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

275 篇 会议
10 册 图书
6 篇 期刊文献

馆藏范围

291 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

256 篇 工学
- 222 篇 计算机科学与技术...
- 99 篇 软件工程
- 54 篇 光学工程
- 31 篇 信息与通信工程
- 17 篇 电气工程
- 17 篇 生物工程
- 16 篇 生物医学工程（可授...
- 11 篇 电子科学与技术（可...
- 8 篇 仪器科学与技术
- 6 篇 控制科学与工程
- 6 篇 化学工程与技术
- 5 篇 力学（可授工学、理...
- 5 篇 机械工程
- 5 篇 建筑学
- 5 篇 土木工程
- 3 篇 材料科学与工程（可...
- 3 篇 安全科学与工程
- 2 篇 动力工程及工程热...
- 2 篇 测绘科学与技术
156 篇 理学
- 123 篇 数学
- 53 篇 物理学
- 17 篇 生物学
- 10 篇 统计学（可授理学、...
- 9 篇 化学
- 4 篇 地球物理学
- 4 篇 系统科学
60 篇 医学
- 59 篇 临床医学
- 3 篇 基础医学(可授医学...
7 篇 管理学
- 5 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学

主题

19 篇 variational meth...
12 篇 inverse problems
9 篇 diffusion
9 篇 computer vision
9 篇 numerical method...
8 篇 image segmentati...
8 篇 image registrati...
8 篇 image processing...
7 篇 variational tech...
7 篇 total variation
7 篇 iterative method...
7 篇 pattern recognit...
6 篇 image enhancemen...
6 篇 image processing
6 篇 image reconstruc...
5 篇 computer graphic...
5 篇 machine learning
5 篇 regularization
5 篇 mathematical mor...
5 篇 these keywords w...

机构

6 篇 mathematical ima...
4 篇 department of ma...
4 篇 univ saarland fa...
4 篇 eindhoven univ t...
4 篇 department of ma...
3 篇 institute of mat...
3 篇 univ copenhagen ...
3 篇 department of bi...
3 篇 mathematical ima...
2 篇 ophthalmology de...
2 篇 normandie univ u...
2 篇 image and patter...
2 篇 cmla cnrs ens ca...
2 篇 mathematical ima...
2 篇 georgia inst tec...
2 篇 department of ma...
2 篇 department of co...
2 篇 tel aviv univ de...
2 篇 univ bonn inst n...
2 篇 univ minnesota d...

作者

27 篇 weickert joachim
14 篇 duits remco
8 篇 nikolova mila
8 篇 peter pascal
7 篇 tai xue-cheng
7 篇 bruhn andres
7 篇 lindeberg tony
7 篇 rumpf martin
6 篇 schnörr christop...
6 篇 durou jean-denis
5 篇 calatroni luca
5 篇 pock thomas
5 篇 lellmann jan
5 篇 lauze francois
5 篇 burger martin
5 篇 kimmel ron
5 篇 sochen nir
5 篇 effland alexande...
5 篇 imiya atsushi
5 篇 dong yiqiu

语言

289 篇 英文
2 篇 其他

检索条件"任意字段=3rd International Conference on Scale Space and Variational Methods in Computer Vision"

共 291 条记录，以下是11-20 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：

MISS: A Generative Pre-training and Fine-Tuning Approach for Med-VQA 33rd

MISS: A Generative Pre-training and Fine-Tuning Approach for...

引用

33rd international conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Chen, Jiawei Yang, Dingkang Jiang, Yue Lei, Yuxuan Zhang, Lihua Fudan Univ Acad Engn & Technol Shanghai Peoples R China Fudan Univ Inst Meta Med Cognit & Intelligent Technol Lab CIT Lab Shanghai Peoples R China Minist Educ Engn Res Ctr AI & Robot Shanghai Peoples R China Jilin Prov Key Lab Intelligence Sci & Engn Changchun Peoples R China

ISBN: (纸本)9783031723520;9783031723537

Medical visual question answering (VQA) is a challenging multimodal task, where vision-Language Pre-trained (VLP) models can effectively improve the generalization performance. However, most current methods in the medical field treat VQA as an answer classification task which is difficult to transfer to practical application scenarios. Additionally, due to the privacy of medical images and the expensive annotation process, large-scale medical image-text pairs datasets for pretraining are severely lacking. In this paper, we propose an efficient MultI-task Self-Supervised-learning-based framework (MISS) for medical VQA tasks. Unlike existing methods, we treat medical VQA as a generative task. We unify the text encoder and multimodal encoder and align image-text features through multi-task learning. Furthermore, we propose a Transfer-and-Caption (TransCap) method that extends the feature space of single-modal image datasets using Large Language Models (LLMs), enabling those traditional medical vision-field task data to be applied to VLP models. We conduct extensive experiments and compare them with existing medical VQA methods adopting a no-generative paradigm. We demonstrate the advantages of pre-training with data generated by the TransCap method and our method achieves excellent results with fewer multimodal datasets. The code has been released at https://***/TIMMY-CHAN/***.

关键词： Medical visual question answering vision-language pre-training Multi-modal learning

来源：评论

学校读者我要写书评

暂无评论

The variational Approach to the Flow of Sobolev-Diffeomorphisms Model 9th

The Variational Approach to the Flow of Sobolev-Diffeomor...

引用

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

作者： Guastini, Mara Rajković, Marko Rumpf, Martin Wirth, Benedikt Institute for Numerical Simulation University of Bonn Endenicher Allee 60 Bonn53115 Germany Applied Mathematics Münster University of Münster Orléans-Ring 10 Münster48149 Germany

ISBN: (纸本)9783031319747

The flow of diffeomorphisms, aka LDDMM, is a framework to define a group G of diffeomorphisms of chosen regularity with a Riemannian structure. If these diffeomorphisms are used to deform a template shape or image, they generate a space of shapes or images to which the Riemannian structure descends. For this reason LDDMM lies at the centre of computational anatomy, shape space theory, and image metamorphosis. Typically, to obtain a geodesic equation on G one formally applies the geodesic equation of Riemannian Lie groups, to which G has structural similarity. Then interpolation tasks between two given deformations, needed for all kinds of statistical analyses, are solved by shooting discretized geodesics within an optimal control approach. If G is chosen with Sobolev regularity, it is known to be a veritable infinite-dimensional Riemannian manifold. In this setting we derive the weak geodesic PDE, which in its strong form coincides with the formally derived one, and present a time discretization to compute a geodesic between given deformations by minimizing a time-discrete path energy, which Mosco-converges to the continuous path energy. This variational ansatz is a more natural alternative to shooting and to our knowledge the first numerical approach to LDDMM by minimization. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Geodesy

来源：评论

学校读者我要写书评

暂无评论

Regularized Material Decomposition for K-edge Separation in Hyperspectral Computed Tomography 9th

Regularized Material Decomposition for K-edge Separation in...

引用

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

作者： Bevilacqua, Francesca Dong, Yiqiu Jørgensen, Jakob Sauer Department of Mathematics University of Bologna Bologna Italy Department of Applied Mathematics and Computer Science Technical University of Denmark Kgs. Lyngby Denmark

ISBN: (纸本)9783031319747

Hyperspectral computed tomography is a developing technique that exploits the property of materials to attenuate X-rays in different quantities depending on the specific energy. It allows to not only reconstruct the object, but also to estimate the concentration of the materials which compose it. The objective of the present study is to obtain an accurate material decomposition from noisy few-projection data. A preliminary comparative study of reconstruction methods based on material decomposition is performed, employing a phantom composed of materials with similar attenuation profiles with characteristic K-edges separated by only 2, 4 and 6 keV. It is found that a one-stage method encompassing both material decomposition and tomographic reconstruction in a single variational model performs better than a more conventional two-stage approach. It is further found that better modelling of noise through use of a weighted least-squares data fidelity improves reconstruction and material separation, as does the use total variation and L1-norm regularization. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Latent-space Disentanglement with Untrained Generator Networks for the Isolation of Different Motion Types in Video Data 9th

Latent-Space Disentanglement with Untrained Generator Netwo...

引用

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

作者： Abdullah, Abdullah Holler, Martin Kunisch, Karl Landman, Malena Sabate Department of Mathematics The Chinese University of Hong Kong Hong Kong Institute of Mathematics and Scientific Computing University of Graz Graz Austria Department of Mathematics Emory University Atlanta United States

ISBN: (纸本)9783031319747

Isolating different types of motion in video data is a highly relevant problem in video analysis. Applications can be found, for example, in dynamic medical or biological imaging, where the analysis and further processing of the dynamics of interest is often complicated by additional, unwanted dynamics, such as motion of the measurement subject. In this work, it is empirically shown that a representation of video data via untrained generator networks, together with a specific technique for latent space disentanglement that uses minimal, one-dimensional information on some of the underlying dynamics, allows to efficiently isolate different, highly non-linear motion types. In particular, such a representation allows to freeze any selection of motion types, and to obtain accurate independent representations of other dynamics of interest. Obtaining such a representation does not require any pre-training on a training data set, i.e., all parameters of the generator network are learned directly from a single video. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Hypergraph p-Laplacians, scale spaces, and Information Flow in Networks 9th

Hypergraph p-Laplacians, Scale Spaces, and Information Flow...

引用

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

作者： Fazeny, Ariane Tenbrinck, Daniel Burger, Martin Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91058 Germany Deutsches Elektronen-Synchrotron Hamburg22607 Germany Fachbereich Mathematik Universität Hamburg Hamburg20146 Germany

ISBN: (纸本)9783031319747

The aim of this paper is to revisit the definition of differential operators on hypergraphs, which are a natural extension of graphs in systems based on interactions beyond pairs. In particular we focus on the definition of Laplacian and p-Laplace operators, their basic spectral properties, variational structure, and their scale spaces. We shall see that the corresponding gradient flows, i.e., diffusion equations on hypergraphs, are possible models for the information flow on social networks, e.g., in opinion formation based on group discussion. Moreover, the spectral analysis and scale spaces induced by these operators provide a potential method to further analyze complex networks and their multiscale structure. The quest for spectral analysis on hypergraphs motivates in particular a definition of differential operators with trivial first eigenfunction and thus more interpretable second eigenfunctions. This property is not automatically satisfied in existing definitions of hypergraph p-Laplacians and we hence provide a novel axiomatic approach that extends previous definitions and can be specialized to satisfy such (or other) desired properties. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Image Blending with Osmosis 9th

Image Blending with Osmosis

引用

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

作者： Bungert, Paul Peter, Pascal Weickert, Joachim Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Campus E1.7 Saarland University Saarbrücken66041 Germany

ISBN: (纸本)9783031319747

Image blending is an integral part of many multi-image applications such as panorama stitching or remote image acquisition processes. In such scenarios, multiple images are connected at predefined boundaries to form a larger image. A convincing transition between these boundaries may be challenging, since each image might have been acquired under different conditions or even by different devices. We propose the first blending approach based on osmosis filters. These drift-diffusion processes define an image evolution with a non-trivial steady state. For our blending purposes, we explore several ways to compose drift vector fields based on the derivatives of our input images. These vector fields guide the evolution such that the steady state yields a convincing blended result. Our method benefits from the well-founded theoretical results for osmosis, which include useful invariances under multiplicative changes of the colour values. Experiments on real-world data show that this yields better quality than traditional gradient domain blending, especially under challenging illumination conditions. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Osmosis

来源：评论

学校读者我要写书评

暂无评论

A Frame Decomposition of the Funk-Radon Transform 9th

A Frame Decomposition of the Funk-Radon Transform

引用

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

作者： Quellmalz, Michael Weissinger, Lukas Hubmer, Simon Erchinger, Paul D. Technische Universität Berlin Institute of Mathematics MA 4-3 Straße des 17. Juni 136 Berlin10623 Germany Johann Radon Institute Linz Altenbergerstraße 69 Linz4040 Austria

ISBN: (纸本)9783031319747

The Funk-Radon transform assigns to a function defined on the unit sphere its integrals along all great circles of the sphere. In this paper, we consider a frame decomposition of the Funk-Radon transform, which is a flexible alternative to the singular value decomposition. In particular, we construct a novel frame decomposition based on trigonometric polynomials and show its application for the inversion of the Funk-Radon transform. Our theoretical findings are verified by numerical experiments, which also incorporate a regularization scheme. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Multi-view Normal Estimation – Application to Slanted Plane-Sweeping 9th

Multi-view Normal Estimation – Application to Slanted Plan...

引用

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

作者： Calvet, Lilian Maignan, Nicolas Brument, Baptiste Mélou, Jean Tozza, Silvia Durou, Jean-Denis Quéau, Yvain Research in Orthopedic Computer Science Balgrist University Hospital University of Zurich Zurich8008 Switzerland Université de Lorraine CNRS Inria LORIA Nancy54000 France IRIT UMR CNRS 5505 Toulouse31000 France Department of Mathematics Università di Bologna Bologna40126 Italy Normandie Univ UNICAEN ENSICAEN CNRS GREYC Caen14000 France

ISBN: (纸本)9783031319747

In this paper, we show how to estimate the normals of a 3D surface from a minimum of two views, assuming that the poses of a calibrated camera are perfectly known. For each pair of image points, the normal at the corresponding 3D point is expressed in function of the local gradients of the grey level, whatever the type of image formation (orthogonal or perspective projection). As an application, this allows us to fully estimate the inter-image homography, which not only depends on the relative pose between views, but also on the local orientation of the surface. Hence, the photo-consistency between patches from two images, which is the basis of the so-called "plane-sweeping" method, is improved. Experiments on synthetic and real data validate our approach. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

3D Object Reconstruction from 2D Images Using variational Autoencoders (VAE) 3

3D Object Reconstruction from 2D Images Using Variational Au...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Mohamed, Aezeden Nii, Rainier Binga, Kipas Pandey, Alok Kumar Karpagam, J. Nnadhini, T.J. School of Mechanical Engineering Png University of Technology Lae Papua New Guinea School of Mathematics and Computer Science Ng University of Technology Lae Papua New Guinea Angau Memorial General Hospital Lae Papua New Guinea Uttaranchal University Dehradun India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore India Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331542375

In this research, we present a new method on how to reconstruct 3D object from 2D images by employing variational Autoencoders (VAE). His generality is a bit stark;however, it is well justified given that classical approaches to 3D reconstruction from multiple perspectives fail to capture detailed geometries from few 2D views. These limitations are surmounted by the proposed VAE based framework our approach learns the distribution of 3D shapes using probabilistic inference leading to accurate reconstruction from one or two 2D images. The model also has a decoder that provides a 3D mesh or voxel grid to effectively be used in computer vision, AR and VR applications. The VAE model takes benefit of a big dataset of 3D object shapes, while the encoder dimension translate the 2D picture in the latent space and the decoder rebuild the 3D objects from this space. From the proposed method evaluation, the results suggest high reconstruction accuracy of the proposed method as compared to the traditional point cloud and mesh-based methods in both quality and time taken. The VAE-based system also improves the model's generalization because it has low computational complexity and creates clear and realistic 3D models. The suggested approach has a massive application to the real-time 3D object reconstruction in the different areas including games, product designing as well as diagnosing tools in medical sciences. © 2025 IEEE.

关键词： variational techniques

来源：评论

学校读者我要写书评

暂无评论

Modeling Large-scale Joint Distributions and Inference by Randomized Assignment 9th

Modeling Large-Scale Joint Distributions and Inference by ...

引用

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

作者： Boll, Bastian Schwarz, Jonathan Gonzalez-Alvarado, Daniel Sitenko, Dmitrij Petra, Stefania Schnörr, Christoph Image and Pattern Analysis Group Heidelberg University Heidelberg Germany Mathematical Imaging Group Heidelberg University Heidelberg Germany

ISBN: (纸本)9783031319747

We propose a novel way of approximating energy-based models by randomizing the parameters of assignment flows, a class of smooth dynamical data labeling systems. Our approach builds on averaging flow limit points within the combinatorially large simplex of joint distributions. In an initial learning stage, the distribution of flow parameters is selected to match a given energy-based model. This entails the difficult problem of estimating model entropy which we address by differentiable approximation of a bias-corrected estimator. The model subsequently allows to perform probabilistic inference by computationally efficient draws of structured integer samples which are approximately governed by the energy-based target Gibbs measure in the low-temperature regime. We conduct a rigorous quantitative assessment by approximating a small two-dimensional Ising model and find close approximation of the combinatorial solution in terms of relative entropy which outperforms a mean-field approximation baseline. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Entropy

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30页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：