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

13,848 篇 会议
852 篇 期刊文献
31 册 图书
29 篇 学位论文
3 篇 专利

馆藏范围

14,762 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,769 篇 工学
- 4,050 篇 计算机科学与技术...
- 2,266 篇 电气工程
- 2,007 篇 软件工程
- 1,253 篇 生物医学工程（可授...
- 1,050 篇 信息与通信工程
- 989 篇 光学工程
- 652 篇 控制科学与工程
- 639 篇 仪器科学与技术
- 626 篇 核科学与技术
- 569 篇 机械工程
- 434 篇 电子科学与技术（可...
- 401 篇 生物工程
- 237 篇 测绘科学与技术
- 150 篇 材料科学与工程（可...
- 116 篇 航空宇航科学与技...
- 112 篇 建筑学
- 112 篇 土木工程
3,753 篇 理学
- 2,647 篇 物理学
- 1,102 篇 数学
- 469 篇 生物学
- 316 篇 统计学（可授理学、...
- 180 篇 化学
- 164 篇 系统科学
2,610 篇 医学
- 1,602 篇 临床医学
- 1,247 篇 特种医学
- 258 篇 基础医学(可授医学...
- 109 篇 医学技术（可授医学...
- 108 篇 药学(可授医学、理...
393 篇 管理学
- 271 篇 管理科学与工程(可...
- 137 篇 图书情报与档案管...
72 篇 农学
37 篇 艺术学
35 篇 法学
22 篇 经济学
21 篇 教育学
21 篇 文学
13 篇 军事学
3 篇 历史学

主题

7,673 篇 image reconstruc...
1,030 篇 cameras
872 篇 three-dimensiona...
784 篇 computed tomogra...
714 篇 image segmentati...
619 篇 reconstruction a...
606 篇 positron emissio...
561 篇 surface reconstr...
547 篇 shape
516 篇 image resolution
465 篇 training
462 篇 magnetic resonan...
456 篇 data mining
375 篇 imaging phantoms
363 篇 detectors
357 篇 deep learning
354 篇 image coding
346 篇 solid modeling
333 篇 attenuation
332 篇 compressed sensi...

机构

89 篇 univ chicago dep...
33 篇 department of ra...
32 篇 tsinghua univ de...
29 篇 department of ra...
28 篇 department of ra...
24 篇 suny stony brook...
22 篇 dartmouth coll t...
21 篇 microsoft resear...
20 篇 univ chinese aca...
20 篇 department of en...
17 篇 washington univ ...
17 篇 univ chicago dep...
16 篇 shanghai jiao to...
15 篇 university of sc...
15 篇 institute of nuc...
15 篇 university of ch...
14 篇 department of ra...
14 篇 tsinghua univ mi...
14 篇 department of ra...
13 篇 tsinghua univers...

作者

82 篇 pan xiaochuan
31 篇 xia dan
26 篇 emil y. sidky
25 篇 kudo hiroyuki
25 篇 liang zhengrong
24 篇 m. defrise
23 篇 li zhang
23 篇 m.a. king
20 篇 zhengrong liang
20 篇 maier andreas
20 篇 ma jianhua
19 篇 kris thielemans
18 篇 yuxiang xing
18 篇 j.a. fessler
18 篇 g.t. gullberg
17 篇 grant t. gullber...
17 篇 liu yan
17 篇 chen guang-hong
16 篇 hutton brian f.
16 篇 chen buxin

语言

14,489 篇 英文
144 篇 其他
121 篇 中文
11 篇 土耳其文
2 篇 德文
2 篇 俄文
1 篇 法文
1 篇 日文
1 篇 泰文
1 篇 乌克兰文

检索条件"任意字段=Conference on Image Reconstruction from Incomplete Data"

共 14763 条记录，以下是381-390 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：

How do Minimum-Norm Shallow Denoisers Look in Function Space? 37

How do Minimum-Norm Shallow Denoisers Look in Function Space...

引用

37th conference on Neural Information Processing Systems (NeurIPS)

作者： Zeno, Chen Ongie, Greg Blumenfeld, Yaniv Weinberger, Nir Soudry, Daniel Technion Israel Inst Technol Elect & Comp Engn Haifa Israel Marquette Univ Dept Math & Stat Sci Milwaukee WI 53233 USA

ISBN: (纸本)9781713899921

Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation. However, the success of these models is not well understood from a theoretical perspective. In this paper, we aim to characterize the functions realized by shallow ReLU NN denoisers- in the common theoretical setting of interpolation (i.e., zero training loss) with a minimal representation cost (i.e., minimal l(2) norm weights). First, for univariate data, we derive a closed form for the NN denoiser function, find it is contractive toward the clean data points, and prove it generalizes better than the empirical MMSE estimator at a low noise level. Next, for multivariate data, we find the NN denoiser functions in a closed form under various geometric assumptions on the training data: data contained in a low-dimensional subspace, data contained in a union of one-sided rays, or several types of simplexes. These functions decompose into a sum of simple rank-one piecewise linear interpolations aligned with edges and/or faces connecting training samples. We empirically verify this alignment phenomenon on synthetic data and real images.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fast image reconstruction for near-field terahertz imaging with multistatic non-uniform sparse arrays 27

Fast image reconstruction for near-field terahertz imaging w...

引用

conference on Radar Sensor Technology XXVII

作者： Molaei, Amir Masoud Hu, Shaoqing Skouroliakou, Vasiliki Fusco, Vincent Chen, Xiaodong Yurduseven, Okan Queens Univ Belfast Inst Elect Commun & Informat Technol ECIT Queens Rd Belfast BT3 9DT Antrim North Ireland Brunel Univ London Coll Engn Design & Phys Sci Kingston Lane Uxbridge UB8 3PH England Queen Mary Univ London Sch Elect Engn & Comp Sci Mile End Rd London E1 4NS England

ISBN: (纸本)9781510661844;9781510661851

In this paper, first, the structure of a linear sparse periodic array for two-dimensional scanning is described. Then, based on its characteristics, an algorithm is presented for fast image reconstruction of the scene in a near-field (NF) multistatic terahertz imaging scenario. Although the basis of this algorithm is developed in the Fourier domain, it is compatible with the non-uniform structure of the array and also takes into account the phase deviations caused by multistatic imaging in NF. The performance of the proposed approach is evaluated with numerical data obtained from electromagnetic simulations in FEKO as well as experimental data. The results are discussed in terms of computational time on the central processing unit and graphics processing unit as well as the quality of the reconstructed image.

关键词： Fast image reconstruction multistatic non-uniform array near-field THz imaging

来源：评论

学校读者我要写书评

暂无评论

SIRA: Relightable Avatars from a Single image 23

SIRA: Relightable Avatars from a Single Image

引用

23rd IEEE/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Caselles, Pol Ramon, Eduard Garcia, Jaime Giro-i-Nieto, Xavier Moreno-Noguer, Francesc Triginer, Gil Crisalix SA Lausanne Switzerland Univ Politecn Cataluna Barcelona Spain UPC CSIC Inst Robot & Informat Ind Barcelona Spain

ISBN: (纸本)9781665493468

Recovering the geometry of a human head from a single image, while factorizing the materials and illumination, is a severely ill-posed problem that requires prior information to be solved. Methods based on 3D Morphable Models (3DMM), and their combination with differentiable renderers, have shown promising results. However, the expressiveness of 3DMMs is limited, and they typically yield over-smoothed and identity-agnostic 3D shapes limited to the face region. Highly accurate full head reconstructions have recently been obtained with neural fields that parameterize the geometry using multilayer perceptrons. The versatility of these representations has also proved effective for disentangling geometry, materials and lighting. However, these methods require several tens of input images. In this paper, we introduce SIRA, a method which, from a single image, reconstructs human head avatars with high fidelity geometry and factorized lights and surface materials. Our key ingredients are two data-driven statistical models based on neural fields that resolve the ambiguities of single-view 3D surface reconstruction and appearance factorization. Experiments show that SIRA obtains state of the art results in 3D head reconstruction while at the same time it successfully disentangles the global illumination, and the diffuse and specular albedos. Furthermore, our reconstructions are amenable to physically-based appearance editing and head model relighting.

关键词： Geometry Surface reconstruction Solid modeling Head Three-dimensional displays Shape Avatars

来源：评论

学校读者我要写书评

暂无评论

Research on Scene Text image Super-Resolution Based on Improved TATT Model 7

Research on Scene Text Image Super-Resolution Based on Impro...

引用

7th International conference on Computer Information Science and Application Technology, CISAT 2024

作者： Zhang, Qingyuan Chen, Yuhua Yunnan Normal University School of Information Science and Technology Kunming China

ISBN: (纸本)9798350375107

Scene text image super-resolution (STISR) is a super-resolution task for specific image data, with the objective of enhancing the clarity of low-resolution scene text images, thereby improving the performance of downstream text recognition tasks. In contrast to regular image data, scene text images comprise solely of text and background, and the background is of no use for downstream text recognition tasks and may also affect the reconstruction effect. The majority of current research on scene text image super-resolution employs straightforward methods, such as thresholding and edge detection, to distinguish text from background. However, these methods are unable to achieve satisfactory precision. In light of the aforementioned circumstances, this paper proposes a mask generation subnet to differentiate between the text and background parts of the image in order to eliminate the interference of complex backgrounds. Additionally, to make the network pay more attention to the text, this paper proposes a channel dilated neighborhood attention block (CDiNAB), which assigns weights to features at both the channel and spatial levels. Experimental results on the TextZoom benchmark dataset demonstrate that the proposed method effectively improves the accuracy of text recognition in comparison to the current mainstream STISR methods. © 2024 IEEE.

关键词： channel dilated neighborhood attention mask generation super-resolution text image

来源：评论

学校读者我要写书评

暂无评论

RawHDR: High Dynamic Range image reconstruction from a Single Raw image

RawHDR: High Dynamic Range Image Reconstruction from a Singl...

引用

IEEE/CVF International conference on Computer Vision (ICCV)

作者： Zou, Yunhao Yan, Chenggang Fu, Ying Beijing Inst Technol Beijing Peoples R China Hangzhou Dianzi Univ Hangzhou Peoples R China

ISBN: (纸本)9798350307184

High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, it becomes a formidable task to retrieve extremely high dynamic range scenes from such limited bit-depth data. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene). To this end, we propose a model tailor-made for Raw images, harnessing the unique features of Raw data to facilitate the Raw-to-HDR mapping. Specifically, we learn exposure masks to separate the hard and easy regions of a high dynamic scene. Then, we introduce two important guidances, dual intensity guidance, which guides less informative channels with more informative ones, and global spatial guidance, which extrapolates scene specifics over an extended spatial domain. To verify our Raw-to-HDR approach, we collect a large Raw/HDR paired dataset for both training and testing. Our empirical evaluations validate the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Approach for image Compression Using Compressed Sensing Technique with Convolutional Autoencoders 2

Optimized Deep Learning Approach for Image Compression Using...

引用

2nd IEEE International conference on data Science and Network Security, ICDSNS 2024

作者： Puttegowda, Kiran Veeraprathap, V. Sequeira, Sharmila Shanthi Aruna, B. Kirankumarhumse Sunil Kumar, D.S. Sudheesh, K.V. Vidyavardhaka College of Engineering Department of Ece Karnataka Mysuru India Atme College of Engineering Department of Ece Karnataka Mysuru India Nitte Meenakshi Institute of Technology Department of Cse Karnataka Bengaluru India Bgs Institute of Technology Adichunchanagiri University Department of Ece Karnataka Mandya India Anatta Innovations Bgs B-School Bengaluru India

ISBN: (纸本)9798350373110

image compression is crucial for efficient storage and transmission of visual data. Traditional methods like JPEG use transform coding, which may result in loss of fine details. Compressed sensing (CS) offers an alternative by exploiting signal sparsity, allowing for significant data reduction without substantial loss of information. Compressed sensing (CS) has proven to be an important technique in signal acquisition, especially in contexts in which sensor quality or the maximum possible duration of the measurement is limited. In this paper, deep learning techniques are used to improve compressive sensing in the context of image acquisition. In a existing approaches deployed stacked denoising autoencoders capable of reconstructing images considerably faster than conventional iterative methods. Apart from reviewing this approach, a possible extension using convolutional autoencoders inspired by the popular VGGnet architecture is discussed. Instead of learning models from scratch, a simple yet effective way for adapting available filters used in imageNet classification is presented. By reformulation of the autoencoder structure in terms of a fully convolutional network can be adapted to arbitrarily large images for efficient learning of the measurement matrix and sparsity basis. Finally, experimental results indicate that the suggested approach outperforms current state-of-the-art methods across several metrics: reconstruction accuracy, time efficiency, and noise reduction capability. Particularly noteworthy is its exceptional reconstruction accuracy even with a limited number of measurements. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Steerers: A framework for rotation equivariant keypoint descriptors

Steerers: A framework for rotation equivariant keypoint desc...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Bokman, Georg Edstedt, Johan Felsberg, Michael Kahl, Fredrik Chalmers Univ Technol Stockholm Sweden Linkoping Univ Linkoping Sweden

ISBN: (纸本)9798350353013;9798350353006

image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction. However, descriptions output by learned descriptors are typically not robust to camera rotation. While they can be made more robust by, e.g., data augmentation, this degrades performance on upright images. Another approach is test-time augmentation, which incurs a significant increase in runtime. Instead, we learn a linear transform in description space that encodes rotations of the input image. We call this linear transform a steerer since it allows us to transform the descriptions as if the im-age was rotated. from representation theory, we know all possible steerers for the rotation group. Steerers can be optimized (A) given a fixed descriptor, (B) jointly with a descriptor or (C) we can optimize a descriptor given a fixed steerer. We perform experiments in these three settings and obtain state-of-the-art results on the rotation invariant image matching benchmarks AIMS and Roto-360. We publish code and model weights at this https url.

关键词： image matching Keypoint description Learned equivariance Rotation equivariance

来源：评论

学校读者我要写书评

暂无评论

NOVEL reconstruction WITH INTER-FRAME MOTION COMPENSATION FOR FAST SUPER-RESOLUTION LIVE CELL IMAGING 29

NOVEL RECONSTRUCTION WITH INTER-FRAME MOTION COMPENSATION FO...

引用

IEEE International conference on image Processing (ICIP)

作者： Harmanec, Adam Kadlecova, Zuzana Sroubek, Filip Czech Acad Sci Inst Informat Theory & Automat Prague Czech Republic Masaryk Univ Dept Histol & Embryol Fac Med Brno Czech Republic Univ Cambridge Cambridge Inst Med Res Cambridge England

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Structured illumination microscopy is a widely popular super-resolution technique for live cell imaging capable of surpassing the diffraction limit. Its temporal resolution is limited by the need to capture multiple low-resolution images to reconstruct a single high-resolution image. When observing rapid biological processes, the local movement between frames leads to the formation of reconstruction artifacts, which subsequently impair the data interpretation. We propose to include this type of movement in the definition of the image formation forward problem. The motion can then be estimated from the original data using optical flow, and the optimization problem is solved using the alternating direction method of multipliers. Our approach is tested against other reconstruction techniques on both synthetic and real biological data.

关键词： image reconstruction structured illumination microscopy (SIM) ADMM optical flow

来源：评论

学校读者我要写书评

暂无评论

Erase to Enhance: data-Efficient Machine Unlearning in MRI reconstruction 7

Erase to Enhance: Data-Efficient Machine Unlearning in MRI R...

引用

7th International conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Xue, Yuyang Liu, Jingshuai McDonagh, Steven Tsaftaris, Sotirios A. School of Engineering The University of Edinburgh EdinburghEH9 3FG United Kingdom

Machine unlearning is a promising paradigm for removing unwanted data samples from a trained model, towards ensuring compliance with privacy regulations and limiting harmful biases. Although unlearning has been shown in, e.g., classification and recommendation systems, its potential in medical image-to-image translation, specifically in image reconstruction, has not been thoroughly investigated. This paper shows that machine unlearning is possible in MRI tasks and has the potential to be of benefit for bias removal. We set up a protocol to study how much shared knowledge exists between datasets of different organs, allowing us to effectively quantify the effect of unlearning. Our study reveals that combining training data can lead to hallucinations and reduced image quality in the reconstructed data. We use unlearning to remove hallucinations as a proxy exemplar for the removal of undesirable data. We show that machine unlearning is possible without full retraining. Furthermore, our observations indicate that maintaining high performance is feasible even when using only a subset of retain data. We have made our code publicly available. © 2024 CC-BY 4.0, Y. Xue, J. Liu, S. McDonagh & S.A. Tsaftaris.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Automated Line Labelling: dataset for Contour Detection and 3D reconstruction 23

Automated Line Labelling: Dataset for Contour Detection and ...

引用

23rd IEEE/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Santhanam, Hari Doiphode, Nehal Shi, Jianbo Univ Penn Philadelphia PA 19104 USA

ISBN: (纸本)9781665493468

Understanding the finer details of a 3D object, its contours, is the first step toward a physical understanding of an object. Many real-world application domains require adaptable 3D object shape recognition models, usually with little training data. For this purpose, we develop the first automatically generated contour labeled dataset, bypassing manual human labeling. Using this dataset, we study the performance of current state-of-the-art instance segmentation algorithms on detecting and labeling the contours. We produce promising visual results with accurate contour prediction and labeling. We demonstrate that our finely labeled contours can help downstream tasks in computer vision, such as 3D reconstruction from a 2D image.

关键词： Solid modeling Computer vision Visualization Three-dimensional displays Shape Training data Manuals

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500页 << < 35 36 37 38 39 40 41 42 43 44 > >>

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：