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

45 篇 会议
1 册 图书

馆藏范围

46 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

43 篇 工学
- 41 篇 计算机科学与技术...
- 34 篇 软件工程
- 6 篇 光学工程
- 4 篇 生物工程
- 3 篇 生物医学工程（可授...
- 2 篇 信息与通信工程
- 1 篇 力学（可授工学、理...
- 1 篇 仪器科学与技术
- 1 篇 建筑学
- 1 篇 土木工程
34 篇 理学
- 31 篇 数学
- 4 篇 物理学
- 4 篇 生物学
- 1 篇 化学
- 1 篇 地球物理学
1 篇 管理学
- 1 篇 图书情报与档案管...

主题

4 篇 variational meth...
4 篇 image registrati...
3 篇 inpainting
3 篇 total variation
3 篇 denoising
2 篇 inverse problems
2 篇 image segmentati...
2 篇 partial differen...
2 篇 nonlinear spectr...
2 篇 diffusion
2 篇 image processing
2 篇 anisotropy
2 篇 image compressio...
1 篇 sampled methods
1 篇 image fusion
1 篇 structure tensor
1 篇 super-resolution
1 篇 assignment flow
1 篇 sparse data
1 篇 partial differen...

机构

3 篇 saarland univ ma...
2 篇 saarland univ ma...
2 篇 univ bonn inst n...
2 篇 univ bordeaux bo...
2 篇 department of bi...
2 篇 private univ hlt...
2 篇 department of ma...
1 篇 department of co...
1 篇 univ copenhagen ...
1 篇 univ politecn ca...
1 篇 academic center ...
1 篇 univ pompeu fabr...
1 篇 beijing computat...
1 篇 hsch wurzburg sc...
1 篇 fraunhofer insti...
1 篇 univ twente dept...
1 篇 computer science...
1 篇 univ helsinki in...
1 篇 univ twente dept...
1 篇 univ siegen hold...

作者

6 篇 weickert joachim
3 篇 peter pascal
3 篇 rumpf martin
2 篇 bruckstein alfre...
2 篇 bertalmio marcel...
2 篇 rosman guy
2 篇 lauze francois
2 篇 cohen laurent d.
2 篇 duits remco
2 篇 kimmel ron
2 篇 effland alexande...
2 篇 pierre fabien
2 篇 imiya atsushi
2 篇 moeller michael
2 篇 welk martin
1 篇 schonlieb carola...
1 篇 st-onge etienne
1 篇 parisotto simone
1 篇 hansen jacob dan...
1 篇 tai xue-cheng

语言

46 篇 英文

检索条件"任意字段=7th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2019"

共 46 条记录，以下是1-10 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：

7th international conference on scale space and variational methods in computer vision, ssvm 2019

7th International Conference on Scale Space and Variational ...

引用

7th international conference on scale space and variational methods in computer vision, ssvm 2019

ISBN: (纸本)9783030223670

the proceedings contain 44 papers. the special focus in this conference is on scale space and variational methods in computer vision. the topics include: Iterative Sampled methods for Massive and Separable Nonlinear Inverse Problems;Refitting Solutions Promoted by $$\ell _variational$$ Sparse Analysis Regularizations with Block Penalties;An Iteration Method for X-Ray CT Reconstruction from Variable-Truncation Projection Data;A New Iterative Method for CT Reconstruction with Uncertain View Angles;time Discrete Geodesics in Deep Feature spaces for Image Morphing;minimal Lipschitz Extensions for Vector-Valued Functions on Finite Graphs;the Convex-Hull-Stripping Median Approximates Affine Curvature Motion;Total Variation and Mean Curvature PDEs on the space of Positions and Orientations;a variational Convex Hull Algorithm;PDE Evolutions for M-Smoothers: From Common Myths to Robust Numerics;macrocanonical Models for Texture Synthesis;variational Registration of Multiple Images with the SVD Based $$\mathrm {S}q\mathrm {N}$$ Distance Measure;Multi-tasking to Correct: Motion-Compensated MRI via Joint Reconstruction and Registration;variational Image Registration for Inhomogeneous-Resolution Pairs;computing Nonlinear Eigenfunctions via Gradient Flow Extinction;sparsification scale-spaces;stable Explicit p-Laplacian Flows Based on Nonlinear Eigenvalue Analysis;provably scale-Covariant Networks from Oriented Quasi Quadrature Measures in Cascade;a Fast Multi-layer Approximation to Semi-discrete Optimal Transport;global Similarity with Additive Smoothness for Spectral Segmentation;segmentation of 2D and 3D Objects with Intrinsically Similarity Invariant Shape Regularisers;finding Structure in Point Cloud Data with the Robust Isoperimetric Loss;lattice Metric space Application to Grain Defect Detection;learning Adaptive Regularization for Image Labeling Using Geometric Assignment;a Balanced Phase Field Model for Active Contours.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Marching Energy CNN 9th

Fast Marching Energy CNN

引用

9th international conference on scale space and variational methods in computer vision, ssvm 2023

作者： Bertrand, théo Makaroff, Nicolas Cohen, Laurent D. CEREMADE UMR CNRS 7534 University Paris Dauphine PSL Research University Paris75775 France

ISBN: (纸本)9783031319747

Leveraging geodesic distances and the geometrical information they convey is key for many data-oriented applications in imaging. Geodesic distance computation has been used for long for image segmentation using Image based metrics. We introduce a new method by generating isotropic Riemannian metrics adapted to a problem using CNN and give as illustrations an example of application. We then apply this idea to the segmentation of brain tumours as unit balls for the geodesic distance computed with the metric potential output by a CNN, thus imposing geometrical and topological constraints on the output mask. We show that geodesic distance modules work well in machine learning frameworks and can be used to achieve state-of-the-art performances while ensuring geometrical and/or topological properties. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Model is Worth Tens of thousands of Examples 9th

A Model is Worth Tens of Thousands of Examples

引用

9th international conference on scale space and variational methods in computer vision, ssvm 2023

作者： Dagès, thomas Cohen, Laurent D. Bruckstein, Alfred M. Department of Computer Science Technion Israel Institute of Technology Haifa Israel Ceremade University Paris Dauphine PSL Research University UMR CNRS 7534 Paris75016 France

ISBN: (纸本)9783031319747

Traditional signal processing methods relying on mathematical data generation models have been cast aside in favour of deep neural networks, which require vast amounts of data. Since the theoretical sample complexity is nearly impossible to evaluate, these amounts of examples are usually estimated with crude rules of thumb. However, these rules only suggest when the networks should work, but do not relate to the traditional methods. In particular, an interesting question is: how much data is required for neural networks to be on par or outperform, if possible, the traditional model-based methods? In this work, we empirically investigate this question in two simple examples, where the data is generated according to precisely defined mathematical models, and where well-understood optimal or state-of-the-art mathematical data-agnostic solutions are known. A first problem is deconvolving one-dimensional Gaussian signals and a second one is estimating a circle’s radius and location in random grayscale images of disks. By training various networks, either naive custom designed or well-established ones, with various amounts of training data, we find that networks require tens of thousands of examples in comparison to the traditional methods, whether the networks are trained from scratch or even with transfer-learning or finetuning. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Posterior Distributions in Underdetermined Inverse Problems 9th

Learning Posterior Distributions in Underdetermined Inverse...

引用

9th international conference on scale space and variational methods in computer vision, ssvm 2023

作者： Runkel, Christina Moeller, Michael Schönlieb, Carola-Bibiane Etmann, Christian Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom Department of Electrical Engineering and Computer Science University of Siegen Siegen Germany

ISBN: (纸本)9783031319747

In recent years, classical knowledge-driven approaches for inverse problems have been complemented by data-driven methods exploiting the power of machine and especially deep learning. Purely data-driven methods, however, come with the drawback of disregarding prior knowledge of the problem even though it has shown to be beneficial to incorporate this knowledge into the problem-solving process. We thus introduce an unpaired learning approach for learning posterior distributions of underdetermined inverse problems. It combines advantages of deep generative modeling with established ideas of knowledge-driven approaches by incorporating prior information about the inverse problem. We develop a new neural network architecture ’UnDimFlow’ (short for Unequal Dimensionality Flow) consisting of two normalizing flows, one from the data to the latent, and one from the latent to the solution space. Additionally, we incorporate the forward operator to develop an unpaired learning method for the UnDimFlow architecture and propose a tailored point estimator to recover an optimal solution during inference. We evaluate our method on the two underdetermined inverse problems of image inpainting and super-resolution. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A Deep Image Prior Learning Algorithm for Joint Selective Segmentation and Registration 8th

A Deep Image Prior Learning Algorithm for Joint Selective Se...

引用

8th international conference on scale space and variational methods in computer vision, ssvm 2021

作者： Burrows, Liam Chen, Ke Torella, Francesco Department of Mathematical Sciences and Centre for Mathematical Imaging Techniques University of Liverpool Liverpool United Kingdom Liverpool Vascular and Endovascular Service Liverpool University Hospitals LiverpoolL7 8XP United Kingdom

ISBN: (纸本)9783030755485

Effective variational models exist for either image segmentation or image registration for a given class of problems, though robustness is a longstanding issue. this paper proposes a new and effective variational model that aims to segment a pair of images through a joint model with registration, with the advantage of only requiring geometric prior information on one image (instead of two images) and obtaining selective segmentation on both images. Moreover we develop a deep image prior based learning algorithm to achieve the same segmentation and registration results by dropping the regularisation terms from the loss function. Numerical experiments show quality results obtained from the new approach. © 2021, Springer Nature Switzerland AG.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

variational Image Registration for Inhomogeneous-Resolution Pairs 7th

Variational Image Registration for Inhomogeneous-Resolution ...

引用

7th international conference on scale space and variational methods in computer vision (ssvm)

作者： Hosoya, Kento Imiya, Atsushi Chiba Univ Sch Sci & Engn Inage Ku Yayoi Cho 1-33 Chiba 2638522 Japan Chiba Univ Inst Management & Informat Technol Inage Ku Yayoi Cho 1-33 Chiba 2638522 Japan

ISBN: (纸本)9783030223687;9783030223670

We propose a variational image registration method for a pair of images with different resolutions. Traditional image registration methods match images assuming that the resolutions of the reference and target images are homogeneous. For the registration of inhomogeneous-resolution image pairs, we first introduce a resolution-conversion method to harmonise the resolution of a pair of images using the rational-order pyramid ***, we develop a variational method for image registration using this resolution-conversion method.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Lattice Metric space Application to Grain Defect Detection 7th

Lattice Metric Space Application to Grain Defect Detection

引用

7th international conference on scale space and variational methods in computer vision (ssvm)

作者： He, Yuchen Kang, Sung Ha Georgia Inst Technol Sch Math Atlanta GA 30332 USA

ISBN: (纸本)9783030223687;9783030223670

We propose a new model for grain defect detection based on the theory of lattice metric space [7]. the lattice metric space (L, d(L)) shows outstanding advantages in representing lattices. Utilizing this advantage, we propose a new algorithm, Lattice clustering algorithm (LCA). After over-segmentation using regularized k-means, the merging stage is built upon the lattice equivalence relation. Since LCA is built upon (L, d(L)), it is robust against missing particles, deficient hexagonal cells, and can handle non-hexagonal lattices without any modification. We present various numerical experiments to validate our method and investigate interesting properties.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Functional Liftings of Vectorial variational Problems with Laplacian Regularization 7th

Functional Liftings of Vectorial Variational Problems with L...

引用

7th international conference on scale space and variational methods in computer vision (ssvm)

作者： Vogt, thomas Lellmann, Jan Univ Lubeck Inst Math & Image Comp MIC Maria Goeppert Str 3 D-23562 Lubeck Germany

ISBN: (纸本)9783030223687;9783030223670

We propose a functional lifting-based convex relaxation of variational problems with Laplacian-based second-order regularization. the approach rests on ideas from the calibration method as well as from sublabel-accurate continuous multilabeling approaches, and makes these approaches amenable for variational problems with vectorial data and higher-order regularization, as is common in image processing applications. We motivate the approach in the function space setting and prove that, in the special case of absolute Laplacian regularization, it encompasses the discretization-first sublabel-accurate continuous multilabeling approach as a special case. We present a mathematical connection between the lifted and original functional and discuss possible interpretations of minimizers in the lifted function space. Finally, we exemplarily apply the proposed approach to 2D image registration problems.

关键词： variational methods Curvature regularization Convex relaxation Functional lifting Measure-based regularization

来源：评论

学校读者我要写书评

暂无评论

A Balanced Phase Field Model for Active Contours 7th

A Balanced Phase Field Model for Active Contours

引用

7th international conference on scale space and variational methods in computer vision (ssvm)

作者： Molnar, Jozsef Tasnadi, Ervin Horvath, Peter Hungarian Acad Sci Biol Res Ctr Szeged Hungary Univ Helsinki Inst Mol Med Finland Helsinki Finland

ISBN: (纸本)9783030223687;9783030223670

In this paper we present a balanced phase field model that eliminates the often undesired curvature-dependent shrinking of the zero level set, while maintaining the smooth interface necessary to calculate fundamental quantities such as the normal vector or the curvature of the represented contour. the proposed model extends the Ginzburg-Landau phase field energy with a higher order smoothness term. the relative weights are determined with the analysis of the level set motion in a curvilinear system adapted to the zero level set. the proposed level set framework exhibits strong shape maintaining capability without significant interference with the active (e.g. a segmentation) model.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Joint CNN and variational Model for Fully-Automatic Image Colorization 7th

Joint CNN and Variational Model for Fully-Automatic Image Co...

引用

7th international conference on scale space and variational methods in computer vision (ssvm)

作者： Mouzon, thomas Pierre, Fabien Berger, Marie-Odile Univ Lorraine Lab Lorrain Rech Informat & Ses Applicat CNRS INRIA Projet MagritUMR 7503 Vandoeuvre Les Nancy France

ISBN: (纸本)9783030223687;9783030223670

this paper aims to couple the powerful prediction of the convolutional neural network (CNN) to the accuracy at pixel scale of the variational methods. In this work, the limitations of the CNN-based image colorization approaches are described. We then focus on a CNN which is able to compute a statistical distribution of the colors for each pixel of the image based on a learning stage on a large color image database. After describing its limitation, the variational method of [17] is briefly recalled. this method is able to select a color candidate among a given set while performing regularization of the result. By combining this approach with a CNN, we designed a fully automatic image colorization framework with an improved accuracy in comparison with CNN alone. Some numerical experiments demonstrate the increased accuracy reached by our method.

关键词： Colorization Convolutional Neural Networks Total variation Optimization

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5页 << < 1 2 3 4 5 > >>

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：