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

920 篇 会议
61 册 图书
23 篇 期刊文献

馆藏范围

1,004 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

821 篇 工学
- 719 篇 计算机科学与技术...
- 375 篇 软件工程
- 336 篇 电气工程
- 108 篇 信息与通信工程
- 105 篇 光学工程
- 91 篇 生物工程
- 54 篇 生物医学工程（可授...
- 41 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 28 篇 控制科学与工程
- 21 篇 机械工程
- 15 篇 安全科学与工程
- 12 篇 仪器科学与技术
- 10 篇 土木工程
- 8 篇 建筑学
- 8 篇 航空宇航科学与技...
- 7 篇 交通运输工程
280 篇 理学
- 126 篇 物理学
- 118 篇 数学
- 94 篇 生物学
- 39 篇 统计学（可授理学、...
- 33 篇 化学
- 11 篇 系统科学
269 篇 医学
- 269 篇 临床医学
- 25 篇 基础医学(可授医学...
- 22 篇 药学(可授医学、理...
75 篇 管理学
- 63 篇 图书情报与档案管...
- 13 篇 管理科学与工程(可...
- 8 篇 工商管理
10 篇 法学
- 9 篇 社会学
4 篇 农学
3 篇 经济学
1 篇 教育学

主题

46 篇 computer graphic...
44 篇 artificial intel...
42 篇 image processing...
33 篇 computer vision
29 篇 deep learning
27 篇 pattern recognit...
25 篇 image segmentati...
22 篇 computer imaging...
20 篇 image enhancemen...
19 篇 graphics process...
17 篇 face recognition
17 篇 image reconstruc...
15 篇 cameras
13 篇 image processing
11 篇 generative adver...
10 篇 object detection
10 篇 computer communi...
10 篇 pixels
10 篇 feature extracti...
10 篇 machine learning

机构

15 篇 indian institute...
11 篇 indian statistic...
11 篇 carnegie mellon ...
11 篇 hebrew universit...
11 篇 google research
10 篇 indian inst tech...
8 篇 indian stat inst...
8 篇 indian inst tech...
7 篇 indian institute...
7 篇 indian institute...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 technische unive...
7 篇 indian inst sci ...
6 篇 indian institute...
6 篇 indian institute...
6 篇 indian inst tech...
6 篇 technical univer...
6 篇 indian inst tech...
6 篇 department of co...

作者

31 篇 chaudhury santan...
26 篇 mukherjee jayant...
25 篇 chaudhuri subhas...
19 篇 das sukhendu
15 篇 babu r. venkates...
14 篇 das partha prati...
14 篇 lall brejesh
14 篇 raman shanmugana...
13 篇 harit gaurav
12 篇 mukherjee dipti ...
12 篇 chanda bhabatosh
12 篇 mishra deepak
11 篇 martial hebert
11 篇 yair weiss
11 篇 vittorio ferrari
11 篇 cristian sminchi...
11 篇 biswas prabir ku...
10 篇 banerjee biplab
10 篇 biswas soma
10 篇 sur arijit

语言

997 篇 英文
3 篇 俄文
3 篇 中文
2 篇 其他

检索条件"任意字段=15th Indian Conference on Computer Vision Graphics and Image Processing"

共 1004 条记录，以下是971-980 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：

Salient Object Detection based on Bayesian Surprise of Restricted Boltzmann Machine 18

Salient Object Detection based on Bayesian Surprise of Restr...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Rahul Roy Susmita Ghosh Ashish Ghosh Machine Intelligence Unit Indian Statistical Institute Kolkata West Bengal Department of Computer Science and Technology Jadavpur University Kolkata West Bengal

ISBN: (纸本)9781450366151

this article presents an algorithm for salient object detection by leveraging the Bayesian surprise of the Restricted Boltzmann Machine (RBM). Here an RBM is trained on patches sampled randomly from the input image. Due to this random sampling, the RBM is likely to get more exposed to background patches than that of the object. thus, the trained RBM will minimize the free energy of its hidden states with respect to the background patches as opposed to the object. this, according to the free energy principle, implies minimizing Bayesian surprise which is a measure for saliency based on Kullback Leibler divergence between the input and reconstructed patch distribution. Hence, when the trained RBM is exposed to patches from the object region, it would have high divergence and in turn a high Bayesian surprise. thus such pixels with high Bayesian surprise could be considered as salient pixels. For each pixel, a neighborhood (with the same size of training patch) is considered and is fed to the trained RBM to obtain the reconstructed patch. thereafter, the Kullback Leibler divergence between the input and reconstructed neighborhood of each pixel is computed to measure the Bayesian surprise and is stored in the corresponding position in a matrix to form the saliency map. Experiments are carried out on three datasets namely MSRA-10K, ECSSD and DUTS. the results obtained depict promising performance by the proposed approach.

关键词： Bayesian Surprise

来源：评论

学校读者我要写书评

暂无评论

Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences 18

Epipolar Geometry based Learning of Multi-view Depth and Ego...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Vignesh Prasad Dipanjan Das Brojeshwar Bhowmick Embedded Systems & Robotics TCS Research & Innovation Kolkata

ISBN: (纸本)9781450366151

Deep approaches to predict monocular depth and ego-motion have grown in recent years due to their ability to produce dense depth from monocular images. the main idea behind them is to optimize the photometric consistency over image sequences by warping one view into another, similar to direct visual odometry methods. One major drawback is that these methods infer depth from a single view, which might not effectively capture the relation between pixels. Moreover, simply minimizing the photometric loss does not ensure proper pixel correspondences, which is a key factor for accurate depth and pose *** contrast, we propose a 2-view depth network to infer the scene depth from consecutive frames, thereby learning inter-pixel relationships. To ensure better correspondences, thereby better geometric understanding, we propose incorporating epipolar constraints to make the learning more geometrically sound. We use the Essential matrix obtained using Nistér's Five Point Algorithm, to enforce meaningful geometric constraints, rather than using it as training labels. this allows us to use lesser no. of trainable parameters compared to state-of-the-art methods. the proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way. Such a geometrically constrained learning performs successfully even in cases where simply minimizing the photometric error would fail.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Regularized Random Walk Ranking for Co-Saliency Detection in images 2018

Regularized Random Walk Ranking for Co-Saliency Detection in...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Sayanti Bardhan Shibu Jacob Indian Institute of Technology Madras Madras India National Institute of Ocean Technology Madras India

ISBN: (纸本)9781450366151

Co-saliency detection refers to the computational process for identification of common but prominent and salient foreground regions in an image. However most of the co-saliency detection methods suffer from the following two limitations. First, co-saliency detection models largely generate superpixel level co-saliency maps that leads to sacrifice of significant information from the pixel level input images. Second, co-saliency detection frameworks mostly involve redesigned models for detection of co-salient objects in an image group, instead of utilization of the existing single image saliency detection models. To address these problems, we propose a novel framework, Co-saliency via Regularized Random Walk Ranking (CR2WR), which provides highly efficient pixel level co-saliency maps and utilizes existing saliency models on a single image to detect co-salient objects in an image sequence. this is achieved by: (1) Introducing Regularized random walk as the ranking function for a two-stage co-saliency detection framework. (2) Novel weighting function to incorporate more image information in graph construction and utilization of normalized Laplacian matrix for efficient cosaliency maps. (3) Generated saliency maps are fused further with high level priors namely, Location and Objectness priors, that enhances detection of co-salient regions. Suitably designed novel objective functions provide an enriched solution. the proposed model is evaluated on challenging benchmark co-saliency datasets. It is demonstrated that the proposed method outperforms prominent state-of-the-art methods in terms of efficiency and computational time.

关键词：

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 18

Sparse Signal Recovery for Multiple Measurement Vectors with...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Shruti Sharma Santanu Chaudhury Jayadeva Jayadeva Snigdha Bhagat Indian Institute of Technology Delhi

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：

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 18

Learning to Prevent Monocular SLAM Failure using Reinforceme...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Vignesh Prasad Karmesh Yadav Rohitashva Singh Saurabh Swapnil Daga Nahas Pareekutty K. Madhava Krishna Balaraman Ravindran Brojeshwar Bhowmick Embedded Systems & Robotics TCS Research & Innovation Kolkata India Robotics Institute Carnegie Mellon University Pittsburgh USA Dept. of Robotics Engineering John Hopkins University Baltimore USA Robotics Research Center KCIS IIIT Hyderabad India Dept. of Computer Science Indian Institute of Technology Madras 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： Monocular SLAM

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 2018

A Deep Learning-based Model for Phase Unwrapping

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： G. E. Spoorthi Subrahmanyam Gorthi Rama Krishna Sai Gorthi Indian Institute of Technology Tirupati A.P

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

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 2018

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

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Muhammed Fasil C. Subhasis Chaudhuri Dept. of Electrical Engineering Indian Institute of Technology Bombay Mumbai 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： MA-RNN RNN person re-identification

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Floorplan Generation 18

Towards Automated Floorplan Generation

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： Kunal Chelani Chitturi Sidhartha Venu Madhav Govindu Indian Institute of Science 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：

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification 2018

Multiple Kernel Fisher Discriminant Metric Learning for Pers...

引用

Proceedings of the 11th indian conference on computer vision, graphics and image processing

作者： T. M. Feroz Ali Rajbabu Velmurugan Kalpesh K. Patel Subhasis Chaudhuri Dept. of Electrical Engineering Indian Institute of Technology Bombay Mumbai India

ISBN: (纸本)9781450366151

Person re-identification addresses the problem of matching pedestrian images across disjoint camera views. Design of feature descriptor and distance metric learning are the two fundamental tasks in person re-identification. In this paper, we propose a metric learning framework for person re-identification, where the discriminative metric space is learned using Kernel Fisher Discriminant Analysis (KFDA), to simultaneously maximize the inter-class variance as well as minimize the intra-class variance. We derive a Mahalanobis metric induced by KFDA and argue that KFDA is efficient to be applied for metric learning in person re-identification. We also show how the efficiency of KFDA in metric learning can be further enhanced for person re-identification by using two simple yet efficient multiple kernel learning methods. We conduct extensive experiments on three benchmark datasets for person re-identification and demonstrate that the proposed approaches have competitive performance with state-of-the-art methods.

关键词： Kernel Fisher Discriminant Analysis Multiple Kernel Fisher Discriminant Analysis Person Re-identification Metric Learning

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for 3D Scene Reconstruction

Generative Adversarial Networks for 3D Scene Reconstruction

引用

International conference on Computing and Networking Technology (ICCNT)

作者： K. Senthamil Selvan Samaksh Goyal Aravindan M K Omkaresh S. Kulkarni K. Yuvaraj Nitish Vashisht Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai india Quantum University Research Center Quantum University School of Engineering and Technology Mechaical Engineering JAIN (Deemed to be University) Bangalore Karnataka India Department of Computer Science and Engineering (AI & ML) Vishwakarma Institute of Technology Pune INDIA Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Generative opposed Networks (GANs) are a generative model broadly utilized in device mastering, PC vision, and herbal language processing (NLP). GANs hire neural networks, a generator, and a discriminator that are trained collectively to be able to generate realistic-looking statistics, along with photographs, audio clips, or 3-D scenes. In this painting, we are aware of $3-\mathrm{D}$ scene reconstruction using GAN-based total methods. We aim to generate 3-D scenes from given 2nd pics, allowing us to benefit from insight into the structure and layout of complicated 3-D environments. To this end, we endorse leveraging a method known as inverse rendering to enhance the accuracy of the reconstructed 3-D scenes. We compare our method to the usage of artificial and real-international images, and the effects display the efficacy of our approach. Finally, we talk about capacity destiny guidelines for three-D scene reconstruction and the usage of GAN-based total strategies.

关键词： three-dimensional displays Shape Neural networks Layout Generative adversarial networks Rendering (computer graphics) Generators image reconstruction Painting Guidelines

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101页 << < 92 93 94 95 96 97 98 99 100 101 > >>

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：