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

1,343 篇 会议
46 册 图书
18 篇 期刊文献

馆藏范围

1,407 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,046 篇 工学
- 738 篇 计算机科学与技术...
- 388 篇 软件工程
- 236 篇 电气工程
- 209 篇 信息与通信工程
- 191 篇 光学工程
- 127 篇 机械工程
- 109 篇 生物工程
- 96 篇 生物医学工程（可授...
- 89 篇 控制科学与工程
- 58 篇 电子科学与技术（可...
- 40 篇 化学工程与技术
- 28 篇 仪器科学与技术
- 23 篇 安全科学与工程
- 21 篇 交通运输工程
- 16 篇 材料科学与工程（可...
- 16 篇 土木工程
- 14 篇 建筑学
399 篇 理学
- 218 篇 物理学
- 155 篇 数学
- 119 篇 生物学
- 46 篇 统计学（可授理学、...
- 37 篇 化学
- 27 篇 系统科学
135 篇 医学
- 131 篇 临床医学
- 47 篇 基础医学(可授医学...
- 41 篇 药学(可授医学、理...
101 篇 管理学
- 56 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 19 篇 工商管理
17 篇 农学
- 16 篇 作物学
11 篇 法学
6 篇 教育学
5 篇 经济学
4 篇 文学
1 篇 艺术学

主题

257 篇 computer vision
125 篇 image processing
122 篇 image segmentati...
93 篇 feature extracti...
83 篇 cameras
61 篇 image color anal...
41 篇 image edge detec...
41 篇 training
39 篇 deep learning
35 篇 three-dimensiona...
33 篇 image enhancemen...
32 篇 image reconstruc...
31 篇 images
29 篇 artificial intel...
28 篇 robustness
27 篇 object detection
27 篇 machine learning
25 篇 neural networks
24 篇 computational mo...
24 篇 pattern recognit...

机构

20 篇 computer vision ...
5 篇 indian statistic...
5 篇 indian institute...
5 篇 indian institute...
5 篇 department of co...
5 篇 computer vision ...
4 篇 techno india uni...
4 篇 department of co...
4 篇 jadavpur univers...
4 篇 department of ma...
4 篇 department of co...
4 篇 department of co...
4 篇 department of co...
3 篇 kentucky imaging...
3 篇 icteam universit...
3 篇 hong kong polyte...
3 篇 department of el...
3 篇 department of ma...
3 篇 indian institute...
3 篇 department of el...

作者

17 篇 raman balasubram...
11 篇 aly a. farag
9 篇 roy partha prati...
8 篇 balasubramanian ...
8 篇 a.a. farag
7 篇 dubey shiv ram
6 篇 arivazhagan s.
6 篇 shekar b.h.
6 篇 mishra deepak
5 篇 bhuyan m.k.
5 篇 lee hyo jong
5 篇 murala subrahman...
5 篇 chaudhuri bidyut...
5 篇 dorit merhof
5 篇 kumar sanjeev
5 篇 nain neeta
5 篇 jawahar c.v.
4 篇 asem ali
4 篇 nagabhushan p.
4 篇 ojha aparajita

语言

1,393 篇 英文
9 篇 中文
3 篇 俄文
2 篇 其他

检索条件"任意字段=International Conference on Computer Vision and Image Processing, CVIP 2016"

共 1407 条记录，以下是331-340 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：

image compression for constrained aerial platforms: A unified framework of laplacian and cGAN 4th

Image compression for constrained aerial platforms: A unifie...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Faheema, A.G.J. Lakshmi, A. Priyanka, Sreedevi Centre for AI and Robotics DRDO Complex Bangalore560093 India

ISBN: (纸本)9789811540172

In this paper, we propose a new lossy image compression technique suitable for computationally challenged platforms. Extensive development in moving platforms create need for encoding images in real time with less computational resources. Conventional compression algorithms have potential to address this problem. However, the reconstruction accuracy of conventional encoders does not match that of deep learning based compression algorithms. In this paper, we have utilized best of both worlds by proposing a new compression method which combines conventional and deep learning based methods to sustain real time transmission and as well good reconstruction quality. We have validated our algorithm across a varied set of test images from EPFL mini drone dataset and Stanford drone dataset. The proposed algorithm exhibits better rate-distortion performance than conventional method. More importantly, our algorithm gives real time performance which has been substantiated by displaying a dramatic improvement in speed as against state-of-the-art deep learning compression method. © Springer Nature Singapore Pte Ltd 2020.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Transformed directional tri concomitant triplet patterns for image retrieval 4th

Transformed directional tri concomitant triplet patterns for...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Hussain, Chesti Altaff Rao, D. Venkata Mastani, S. Aruna Department of ECE JNTU College of Engineering Anatapuramu India QIS Institute of Engineering and Technology Ongole India

ISBN: (纸本)9789811540141

Content-based image retrieval (CBIR) is an accurate characterization of visual information. In this paper, we have proposed a new technique entitled as Transformed Directional Tri Concomitant Triplet Patterns (TdtCTp) for CBIR. TdtCTp consist of three stages to obtain detail directional information about pixel progression. In first stage, structural rule based approach is proposed to extract directional information in various direction. Further, in second stage, microscopic information and correlation between each sub-structural elements are extracted by using concomitant conditions. Finally, minute directional intensity variation information and correlation between the sub-structural elements are extracted by integrating first two stages. Retrieval accuracy is estimated using traditional distance measure technique in terms of average retrieval precision and average retrieval rate on publicly available natural and medical image databases. Performance analysis shows that TdtCTp descriptor outperforms the existing methods in terms of retrieval accuracy. © Springer Nature Singapore Pte Ltd 2020.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Towards ocular recognition through local image descriptors 4th

Towards ocular recognition through local image descriptors

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Vyas, Ritesh Kanumuri, Tirupathiraju Sheoran, Gyanendra Dubey, Pawan Bennett University Greater NoidaUP India National Institute of Technology Delhi Delhi India Accendere Knowledge Management Services SurampalemAP India

ISBN: (纸本)9789811540141

Iris and periocular (collectively termed as ocular) biometric modalities have been the most sought for modalities, due to their increased discrimination ability. Moreover, both these modalities can be captured through a single acquisition setup, leading to ease in user interaction. Owing to these advantages, this paper presents two local descriptors, namely statistical and transform-based descriptors, to investigate the worthiness of ocular recognition. The first descriptor uses mean and variance formulae after two levels of partitioning to extract the distinctive features. Whereas, second descriptor comprises of implementation of curvelet transform, followed by polynomial fitting, to extract the features. Individual iris and periocular features are combined through simple concatenation operation. The experiments performed on the challenging Cross-Eyed database, vindicate the efficacy of both the employed descriptors in same-spectral as well as cross-spectral matching scenarios. © Springer Nature Singapore Pte Ltd 2020.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

3D CNN with localized residual connections for hyperspectral image classification 4th

3D CNN with localized residual connections for hyperspectral...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Dwivedi, Shivangi Mandal, Murari Yadav, Shekhar Vipparthi, Santosh Kumar Madan Mohan Malaviya University of Technology Gorakhpur India Vision Intelligence Lab Malaviya National Institute of Technology Jaipur India

ISBN: (纸本)9789811540172

In this paper we propose a novel 3D CNN network with localized residual connections for hyperspectral image classification. Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a model which incorporates residual features from multiple stages in the network. The proposed architecture processes individual spatio-spectral feature rich cubes from hyperspectral images through 3D convolutional layers. The residual connections result in improved performance due to assimilation of both low-level and high-level features. We conduct experiments over Pavia University and Pavia Center dataset for performance analysis. We compare our method with two recent state-of-the-art methods for hyperspectral image classification method. The proposed network outperforms the existing approaches by a good margin. © Springer Nature Singapore Pte Ltd 2020.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis for various stroke prediction techniques 4th

A comparative analysis for various stroke prediction techniq...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Singh, M. Sheetal Choudhary, Prakash Thongam, Khelchandra Department of Computer Science and Engineering National Institute of Technology Manipur Imphal India Department of Computer Science and Engineering National Institute of Technology Hamirpur HamirpurHP India

ISBN: (纸本)9789811540172

Stroke is a major life-threatening disease mostly occurs to a person of age 65 years and above but nowadays also happen in younger age due to unhealthy diet. If we can predict a stroke in its early stage, then it can be prevented. In this paper, we evaluate five different machine learning techniques to predict stroke on Cardiovascular Health Study (CHS) dataset. We use Decision Tree (DT) with the C4.5 algorithm for feature selection, Principal Component Analysis (PCA) is used for dimension reduction and, Artificial Neural Network (ANN) and Support Vector Machine (SVM) are used for classification. The predictive methods discussed in this paper are tested on different data samples based on different machine learning techniques. From the different methods applied, the composite method of DT, PCA and ANN gives the optimal result. © Springer Nature Singapore Pte Ltd 2020.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Encoder decoder based image semantic space creation for clothing items retrieval 4th

Encoder decoder based image semantic space creation for clot...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Kedia, Keshav Kumar Jain, Gaurav Kumar Grover, Vipul Samsung R&D Institute India Bangalore BangaloreKarnataka560037 India

ISBN: (纸本)9789811540141

Suggesting clothing items using query images is very convenient in online shopping, however feature extraction is not very easy for the intended query due to other objects and background variations present in these images. We need better feature extractor which extracts features only from intended clothing item in query image and rejects strong features from remaining part. To accomplish this we propose single step encoder-decoder based image translation and feature extraction approach with reverse weight transfer method for creating a common space between catalog of shopping images and query images. We present generated images and retrieved images from test set and compute the exact image retrieval accuracy. We achieved 30.6%, 46.8% and 56.3% exact image retrieval accuracy for top 1, top 3 and top 5 suggestions respectively. We also conducted a subjective survey on similar items retrieval and on an average 3.33 clothing items are relevant out of 5 items retrieved for ~500 responses which shows the effectiveness of this method. © Springer Nature Singapore Pte Ltd 2020.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

vision-Based malware detection and classification using lightweight deep learning paradigm 4th

Vision-Based malware detection and classification using ligh...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Abijah Roseline, S. Hari, G. Geetha, S. Krishnamurthy, R. Vellore Institute of Technology - Chennai Campus ChennaiTamilnadu600127 India Sri Vasavi Engineering College TadepalligudemAndhra Pradesh534101 India

ISBN: (纸本)9789811540172

Cyber attackers develop new malicious software to attack their targets every year. Recent sophisticated malware targets financial data and steals the credentials of users. Security analysts design novel methods to defend against malware attacks, but, unfortunately, with the proliferation of newly discovered malware, the methods are inefficient. The need for automated detection of unknown and new malware is still challenging in cybersecurity research. Machine learning approaches are applied for malware detection, however, they require larger feature extraction and feature engineering. The proposed work analyzes and classifies malware based on visualization technique and employs Lightweight Convolutional Neural Networks deep learning model. The model performed better achieving an accuracy of 97% and 95% for the two malware datasets including benign samples. They did not require more hardware resources and model is trained with a low computational cost. The model was evaluated on Malimg dataset and Kaggle’s Microsoft Malware Classification Challenge (BIG 2015) dataset. © Springer Nature Singapore Pte Ltd 2020.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

VISUAL RELATIONSHIP CLASSIFICATION WITH NEGATIVE-SAMPLE MINING

VISUAL RELATIONSHIP CLASSIFICATION WITH NEGATIVE-SAMPLE MINI...

引用

IEEE international conference on image processing (ICIP)

作者： Estevao Filho, Roberto de M. Gomes, Jose Gabriel R. C. Nunes, Leonardo de O. Univ Fed Rio de Janeiro COPPE Elect Engn Program Rio De Janeiro Brazil Microsoft Adv Technol Labs Sao Paulo Brazil

ISBN: (纸本)9781728163956

This paper introduces the application of a visual relationship classifier as a standalone system that is meant to be used with external detectors. Through these lens, we propose a training scheme that uses unannotated pairs of objects as negative samples in order to improve precision. The proposed network architecture incorporates common techniques presented in related state-of-the-art solutions with a novel positional encoding scheme. We evaluate the proposed training method and architecture on the Open images dataset and improve mAP from 34.6% to 78.2% when considering all possible object pairings in each image. For a case where only ground-truth pairs are considered, our method presents a small decrease, from 91.0% to 88.8% mAP.

关键词： deep convolutional neural networks visual relationships computer vision machine learning

来源：评论

学校读者我要写书评

暂无评论

An edge-based image steganography method using modulus-3 strategy and comparative analysis 4th

An edge-based image steganography method using modulus-3 str...

引用

4th international conference on computer vision and image processing, cvip 2019

作者： Tripathy, Santosh Kumar Srivastava, Rajeev VaranasiUP221005 India

ISBN: (纸本)9789811540172

Steganography or "Covered Writing" is a security tool for hiding secret information inside any media or object of interest. It provides secure communication between the sender and the receiver. The spatial domain image steganography techniques such as the Least Significant Bit (LSB) substitution and edge-based hiding schemes have been vastly exploited in the literature. An improved LSB method using modulus-3 strategy can be found in the literature, which has the advantages of high embedding capacity and resistance against Subtractive Pixel Adjacency Matrix (SPAM) steganalysis. However, one drawback is that it hides data sequentially. The edge-based hiding techniques have the advantage that it can tolerate significant variations in edge pixels and fulfill all the requirements of the Human vision System (HVS), but it has limited in embedding capacity. The proposed work is a reversible data hiding scheme that takes the advantages of both the edge-based algorithm and the novel modulus-3 hiding scheme. At first, we converted the message into ternary data, and then we applied the novel modulus-3 strategy to hide two ternary bits in the edge pixel of the image thereby taking the advantages of both modulus-3 strategy and edge-based hiding approach. We have implemented four edge detection algorithms like Laplacian, Canny, Sobel, and Prewitt to find four different edge areas from the cover image. For each edge area, we applied the modulus-3 strategy to hide the entire ternary message, and then, we made a comparative analysis based on the performance of four edge detectors, and finally, we concluded. © Springer Nature Singapore Pte Ltd 2020.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

BOOSTING image-BASED LOCALIZATION VIA RANDOMLY GEOMETRIC DATA AUGMENTATION

BOOSTING IMAGE-BASED LOCALIZATION VIA RANDOMLY GEOMETRIC DAT...

引用

IEEE international conference on image processing (ICIP)

作者： Wan, Yiming Gao, Wei Han, Sheng Wu, Yihong Chinese Acad Sci Inst Automat NLPR Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

ISBN: (纸本)9781728163956

Visual localization is a fundamental problem in computer vision and robotics. Recently, deep learning has shown to be effective for robust monocular localization. Most deep learning-based methods utilize convolution neural network (CNN) to regress global 6 degree-of-freedom (Dof) pose. However, these methods suffer from pose sparsity, leading to over-fitting during training and poor localization performance on unseen data. In this paper, we try to alleviate this issue by implementing randomly geometric augmentation (RGA) during training. Specifically, we firstly estimate the depth map using a depth estimation network for the initial training image. Combing the estimated depth, RGB image and its corresponding pose, we can randomly synthesize new images of different views. The synthesized and initial images are used to train the pose regression network. Experiment results show our geometric augmentation strategy can significantly improve the localization accuracy.

关键词： Visual localization deep learning

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141页 << < 30 31 32 33 34 35 36 37 38 39 > >>

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：