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

1,851 篇 会议
124 册 图书
40 篇 期刊文献

馆藏范围

2,015 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,517 篇 工学
- 1,317 篇 计算机科学与技术...
- 750 篇 软件工程
- 430 篇 电气工程
- 252 篇 信息与通信工程
- 251 篇 光学工程
- 195 篇 生物工程
- 118 篇 生物医学工程（可授...
- 117 篇 控制科学与工程
- 95 篇 电子科学与技术（可...
- 87 篇 机械工程
- 68 篇 化学工程与技术
- 59 篇 安全科学与工程
- 37 篇 仪器科学与技术
- 37 篇 交通运输工程
- 34 篇 材料科学与工程（可...
- 22 篇 建筑学
- 18 篇 农业工程
620 篇 理学
- 324 篇 物理学
- 232 篇 数学
- 209 篇 生物学
- 71 篇 化学
- 62 篇 统计学（可授理学、...
- 28 篇 系统科学
345 篇 医学
- 333 篇 临床医学
- 61 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
174 篇 管理学
- 121 篇 图书情报与档案管...
- 66 篇 管理科学与工程(可...
24 篇 农学
- 22 篇 作物学
23 篇 法学
- 21 篇 社会学
12 篇 教育学
8 篇 经济学
5 篇 军事学
2 篇 文学

主题

232 篇 computer vision
101 篇 image processing
92 篇 deep learning
89 篇 artificial intel...
84 篇 image processing...
73 篇 image segmentati...
72 篇 computer graphic...
68 篇 feature extracti...
63 篇 pattern recognit...
43 篇 machine learning
41 篇 object detection
41 篇 convolutional ne...
37 篇 computational mo...
37 篇 computer imaging...
36 篇 image enhancemen...
34 篇 image reconstruc...
32 篇 graphics process...
32 篇 image classifica...
31 篇 face recognition
31 篇 visualization

机构

19 篇 indian statistic...
15 篇 indian institute...
12 篇 indian inst tech...
9 篇 indian institute...
9 篇 indian institute...
9 篇 indian inst tech...
8 篇 indian institute...
8 篇 indian institute...
8 篇 indian inst tech...
8 篇 indian institute...
7 篇 indian stat inst...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian inst sci ...
6 篇 iit kharagpur kh...
6 篇 indian inst tech...
6 篇 faculty of elect...
6 篇 department of co...

作者

31 篇 chaudhury santan...
25 篇 mukherjee jayant...
25 篇 chaudhuri subhas...
21 篇 das sukhendu
16 篇 lall brejesh
15 篇 babu r. venkates...
15 篇 raman shanmugana...
13 篇 das partha prati...
13 篇 mukherjee dipti ...
13 篇 harit gaurav
13 篇 mishra deepak
11 篇 chanda bhabatosh
11 篇 mukherjee snehas...
10 篇 biswas soma
10 篇 raman balasubram...
10 篇 jawahar c.v.
10 篇 biswas prabir ku...
10 篇 sur arijit
9 篇 banerjee biplab
9 篇 balasubramanian ...

语言

1,974 篇 英文
37 篇 其他
6 篇 中文
2 篇 俄文

检索条件"任意字段=6th Indian Conference on Computer Vision, Graphics and Image Processing"

共 2015 条记录，以下是901-910 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：

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

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

Semantic multinomial representation for scene images using CNN-based pseudo-concepts and concept neural network 6th

Semantic multinomial representation for scene images using C...

引用

6th National conference on computer vision, Pattern Recognition, image processing and graphics, NCVPRIPG 2017

作者： Pradhan, Deepak Kumar Gupta, Shikha thenkanidiyoor, Veena Aroor Dinesh, Dileep Department of Computer Science and Engineering National Institute of Technology Goa PondaGoa401403 India School of Computing and Electrical Engineering Indian Institute of Technology Mandi MandiH.P.175001 India

ISBN: (纸本)9789811300196

For challenging visual recognition tasks such as scene classification and object detection there is a need to bridge the semantic gap between low-level features and the semantic concept descriptors. this requires mapping a scene image onto a semantic representation. Semantic multinomial (SMN) representation is a semantic representation of an image that corresponds to a vector of posterior probabilities of concepts. In this work we propose to build a concept neural network (CoNN) to obtain the SMN representation for a scene image. An important issue in building a CoNN is that it requires the availability of ground truth concept labels. In this work we propose to use pseudo-concepts obtained from feature maps of higher level layers of convolutional neural network. the effectiveness of the proposed approaches are studied using standard datasets. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning to Prevent Monocular SLAM Failure using Reinforcement Learning 11

Learning to Prevent Monocular SLAM Failure using Reinforceme...

引用

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

作者： Prasad, Vignesh Yadav, Karmesh Saurabh, Rohitashva Singh Daga, Swapnil Pareekutty, Nahas Krishna, K. Madhava Ravindran, Balaraman Bhowmick, Brojeshwar TCS Res & Innovat Embedded Syst & Robot Kolkata India Carnegie Mellon Univ Inst Robot Pittsburgh PA 15213 USA Johns Hopkins Univ Dept Robot Engn Baltimore MD USA IIIT Hyderabad Robot Res Ctr KCIS Hyderabad Telangana India Indian Inst Technol Dept Comp Sci Madras Tamil Nadu India

ISBN: (纸本)9781450366151

Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment. While Monocular SLAM is a well studied problem, automating Monocular SLAM by integrating it with trajectory planning frameworks is particularly challenging. this paper presents a novel formulation based on Reinforcement Learning (RL) that generates fail safe trajectories wherein the SLAM generated outputs do not deviate largely from their true values. Quintessentially, the RL framework successfully learns the otherwise complex relation between perceptual inputs and motor actions and uses this knowledge to generate trajectories that do not cause failure of SLAM. We show systematically in simulations how the quality of the SLAM dramatically improves when trajectories are computed using RL. Our method scales effectively across Monocular SLAM frameworks in both simulation and in real world experiments with a mobile robot.

关键词： Reinforcement Learning Robot Navigation Monocular SLAM

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

Activity Recognition in Egocentric Videos Using Bag of Key Action Units 11

Activity Recognition in Egocentric Videos Using Bag of Key A...

引用

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

作者： Suma, K. Sai Aditya, G. Mukherjee, Snehasis Indian Inst Informat Technol Sricity Chittoor Andhra Pradesh India

ISBN: (纸本)9781450366151

In this paper we present a novel methodology for recognizing human activity in Egocentric video based on the Bag of Visual Features. the proposed technique is based on the assumption that, only a portion of the whole video can be sufficient to identify an activity. Rather, we argue that, for activity recognition in egocentric videos, the proposed approach performs better than any deep learning based method. Because, in egocentric videos, often the person wiring the sensor, becomes static for long time, or moves his head frequently. In both the cases, it becomes difficult to learn the spatio-temporal pattern of the video during action. the proposed approach divides the video into smaller video segments called Video Units. Spatio-temporal features extracted from the units, are clustered to construct the dictionary of Action Units (AU). the AUs are ranked based upon their score of likeliness. the scores are obtained by constructing a weighted graph with the AUs as vertices and edge weights calculated based on the frequencies of occurrences of the AUs during the activity. the less significant AUs are pruned out from the dictionary, and the revised dictionary of key AUs are used for activity *** test our approach on benchmark egocentric dataset and achieve a good accuracy.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Moving Average Recurrent Neural Network Model for Video-based Person Re-Identification 11

Moving Average Recurrent Neural Network Model for Video-base...

引用

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

作者： Fasil, Muhammed C. Chaudhuri, Subhasis Indian Inst Technol Dept Elect Engn Mumbai Maharashtra India

ISBN: (纸本)9781450366151

Person re-identification has great applications in video surveillance. It can be viewed as recognizing the same person across non-overlapping cameras. Video-based person re-identification methods are gaining increased attention due to the better discriminative nature of spatio-temporal feature representations. Current video-based methods make use of RNN to extract temporal information. In this paper, we propose a novel Moving Average Recurrent Neural Network (MA-RNN) model that can build a strong feature representation by taking both previous and present inputs at each time stamp. Specifically, here the recurrent layer produces a better sequential information by looking back directly in to the past values where as general RNNs has only an indirect dependence on the previous values in the form of hidden-state information. the proposed model is tested on two publicly available datasets: iLIDS-VID and PRID-2011 and it performed better in comparison with the state-of-the-art methods with a significant margin. We also analyze the effect of the depth of previous input dependence of the MA-RNN model on the matching accuracy.

关键词： RNN MA-RNN person re-identification

来源：评论

学校读者我要写书评

暂无评论

GMM based single depth image super-resolution 6th

GMM based single depth image super-resolution

引用

6th National conference on computer vision, Pattern Recognition, image processing and graphics, NCVPRIPG 2017

作者： Balure, Chandra Shaker Kini, M. Ramesh Bhavsar, Arnav National Institute of Technology Karnataka Surathkal Mangalore India Indian Institute of Technology Mandi MandiH.P. India

ISBN: (纸本)9789811300196

Super-resolution (SR) is a technique to improve the resolution of an image from a sequence of input images or from a single image. As SR is an ill-posed inverse problem, it leads to many suboptimal solutions. Since modern depth cameras suffer from low-spatial resolution and are noisy, we present a Gaussian mixture model (GMM) based method for depth image super-resolution (SR). We train GMM from a set of high-resolution and low-resolution (HR-LR) synthetic training depth images to learn the relation between the HR and the LR patches in the form of covariance matrices. We use expectation-maximization (EM) algorithm to converge to an optimal solution. We show the promising results qualitatively and quantitatively in comparison to other depth image SR methods. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

DP-GAN: Dual Pathway Generative Adversarial Network for Face Recognition in Degraded Scenarios 11

DP-GAN: Dual Pathway Generative Adversarial Network for Face...

引用

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

作者： Bhattacharjee, Avishek Banerjee, Samik Das, Sukhendu Indian Inst Technol Madras Chennai 600036 Tamil Nadu India

ISBN: (纸本)9781450366151

Face Recognition (FR) using Convolutional Neural Network (CNN) based models have achieved considerable success in constrained environments. they however fail to perform well in unconstrained scenarios, especially when the images are captured using surveillance cameras. these probe samples suffer from degradations such as noise, poor illumination, low resolution, blur as well as aliasing, when compared to the rich training (gallery) set, comprising mostly of mugshot images captured in laboratory settings. these images in the training (gallery) set are crisp and have high contrast, compared to the probe samples. To cope with this scenario, we propose a novel dual-pathway generative adversarial network (DP-GAN) which maps low resolution images captured using surveillance camera into their corresponding high resolution images, which are gallery-like, using a novel combination of multi-scale reconstruction and Jensen-Shannon divergence based loss. these images thus obtained are then used to train a deep domain adaptation (deep-DA) network to perform the task of FR. the proposed network achieves superior results (>90%) on four benchmark surveillance face datasets, evident from the rank-1 recognition rates when compared with recent state-of-the-art CNN-based techniques.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Single noisy image super resolution by minimizing nuclear norm in virtual sparse domain 6th

Single noisy image super resolution by minimizing nuclear no...

引用

6th National conference on computer vision, Pattern Recognition, image processing and graphics, NCVPRIPG 2017

作者： Mandal, Srimanta Rajagopalan, A.N. Image Processing and Computer Vision Lab Department of Electrical Engineering IIT Madras Chennai600036 India

ISBN: (纸本)9789811300196

Super-resolving a noisy image is a challenging problem, and needs special care as compared to the conventional super resolution approaches, when the power of noise is unknown. In this scenario, we propose an approach to super-resolve single noisy image by minimizing nuclear norm in a virtual sparse domain that tunes with the power of noise via parameter learning. the approach minimizes nuclear norm to explore the inherent low-rank structure of visual data, and is further augmented with coarse-to-fine information by adaptively re-aligning the data along the principal components of a dictionary in virtual sparse domain. the experimental results demonstrate the robustness of our approach across different powers of noise. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Optical resolving power

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202页 << < 87 88 89 90 91 92 93 94 95 96 > >>

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：