization and Deep Learning Algorithm

Medical Image Fusion Based on Weighted Least Square Optimiza...

引用

Japan-Egypt International conference on Electronics, communications and Computers (JEC-ECC)

作者： C. Ghandour Walid El-Shafai S. El-Rabaie Faculty of Electronic Engineering Menoufia University Menouf Egypt Security Engineering Lab Prince Sultan University Riyadh KSA

ISBN: (纸本)9781665482936

Recently, medical image processing has become a hot area of research, especially with the rapid development in technology and instrumentation, and that’s because of its effective role in the health sector. So that it becomes a very active research tool. This research introduces an image fusion algorithm that utilizes a deep learning model to produce only one medical fused image that includes all the traits from the medical source images. Firstly, the source images are separated into detailed content and base parts using the Gaussian and rolling guidance filters (RGF). Secondly, by the weighted averaging strategy, the base parts are fused. For the detail content, to quote traits of multi-layer which employ weighted average strategy to produce the fused detail content several candidates, the deep learning network is utilized. The max selection technique is employed to gain the last detailed content as soon as these candidates are gotten. Eventually, by uniting the fused detail and base layers, the fused image will be recreated. The experimental outcomes show that this algorithm can accomplish better results by comparing the other fusion methods in both thematic assessment and visual quality.

关键词： Deep learning visualization Instruments Filtering algorithms Information filters Task analysis image fusion

来源：评论

学校读者我要写书评

暂无评论

Use of Depth Completion and SLAM Algorithm to Build Dense Maps of Large Scenes

Use of Depth Completion and SLAM Algorithm to Build Dense Ma...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Yongxing Jia Mingcan Li Fenghui Xu Jing Yu College of Communications Engineering Army Engineering University of PLA Nanjing China

ISBN: (纸本)9781665446006

Limited by the range of sensor, constructing a dense outdoor map of large scene with a depth camera is difficult. Since the state-of-the-art performance on data fusion for pixel-level distance estimation, this paper proposes a mapping system which employs depth image generated by an unsupervised Lidar-Stereo network to achieve accurate reconstruction. Firstly, in the ORBSLAM2 stereo mode, the system estimates the pose information to finish camera localization. And in another thread LidarStereoNet is used to generate a depth image within visual angle to describe the pixel-level distance. Then, for correcting the completed depth image to truth ground, a nonlinear transformation between the generation and the rendering is performed to restore the accurate distance relationship. Finally, the RGB image, pose information and depth rendering image are entered into the dense mapping module to get a large-scale point cloud model. After running on KITTI dataset, the experiment results show that the system can construct a pretty comprehensive scene model after only one trip, and using the numerical truncation and filtering methods to extract usable areas can make the mapping results more accurate.

关键词： Point cloud compression Location awareness visualization Simultaneous localization and mapping Instruction sets Rendering (computer graphics) Cameras

来源：评论

学校读者我要写书评

暂无评论

Deep LSTM Transfer Learning for Personalized ECG Anomaly Detection on Wearable Devices 5th

Deep LSTM Transfer Learning for Personalized ECG Anomaly Det...

引用

5th International conference on Cognitive Systems and Signal processing, ICCSIP 2020

作者： Deng, Xin Zhou, Jianqiao Xiao, Bin Xiang, Xiaohong Yuan, Yi Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and Telecommunication Chongqing400065 China Chongqing Key Laboratory of Image Recognition Chongqing University of Posts and Telecommunication Chongqing400065 China

ISBN: (纸本)9789811623356

Cardiovascular diseases are the main cause of global non-communicable deaths, accounting for about one-third of the total deaths in the world. Wearable devices are used for early monitoring and early prevention of cardiovascular diseases. Aimed at the low configuration, low power consumption and personalized characteristics of the wearable ECG equipment, a transfer learned with deep LSTM model is proposed in this work. The model is computational efficient and serves as the patient-specific ECG anomaly detector that can be used on the wearable devices. Based on the MIT-BIH open dataset, the experiment results show that the transfer learning model produces superior weighted F2 scores compared to the general model and the naive model for detecting ECG anomalies, such as the premature ventricular contractions and atrial premature beats. The transfer learning model proposed here provides a sensitive, personalized ECG anomaly detection mechanism that has the added benefit of light, quick and robust learning process to be used on wearable devices, which can meet the requirement of ECG monitoring for patients by wearable devices. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

In Which images Does This Corner Appears? A Novel Approach for Three-Dimensional Query of Historical Photographs Collections in Urban Heritage Research 2nd

In Which Images Does This Corner Appears? A Novel Approach f...

引用

2nd International conference on Research and Education in Urban History in the Age of Digital Libraries, UHDL 2019

作者： Suazo, Antonio Centro Nacional de Conservación y Restauración 683 Recoleta St Santiago Chile

ISBN: (纸本)9783030931858

In order to improve the cataloging and search of historical photographs available in public online archives, recent advances support for spatially orienting images in a three-dimensional environment to freely explore these collections, thus addressing navigation issues. However, common search tasks still depend on the traditional approach based on text descriptions and keywords. To overcome this, a novel approach is proposed for querying images based on recovered 3d spatial data. By projecting image pixels over the surface of reconstructed geometry from depicted objects, a resulting point cloud is stored and queried by a search volume, retrieving 3d points and so the associated images. The proposal and its potential are validated through a specific case study from the field of urban history, a dilapidated building located in Santiago of Chile, and its associated photographic collections. Finally, the results obtained are discussed, the types of queries that the system allows, and some limitations identified. The conclusion shows that a new set of possibilities emerges, which allows interrogating images with specific tools and functions derived from a 3d spatial database, improving the access and use of collections for historical research with three-dimensional interest. © 2021, Springer Nature Switzerland AG.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Generating Cooking Recipes from Cooking Videos Using Deep Learning Considering Previous Process with Video Encoding 2020

Generating Cooking Recipes from Cooking Videos Using Deep Le...

引用

3rd International conference on Applications of Intelligent Systems, APPIS 2020

作者： Fujii, Tatsuki Orihara, Ryohei Sei, Yuichi Tahara, Yasuyuki Ohsuga, Akihiko University of Electro-Communications Chofu Tokyo Japan

ISBN: (纸本)9781450376303

Research on generating natural language captions to visual data such as images and videos has produced considerable results with deep learning methods and attracted attention in recent years. In this research, we aim to generate recipe sentences from cooking videos acquired from YouTube. We treat the task as image captioning. There are two aspects to be considered in order to do so. We believe that the semantics of each process should be taken into account to improve the captioning ' s accuracy. Furthermore, data processing, that is obtaining images from each process using several visual processing methods such as object detection should be important. We propose a captioning model where a sentence vector is embedded to consider the consistency of the recipe. From differences between generated recipes and the reference recipe, we can calculate recipe scores. We use three metrics that are used in previous studies to evaluate the image captioning model. We compare the scores to with ones from baseline models. © 2020 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Analyzing image Classification via EEG 7th

Analyzing Image Classification via EEG

引用

7th National conference on Computer Vision, Pattern Recognition, image processing, and Graphics, NCVPRIPG 2019

作者： Mishra, Rahul Bhavsar, Arnav Multimedia Analytics Networks and Systems Lab School of Computing and Electrical Engineering IIT Mandi Mandi India

ISBN: (纸本)9789811586965

Electroencephalogram (EEG) has been a popular technique for brain-computer interface (BCI) and brain decoding studies. However, decoding perceptual information (e.g. images and sound) is only recently being considered. In this work, we make an attempt to experimentally analyze and address the task of classification of images that a person sees, based on the captured EEG during the visual task. For this work, we used a publicly available dataset and, as a part of our analysis, find some important concerns associated with that dataset, which also highlights challenges in EEG based image classification. After we process the data to address these concerns, we show that there may still be some discriminative traits in the EEG data for classifying a small number of classes. © 2020, Springer Nature Singapore Pte Ltd.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

A Deep Pyramid Attention Network for Single image Super-resolution

A Deep Pyramid Attention Network for Single Image Super-reso...

引用

Japan-Egypt International conference on Electronics, communications and Computers (JEC-ECC)

作者： Garas Gendy Hazem Mohammed Nabil Sabor Guanghui He Shanghai Jiao Tong University Shanghai China Faculty of Engineering Assiut University Assiut Egypt

ISBN: (纸本)9781665482936

The pyramid attention (PA) network is a new structure developed for digital image processing. This network was designed to extract long-range features at different locations and scales. Recently, PA architecture has been introduced in single image super-Resolution (SISR) to improve the model's ability to benefit from data's self-similarity. However, the effects of location and number of PA on extracting the self-similarity are not explored. In this paper, a Deep Pyramid Attention Network (DPANet) is proposed for SISR based on exploring the PA block. This is performed by studying the effect of varying the number of PA blocks and their locations on the model performance. Moreover, the effect of the residual scale on the PA's performance is studied. Evaluated based on five benchmark datasets, we concluded that using five PA blocks without down-scale residual interchanging with Resblocks in the network achieves significantly better results compared to the state-of-the-art methods. In addition, our model achieves superior visual quality and accuracy.

关键词： visualization Correlation Computational modeling Simulation Digital images Superresolution Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Efficient Binary Multi-view Subspace Learning for Instance-Level image Retrieval 27th

Efficient Binary Multi-view Subspace Learning for Instance-L...

引用

27th International conference on Neural Information processing

作者： Wu, Zhijian Li, Jun Xu, Jianhua Nanjing Normal Univ Sch Comp Sci & Technol Nanjing 210023 Jiangsu Peoples R China

ISBN: (纸本)9783030638191;9783030638207

The existing hashing methods mainly handle either the feature based nearest-neighbour search or the category-level image retrieval, whereas a few efforts are devoted to instance retrieval problem. Besides, although multi-view hashing methods are capable of exploring the complementarity among multiple heterogeneous visual features, they heavily rely on massive labeled training data, and somewhat affects the real-world applications. In this paper, we propose a binary multi-view fusion framework for directly recovering a latent Hamming subspace from the multi-view features. More specifically, the multi-view subspace reconstruction and the binary quantization are integrated in a unified framework so as to minimize the discrepancy between the original multi-view high-dimensional Euclidean space and the resulting compact Hamming subspace. In addition, our method is amenable to efficient iterative optimization for learning a compact similarity-preserving binary code. The resulting binary codes demonstrate significant advantage in retrieval precision and computational efficiency at the cost of limited memory footprint. More importantly, our method is essentially an unsupervised learning scheme without any labeled data involved, and thus can be used in the cases when the supervised information is unavailable or insufficient. Experiments on public benchmark and large-scale datasets reveal that our method achieves competitive retrieval performance comparable to the state-of-the-art and has excellent scalability in large-scale scenario.

关键词： Instance retrieval Multi-view fusion Multi-view subspace reconstruction Binary quantization

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465页 << < 109 110 111 112 113 114 115 116 117 118 > >>

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：