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

1,413 篇 会议
56 册 图书
27 篇 期刊文献

馆藏范围

1,496 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,010 篇 工学
- 901 篇 计算机科学与技术...
- 410 篇 软件工程
- 389 篇 电气工程
- 131 篇 信息与通信工程
- 122 篇 光学工程
- 90 篇 生物工程
- 65 篇 生物医学工程（可授...
- 58 篇 电子科学与技术（可...
- 38 篇 控制科学与工程
- 34 篇 化学工程与技术
- 29 篇 机械工程
- 21 篇 仪器科学与技术
- 17 篇 安全科学与工程
- 10 篇 材料科学与工程（可...
- 9 篇 建筑学
- 8 篇 土木工程
347 篇 医学
- 344 篇 临床医学
- 27 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
333 篇 理学
- 158 篇 物理学
- 147 篇 数学
- 93 篇 生物学
- 47 篇 统计学（可授理学、...
- 32 篇 化学
- 16 篇 系统科学
92 篇 管理学
- 69 篇 图书情报与档案管...
- 23 篇 管理科学与工程(可...
- 13 篇 工商管理
12 篇 农学
- 12 篇 作物学
10 篇 法学
- 9 篇 社会学
6 篇 经济学
3 篇 教育学
2 篇 文学
1 篇 艺术学

主题

142 篇 computer vision
80 篇 image processing
77 篇 image segmentati...
54 篇 computer graphic...
54 篇 feature extracti...
52 篇 cameras
46 篇 deep learning
38 篇 shape
35 篇 face recognition
34 篇 artificial intel...
34 篇 image reconstruc...
30 篇 robustness
28 篇 object detection
28 篇 image color anal...
25 篇 image enhancemen...
25 篇 image edge detec...
25 篇 pattern recognit...
25 篇 layout
24 篇 biometrics
23 篇 image processing...

机构

20 篇 indian statistic...
19 篇 indian institute...
17 篇 department of co...
14 篇 computer vision ...
12 篇 indian institute...
11 篇 department of el...
10 篇 indian inst tech...
9 篇 indian stat inst...
9 篇 indian institute...
9 篇 indian inst tech...
9 篇 indian institute...
8 篇 indian institute...
8 篇 department of el...
8 篇 indian institute...
8 篇 indian inst sci ...
8 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian institute...
7 篇 indian inst tech...
7 篇 indian inst tech...

作者

40 篇 chaudhury santan...
29 篇 chaudhuri subhas...
26 篇 mukherjee jayant...
20 篇 das sukhendu
19 篇 raman shanmugana...
18 篇 santanu chaudhur...
17 篇 balasubramanian ...
16 篇 harit gaurav
16 篇 lall brejesh
15 篇 babu r. venkates...
15 篇 chanda bhabatosh
14 篇 mukherjee dipti ...
13 篇 das partha prati...
12 篇 biswas prabir ku...
12 篇 mishra deepak
11 篇 raman balasubram...
11 篇 sukhendu das
10 篇 biswas soma
10 篇 bhowmick partha
10 篇 bhavsar arnav

语言

1,484 篇 英文
9 篇 中文
4 篇 其他

检索条件"任意字段=Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing"

共 1496 条记录，以下是451-460 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 Co-segmentation using Graph Convolution Neural Network 11

Image Co-segmentation using Graph Convolution Neural Network

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Banerjee, Sayan Hati, Avik Chaudhuri, Subhasis Velmurugan, Rajbabu Indian Inst Technol Mumbai Maharashtra India

ISBN: (纸本)9781450366151

image co-segmentation is jointly segmenting two or more images sharing common foreground objects. In this paper, we propose a novel graph convolution neural network (graph CNN) based end-to-end model for performing co-segmentation. At the beginning, each input image is over-segmented into a set of superpixels. Next, a weighted graph is formed using the over-segmented images exploiting spatial adjacency and both intra-image and inter-image feature similarities among the image superpixels (nodes). Subsequently, the proposed network, consisting of graph convolution layers followed by node classification layers, classifies each superpixel either into the common foreground or its complement. During training, along with the co-segmentation network, an additional network is introduced to exploit the corresponding semantic labels, and the two networks share the same weights in graph convolution layers. The whole model is learned in an end-to-end fashion using a novel cost function comprised of a superpixel wise binary cross entropy and a multi-label cross entropy. We also use empirical class probabilities in the loss function to deal with class imbalance. Experimental results reflect that the proposed technique is very competitive with the state-of-the-art methods on two challenging datasets, Internet and Pascal-VOC.

关键词： Co-segmentation graph superpixel graph CNN convolution filter

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-based Model for Phase Unwrapping 11

A Deep Learning-based Model for Phase Unwrapping

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Spoorthi, G. E. Gorthi, Subrahmanyam Gorthi, Rama Krishna Sai Indian Inst Technol Tirupati Andhra Pradesh India

ISBN: (纸本)9781450366151

Phase unwrapping is an important problem in several applications that attempts to restore original phase from wrapped phase. In this paper, we propose a novel phase unwrapping model based on the deep convolutional neural network by formulating the phase unwrapping as a semantic segmentation problem. The proposed architecture consists of a convolutional encoder network and corresponding decoder network followed by a pixel-wise classification layer. One of the critical challenges in DCNN is availability of large set of labeled training data. This issue is effectively circumvented for the proposed framework through a generic simulation procedure that automatically generates large labeled data. Results from the proposed method are compared with widely used quality-guided phase unwrapping algorithm for various SNR values. It is found that the proposed method is performing well both in terms of accuracy and computational time, even in the presence strong noise. To the best of our knowledge, this is the first work that uses convolutional neural network for phase unwrapping, and this will hopefully pave the way to a new class of techniques for unwrapping the phase.

关键词： Phase Unwrapping Deep Convolutional Neural Network (DCNN) Encoder Decoder Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Neural Network Based Approach for Geo-Localizing Events in Crowd Sourced Videos 11

A Neural Network Based Approach for Geo-Localizing Events in...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： More, Amit Chaudhuri, Subhasis Indian Inst Technol Mumbai Maharashtra India

ISBN: (纸本)9781450366151

Popular events are often video recorded simultaneously by a general crowd using smartphones. In the present work, we propose a robust recurrent neural network (RNN) based approach for geo-localizing these events using sensor data collected by user smartphones while recording such events. For this task we use GPS and compass sensors, which are commonly available on the smartphones. The circular nature (modulo 2p) of the orientation data from compass limits the ability of the classical neural networks (NN) to geo-localize these events. We mitigate this issue by incorporating circular nodes in our network and show the performance improvements. We train the proposed NN model using simulated data and apply it directly on real data. We train several RNN models using this strategy and show our analyses. The proposed work outperforms all previous approaches in terms of event geo-localization accuracy.

关键词： Event Geo-localization Neural Network Circular Nodes GPS data Compass Data Smartphone

来源：评论

学校读者我要写书评

暂无评论

SegFast : A Faster SqueezeNet based Semantic image Segmentation Technique using Depth-wise Separable Convolutions 11

SegFast : A Faster SqueezeNet based Semantic Image Segmentat...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Pal, Anisha Jaiswal, Shourya Ghosh, Swarnendu Das, Nibaran Nasipuri, Mita Manipal Inst Technol Dept Informat & Commun Technol Manipal Karnataka India Manipal Inst Technol Dept Elect & Commun Engn Manipal Karnataka India Jadavpur Univ Dept Comp Sci & Engn Kolkata W Bengal India

ISBN: (纸本)9781450366151

Recent trends in image segmentation algorithms have shown various large scale networks with impressive performance for natural scene images. However most of the networks come with costly overheads such has large memory requirements or dependence on huge number of parallel processing units. In most cases costly graphics processing units or GPUs are used to boost computational capability. However for creating products in the real world we need to consider speed, performance as well as cost of deployment. We propose a novel "spark" module which is a combination of the "fire" module of SqueezeNet and depth-wise separable convolutions. Along with this modified SqueezeNet as an encoder we also propose the use of depth-wise separable transposed convolution for a decoder. The resultant encoder-decoder network has approximately 49 times lesser number of parameters than SegNet and almost 223 times lesser number of parameters than fully convolutional networks(FCN). Even in a CPU the network completes a forward pass for a single sample in approximately 0.39 seconds which is almost 5.1 times faster as compared to SegNet and almost 8.7 times faster compared to FCN.

关键词： Deep Learning image Segmentation Squeeze Net Depthwise separable convolution

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Floorplan Generation 11

Towards Automated Floorplan Generation

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Chelani, Kunal Sidhartha, Chitturi Govindu, Venu Madhav Indian Inst Sci Bengaluru India

ISBN: (纸本)9781450366151

In this paper, we propose a pipeline for generating a 2D floorplan using depth cameras. In our pipeline we use an existing approach to recovering the camera motion trajectories from the depth and RGB sequences. Given these motion estimates we construct a full 3D representation of the scanned indoor spaces. For generating a floorplan we need to abstract the large volumes of registered 3D data into a simplified rectilinear representation. We evaluate two approaches to solve this problem, viz slicing the reconstructed volume at a given height and direct segmentation of the 3D point cloud representation into individual planar segments. We also note that the fidelity of our estimated floorplan crucially depends on the accuracy of the estimation of the ground plane orientation. We examine the comparative accuracies of two ground plane estimation methods for each of the above mentioned approaches to rectilinear abstraction. Given the line drawing abstractions of the individual rooms, we merge them into a consistent floorplan. We present results on a real-world floorplan estimation problem and demonstrate its accuracy. Additionally, the implications of errors in the individual components of our pipeline are also studied.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

LEDNet: Deep Network for Single image Haze Removal 11

LEDNet: Deep Network for Single Image Haze Removal

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Dudhane, Akshay Murala, Subrahmanyam Dhall, Abhinav Indian Inst Technol Ropar Comp Vis & Pattern Recognit Lab Rupnagar India Indian Inst Technol Ropar Learning Affect & Semant Image Anal Grp Rupnagar India

ISBN: (纸本)9781450366151

Haze during the bad weather, degrades the visibility of the scene drastically. Degradation of scene visibility varies with respect to the transmission coefficient/map (T-c) of the scene. Estimation of accurate T-c is key step to reconstruct the haze free scene. Previously, local as well as global priors were proposed to estimate the T-c. We, on the other hand, propose integration of local and global approaches to learn both point level and object level T-c. The proposed local encoder decoder network (LEDNet) estimates the scene transmission map in two stages. During first stage, network estimates the point level T-c using parallel convolutional filters and spatial invariance filtering. The second stage comprises of a two level encoder-decoder architecture which anticipates the object level T-c. We also propose, local air-light estimation (LAE) algorithm, which is able to obtain the air-light component of the outdoor scene. Combination of LEDNet and LAE improves the accuracy of haze model to recover the scene radiance. Structural similarity index, mean square error and peak signal to noise ratio are used to evaluate the performance of the proposed approach for single image haze removal. Experiments on benchmark datasets show that LEDNet outperforms the existing state-of-the-art methods for single image haze removal.

关键词： Haze removal CNN transmission map

来源：评论

学校读者我要写书评

暂无评论

Sparse Signal Recovery for Multiple Measurement Vectors with Temporally Correlated Entries: A Bayesian Perspective 11

Sparse Signal Recovery for Multiple Measurement Vectors with...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sharma, Shruti Chaudhury, Santanu Jayadeva, Jayadeva Bhagat, Snigdha Indian Inst Technol Delhi New Delhi India

ISBN: (纸本)9781450366151

Bayesian Sparse Signal Recovery (SSR) for Multiple Measurement Vectors, when elements of each row of solution matrix are correlated, is addressed in the paper. We propose a standard linear Gaussian observation model and a three-level hierarchical estimation framework, based on Gaussian Scale Mixture (GSM) model with some random and deterministic parameters, to model each row of the unknown solution matrix. This hierarchical model induces heavy-tailed marginal distribution over each row which encompasses several choices of distributions viz. Laplace distribution, Student's t distribution and Jeffery prior. Automatic Relevance Determination (ARD) phenomenon introduces sparsity in the model. It is interesting to see that Block Sparse Bayesian Learning framework is a special case of the proposed framework when induced marginal is Jeffrey prior. Experimental results for synthetic signals are provided to demonstrate its effectiveness. We also explore the possibility of using Multiple Measurement Vectors to model Dynamic Hand Posture Database which consists of sequence of temporally correlated hand posture sequence. It can be seen that by exploiting temporal correlation information present in the successive image samples, the proposed framework can reconstruct the data with less linear random measurements with high fidelity.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

On-Demand Augmentation of Contour Trees 11

On-Demand Augmentation of Contour Trees

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sharma, Mohit Natarajan, Vijay Indian Inst Sci Bangalore Karnataka India

ISBN: (纸本)9781450366151

The contour tree represents the topology of level sets of a scalar function. Nodes of the tree correspond to critical level sets and arcs of the tree represent a collection of topologically equivalent level sets connecting two critical level sets. The augmented contour tree contains degree-2 nodes on the arcs that represent regular level sets. The degree-2 nodes correspond to regular points of the scalar function and other critical points that do not affect the number of level set components. The augmented contour tree is significantly larger in size and requires more effort to compute when compared to the contour tree. Applications of the contour tree to data exploration and visualization require the augmented contour tree. Current approaches propose algorithms to compute the contour tree and the augmented contour tree from scratch. Precomputing and storing the large augmented contour tree will not be necessary if the contour tree can be augmented on-demand. This paper poses the problem of computing the augmented contour tree given a contour tree as input. Computational experiments demonstrate that the on-demand augmentation can be computed fast while resulting in good memory savings.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

A Rapid Non-Linear Diffusion Compressed Sensing parallel MR image Reconstruction 11

A Rapid Non-Linear Diffusion Compressed Sensing parallel MR ...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Joy, Ajin Paul, Joseph Suresh Indian Inst Informat Technol & Management Kerala Trivandrum Kerala India

ISBN: (纸本)9781450366151

Optimization of the tradeoff between computation time and image quality is essential for reconstructing high-quality magnetic resonance image (MRI) from a limited number of acquired samples in a short time using compressed sensing (CS) algorithms. In this paper, we achieve this for the edge preserving non-linear diffusion reconstruction (NLDR) which eliminates the critical step-size tuning of the total variation (TV) based CS-MRI. Based on optimization of contrast parameter that controls noise and signal in sensitivity modulated channel images, we propose an a-switching NLDR technique for a faster approximation of reconstruction image without affecting the image quality. Proposed algorithm exploits the difference in the extent of undersampling artifacts in signal-background regions of the channel images to arrive at different estimates of contrast parameter, leading to an effective optimization of speed and quality. While maintaining better image quality as compared to conventional TV reconstruction, the switched NLDR also achieves 25-35% gain in convergence time over NLDR without switching. This makes the switched NLDR a better candidate for fast reconstruction over traditional TV and NLDR approaches. In the detailed numerical experiments, we have compared and optimized the tradeoff for various state-of-the-art choices of contrast parameter.

关键词： parallel MRI nonlinear diffusion contrast parameter

来源：评论

学校读者我要写书评

暂无评论

An incremental topological map building using monocular vision 11

An incremental topological map building using monocular visi...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Bhowmick, Soumabha Mukherjee, Jayanta Deb, Alok Kanti Indian Inst Technol Kharagpur W Bengal India Inst Clar Documentat Kharagpur W Bengal India

ISBN: (纸本)9781450366151

In this work a memory efficient topological map generation algorithm has been proposed using local descriptors. A topological map is a graphical data structure where each node signifies an area within an environment. These nodes are connected by links which ensure the presence of a physical path between the pair. Experiments have been conducted with feature descriptors using a vocabulary based approach. These approaches take huge memory and time. To deal with these a KD-tree based map generation algorithm has been proposed where each node in the tree stores a descriptor and a table of occurrence. This table stores node ids of the locations, where the corresponding descriptor is present. The map generation algorithm is a two-stage algorithm. In the first stage, the visual similarity based position identification is conducted in order to check for loop-closures. It is followed by a corrective step on validating the decision of loop closure, if any. The table of occurrence keeps track of presence of each descriptor. The least occurring descriptors are pruned at regular intervals, making the algorithm memory-efficient. The approach has been experimented with several benchmark datasets.

关键词： KD-tree Topological Map Loop Closure Local descriptor

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150页 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：