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

605 篇 会议
17 篇 期刊文献

馆藏范围

622 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

360 篇 工学
- 188 篇 计算机科学与技术...
- 110 篇 电气工程
- 89 篇 软件工程
- 52 篇 生物医学工程（可授...
- 41 篇 光学工程
- 40 篇 测绘科学与技术
- 36 篇 仪器科学与技术
- 36 篇 信息与通信工程
- 27 篇 控制科学与工程
- 21 篇 核科学与技术
- 20 篇 电子科学与技术（可...
- 20 篇 生物工程
- 18 篇 机械工程
- 8 篇 材料科学与工程（可...
- 5 篇 土木工程
- 4 篇 建筑学
- 4 篇 航空宇航科学与技...
242 篇 理学
- 198 篇 物理学
- 44 篇 数学
- 25 篇 生物学
- 12 篇 统计学（可授理学、...
- 6 篇 化学
- 5 篇 系统科学
- 4 篇 大气科学
219 篇 医学
- 180 篇 临床医学
- 79 篇 特种医学
- 13 篇 医学技术（可授医学...
- 5 篇 基础医学(可授医学...
13 篇 管理学
- 11 篇 管理科学与工程(可...
8 篇 农学
- 5 篇 作物学
1 篇 文学
1 篇 军事学

主题

259 篇 image reconstruc...
37 篇 computed tomogra...
33 篇 three-dimensiona...
30 篇 reconstruction a...
25 篇 training
24 篇 image segmentati...
24 篇 cameras
23 篇 solid modeling
23 篇 surface reconstr...
22 篇 image restoratio...
22 篇 tomography
22 篇 image processing
21 篇 compressed sensi...
21 篇 shape
21 篇 image quality
18 篇 magnetic resonan...
17 篇 deep learning
17 篇 image resolution
16 篇 biomedical imagi...
16 篇 image registrati...

机构

8 篇 univ canterbury ...
6 篇 univ canterbury ...
4 篇 dartmouth coll t...
3 篇 univ rochester i...
3 篇 univ n carolina ...
3 篇 departamento de ...
3 篇 hosp gen univ gr...
2 篇 department of ra...
2 篇 linkoping univ d...
2 篇 peking univ peop...
2 篇 department of ra...
2 篇 laboratoire des ...
2 篇 univ chinese aca...
2 篇 siemens srl bras...
2 篇 school of comput...
2 篇 department of en...
2 篇 unidad de medici...
2 篇 washington univ ...
2 篇 the technical un...
2 篇 tsinghua univ de...

作者

8 篇 millane rp
7 篇 desco m.
7 篇 anastasio mark a...
5 篇 doerschuk peter ...
5 篇 lambert a
5 篇 fraser d
4 篇 kudo hiroyuki
4 篇 vaquero j. j.
4 篇 millane r. p.
4 篇 bouman ca
4 篇 fiddy michael a.
4 篇 bones philip j.
4 篇 millane rick p.
4 篇 tahtali murat
4 篇 abella m.
4 篇 zheng yili
4 篇 andrew j. reader
4 篇 reader andrew j.
4 篇 m. desco
4 篇 testorf markus e...

语言

621 篇 英文
1 篇 其他

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

共 622 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：

R2D2 image reconstruction WITH MODEL UNCERTAINTY QUANTIFICATION IN RADIO ASTRONOMY 32

R2D2 IMAGE RECONSTRUCTION WITH MODEL UNCERTAINTY QUANTIFICAT...

引用

32nd European Signal Processing conference (EUSIPCO)

作者： Aghabiglou, Amir Chu, Chung San Dabbech, Arwa Wiaux, Yves Heriot Watt Univ Inst Sensors Signals & Syst Edinburgh EH14 4AS Midlothian Scotland

ISBN: (纸本)9789464593617;9798331519773

The "Residual-to-Residual DNN series for high-Dynamic range imaging" (R2D2) approach was recently introduced for Radio-Interferometric (RI) imaging in astronomy. R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of Deep Neural Networks (DNNs) taking the previous iteration's image estimate and associated data residual as inputs. In this work, we investigate the robustness of the R2D2 image estimation process, by studying the uncertainty associated with its series of learned models. Adopting an ensemble averaging approach, multiple series can be trained, arising from different random DNN initializations of the training process at each iteration. The resulting multiple R2D2 instances can also be leveraged to generate "R2D2 samples", from which empirical mean and standard deviation endow the algorithm with a joint estimation and uncertainty quantification functionality. Focusing on RI imaging, and adopting a telescope-specific approach, multiple R2D2 instances were trained to encompass the most general observation setting of the Very Large Array (VLA). Simulations and real-data experiments confirm that: (i) R2D2's image estimation capability is superior to that of the state-of-the-art algorithms;(ii) its ultra-fast reconstruction capability (arising from series with only few DNNs) makes the computation of multiple reconstruction samples and of uncertainty maps practical even at large image dimension;(iii) it is characterized by a very low model uncertainty.

关键词： Computational methods Deep learning Astronomy image processing Aperture synthesis

来源：评论

学校读者我要写书评

暂无评论

Complete 3D Human reconstruction from a Single incomplete image

Complete 3D Human Reconstruction from a Single Incomplete Im...

引用

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

作者： Wang, Junying Yoon, Jae Shin Wang, Tuanfeng Y. Singh, Krishna Kumar Neumann, Ulrich Univ Southern Calif Los Angeles CA 90007 USA Adobe Res San Francisco CA USA

ISBN: (纸本)9798350301298

This paper presents a method to reconstruct a complete human geometry and texture from an image of a person with only partial body observed, e.g., a torso. The core challenge arises from the occlusion: there exists no pixel to reconstruct where many existing single-view human reconstruction methods are not designed to handle such invisible parts, leading to missing data in 3D. To address this challenge, we introduce a novel coarse-to-fine human reconstruction framework. For coarse reconstruction, explicit volumetric features are learned to generate a complete human geometry with 3D convolutional neural networks conditioned by a 3D body model and the style features from visible parts. An implicit network combines the learned 3D features with the high-quality surface normals enhanced from multiviews to produce fine local details, e.g., high-frequency wrinkles. Finally, we perform progressive texture inpainting to reconstruct a complete appearance of the person in a view-consistent way, which is not possible without the reconstruction of a complete geometry. In experiments, we demonstrate that our method can reconstruct high-quality 3D humans, which is robust to occlusion.

关键词： body gesture Humans: Face movement pose

来源：评论

学校读者我要写书评

暂无评论

reconstruction OF COMPLEX SCENE RADIATION FIELDS BASED ON image RESTORATION EQUATION 31

RECONSTRUCTION OF COMPLEX SCENE RADIATION FIELDS BASED ON IM...

引用

31st International conference on Nuclear Engineering (ICONE) - 24/7 Clean Nuclear Energy - Solution for Global Warming

作者： Hu, Hao Dong, Xinwen Xu, Yuhan Zhuang, Shuhan Fang, Sheng Tsinghua Univ Inst Nucl & New Energy Technol Beijing 100084 Peoples R China

ISBN: (纸本)9780791888285

In the context of nuclear safety production, the detailed information on three-dimensional radiation field dose rates plays a vital role in enhancing radiation protection and planning for radioactive areas. Research on inversion methods, especially under scenarios of sparse or irregular measurement points, has attracted significant attention. Currently, there are advances in inversion methods based on interpolation algorithms and neural network techniques. Interpolation algorithms are inversion methods capable of rapidly inverting and reconstructing the distribution of radiation field dose rates with limited radiation field data. These methods include grid data interpolation, finite element methods, inverse distance weighting, kriging, and radial basis function methods, and are the most widely used methods for the quick reconstruction of radiation fields at present. Based on the information of known sample points, these algorithms predict information at unsampled points by selecting appropriate analytical models to find suitable mapping relationships. They offer the advantages of simplicity and speed, but have poor capability in restoring the geometric shapes of multiple radiation sources and face significant challenges in the direct inversion and reconstruction of three-dimensional radiation fields. In some cases, sparse sampling data can lead to suboptimal inversion results. Neural network algorithms, renowned for their strong nonlinear mapping capabilities, can approximate complex functions by learning from extensive data sets. Once appropriately trained, neural networks can process incomplete or uncertain knowledge and predict outcomes based on limited data. These algorithms are commonly used in image restoration and inverse problem-solving. In recent radiation field dose rate inversion methods, neural network algorithms have gained attention due to their exceptional data fitting and predictive *** recent years, research has proposed an inversion met

关键词： Radiation Field reconstruction Restoration Equations Complex Scenes

来源：评论

学校读者我要写书评

暂无评论

Research on depth estimation and human body reconstruction effects in single-image scene reconstruction 2

Research on depth estimation and human body reconstruction e...

引用

2nd International conference on Big data, Computational Intelligence, and Applications, BDCIA 2024

作者： Zhou, Xiuyuan Li, Yuanzhen Zhu, Yaling Liu, Ruilin Yang, Lina Jing, Yongxia Lanzhou Institute of Technology Gansu Lanzhou730030 China Yunnan University Yunnan Kunming650091 China Qiongtai Normal University Hainan Haikou571100 China

ISBN: (纸本)9781510689053

With the rapid development of digital technology and deep learning, recovering 3D scene information and reconstructing human bodies from a single image has become a focal point of research in computer vision and computer graphics. This technology has also found widespread application in fields such as cultural relic restoration, autonomous driving, virtual reality, and medical image analysis. In this paper, we explore the challenges posed by the network's contextual perception abilities and the influence of loss functions, which can lead to issues like incomplete depth structures, depth drift, and texture copying. To overcome these obstacles, we propose refined methods that produce highly accurate and structurally sound depth estimates, effectively resolving problems such as texture copying and depth drift. Our methods demonstrate strong generalization capabilities in human depth estimation models, enabling precise depth estimation across various scenarios. © 2025 SPIE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

reconstruction of simulated VLBI data using the SARA method and random raw patches

Reconstruction of simulated VLBI data using the SARA method ...

引用

2023 International conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Atmaja, Ratri Dwi Suksmono, Andriyan Bayu Danudirdjo, Donny Hidayat, Taufiq Institut Teknologi Bandung School of Electrical Engineering and Informatics School of Electrical Engineering Telkom University Bandung Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Institut Teknologi Bandung Faculty of Mathematics and Natural Sciences Bandung Indonesia

ISBN: (纸本)9798350320954

VLBI (very long baseline interferometry) is used to image astronomical objects. However, the image quality decreases due to incomplete visibility measurements. The visibility is affected by the frequency, baseline length, measurement duration, and some telescopes used. A popular method that can solve this quality degradation problem in VLBI is SARA (sparsity averaging reweighted analysis). This study aims to increase the SARA performance with scoped in improving NRMSE (normalized root mean square error) and SNR (signal-to-noise ratio) on simulated VLBI data. We used random raw patch pairs from the SARA results to get a trained dictionary. In collecting the data for training, we used ten original images of the surrounding objects that we captured. Then we measured it using a VLBI sampling pattern, processed it using SARA, and applied the SARA results as a pre-reconstruction image. After that, we trained these ten pairs of the original and pre-reconstruction images. In reconstruction, we used the dictionary to test two simulated data and compare the results with the SARA. Finally, the results showed that the combination of SARA and random raw patches had a smaller NRMSE and a higher SNR than the SARA alone. © 2023 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

RepF-Net: Distortion-Aware Re-projection Fusion Network for Object Detection in Panorama image 16th

RepF-Net: Distortion-Aware Re-projection Fusion Network for ...

引用

16th Asian conference on Computer Vision (ACCV)

作者： Li, Mengfan Meng, Ming Zhou, Zhong Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Commun Univ China Sch Data Sci & Media Intelligence Beijing Peoples R China

ISBN: (纸本)9783031263125;9783031263132

Panorama image has a large 360 degrees field of view, providing rich contextual information for object detection, widely used in virtual reality, augmented reality, scene understanding, etc. However, existing methods for object detection on panorama image still have some problems. When 360 degrees content is converted to the projection plane, the geometric distortion brought by the projection model makes the neural network can not extract features efficiently, the objects at the boundary of the projection image are also incomplete. To solve these problems, in this paper, we propose a novel two-stage detection network, RepF-Net, comprehensively utilizing multiple distortion-aware convolution modules to deal with geometric distortion while performing effective features extraction, and using the non-maximum fusion algorithm to fuse the content of the detected object in the post-processing stage. Our proposed unified distortion-aware convolution modules can be used to deal with distortions from geometric transforms and projection models, and be used to solve the geometric distortion caused by equirectangular projection and stereographic projection in our network. Our proposed non-maximum fusion algorithm fuses the content of detected objects to deal with incomplete object content separated by the projection boundary. Experimental results show that our RepF-Net outperforms previous state-of-the-art methods by 6% on mAP. Based on RepF-Net, we present an implementation of 3D object detection and scene layout reconstruction application.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Medical image Classification through Deep Learning and Matrix Decomposition 31

Privacy-Preserving Medical Image Classification through Deep...

引用

31st Mediterranean conference on Control and Automation (MED)

作者： Popescu, Andreea Bianca Nita, Cosmin Ioan Taca, Ioana Antonia Vizitiu, Anamaria Itu, Lucian Mihai Transilvania Univ Brasov Brasov Romania Siemens SRL Brasov Romania

ISBN: (纸本)9798350315431

Deep learning (DL)-based solutions have been extensively researched in the medical domain in recent years, enhancing the efficacy of diagnosis, planning, and treatment. Since the usage of health-related data is strictly regulated, processing medical records outside the hospital environment for developing and using DL models demands robust data protection measures. At the same time, it can be challenging to guarantee that a DL solution delivers a minimum level of performance when being trained on secured data, without being specifically designed for the given task. Our approach uses singular value decomposition (SVD) and principal component analysis (PCA) to obfuscate the medical images before employing them in the DL analysis. The capability of DL algorithms to extract relevant information from secured data is assessed on a task of angiographic view classification based on obfuscated frames. The security level is probed by simulated artificial intelligence (AI)-based reconstruction attacks, considering two threat actors with different prior knowledge of the targeted data. The degree of privacy is quantitatively measured using similarity indices. Although a trade-off between privacy and accuracy should be considered, the proposed technique allows for training the angiographic view classifier exclusively on secured data with satisfactory performance and with no computational overhead, model adaptation, or hyperparameter tuning. While the obfuscated medical image content is well protected against human perception, the hypothetical reconstruction attack proved that it is also difficult to recover the complete information of the original frames.

关键词： image obfuscation singular value decomposition principal component analysis deep learning medical imaging

来源：评论

学校读者我要写书评

暂无评论

Advanced compressed sensing photoacoustic imaging techniques using iteratively enhanced L1 regularization

Advanced compressed sensing photoacoustic imaging techniques...

引用

2024 International conference on Computer Application and Information Security, ICCAIS 2024

作者： Wang, Lu Yao, Yaru Hao, Ziqi Hu, Xiaolong School of Mathematical Sciences Liaocheng University Shandong Liaocheng252000 China

ISBN: (纸本)9781510689312

Photoacoustic imaging (PAI) offers significant advantages but faces challenges in data processing and reconstruction. Sparse reconstruction techniques and compressed sensing theory have advanced its development. Regularization methods are commonly used to address the ill-posed problem of reconstructing PAI images from incomplete and noisy experimental data. While the L1-norm efficiently promotes sparsity in regularization methods, it often results in undesirable edge smoothing, which can degrade image quality. To address this limitation, this paper employs the Modified Iterative Reweighted L1 (MIRL1) regularization method, which aims to enhance sparsity while preserving critical image features such as edges. Experiments with simulated signals containing Gaussian noise show that MIRL1 outperforms traditional L1-norm-based SPGL1 and L0-norm-based SL0 algorithms in terms of image quality and noise robustness. MIRL1 enhances image clarity and maintains strong resistance to noise, providing superior image recovery results. This finding is significant for the development of sparse sampling PAI imaging algorithms. © The Authors.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

9th International Skin Imaging Collaboration Workshop, ISIC 2024, 7th International Workshop on Interpretability of Machine Intelligence in Medical image Computing, iMIMIC 2024, Embodied AI and Robotics for HealTHcare Workshop, EARTH 2024 and 5th MICCAI Workshop on Distributed, Collaborative and Federated Learning, DeCaF 2024 held at 27th International conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2024

9th International Skin Imaging Collaboration Workshop, ISIC ...

引用

9th International Skin Imaging Collaboration Workshop, ISIC 2024, 7th International Workshop on Interpretability of Machine Intelligence in Medical image Computing, iMIMIC 2024, Embodied AI and Robotics for HealTHcare Workshop, EARTH 2024 and 5th MICCAI Workshop on Distributed, Collaborative and Federated Learning, DeCaF 2024 held at 27th International conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2024

ISBN: (纸本)9783031776090

The proceedings contain 23 papers. The special focus in this conference is on Skin Imaging Collaboration, Interpretability of Machine Intelligence in Medical image Computing, Embodied AI and Robotics for HealTHcare Workshop and MICCAI Workshop on Distributed, Collaborative and Federated Learning. The topics include: DeCaF 2024 Preface;i2M2Net: Inter/Intra-modal Feature Masking Self-distillation for incomplete Multimodal Skin Lesion Diagnosis;from Majority to Minority: A Diffusion-Based Augmentation for Underrepresented Groups in Skin Lesion Analysis;segmentation Style Discovery: Application to Skin Lesion images;a Vision Transformer with Adaptive Cross-image and Cross-Resolution Attention;lesion Elevation Prediction from Skin images Improves Diagnosis;DWARF: Disease-Weighted Network for Attention Map Refinement;PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans;Detecting Unforeseen data Properties with Diffusion Autoencoder Embeddings Using Spine MRI data;interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis;TextCAVs: Debugging Vision Models Using Text;evaluating Visual Explanations of Attention Maps for Transformer-Based Medical Imaging;Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI;EndoGS: Deformable Endoscopic Tissues reconstruction with Gaussian Splatting;VISAGE: Video Synthesis Using Action Graphs for Surgery;a Review of 3D reconstruction Techniques for Deformable Tissues in Robotic Surgery;SurgTrack: CAD-Free 3D Tracking of Real-World Surgical Instruments;MUTUAL: Towards Holistic Sensing and Inference in the Operating Room;Complex-Valued Federated Learning with Differential Privacy and MRI Applications;enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications;federated Impression for Learning with Distributed Heterogeneous data;A Federated Learning-Friendly Approach for Parameter-Efficient Fine-Tuning of SAM in 3D Segmentation;probing the Effic

关键词：

来源：评论

学校读者我要写书评

暂无评论

Masked image Modeling Advances 3D Medical image Analysis 23

Masked Image Modeling Advances 3D Medical Image Analysis

引用

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

作者： Chen, Zekai Agarwal, Devansh Aggarwal, Kshitij Safta, Wiem Balan, Mariann Micsinai Brown, Kevin Bristol Myers Squibb New York NY 10016 USA

ISBN: (纸本)9781665493468

Recently, masked image modeling (MIM) has gained considerable attention due to its ability to learn from vast amounts of unlabeled data and has been demonstrated to be effective on various vision tasks involving natural images. Meanwhile, the potential of self-supervised learning in modeling 3D medical images is anticipated to be immense due to the high quantities of unlabeled images and the expense and difficulty of quality labels. However, MIM's applicability to medical images remains uncertain. In this paper, we demonstrate that masked image modeling approaches can also advance 3D medical image analysis in addition to natural images. We study how masked image modeling strategies leverage performance from the viewpoints of 3D medical image segmentation as a representative downstream task: i) when compared to naive contrastive learning, masked image modeling approaches accelerate the convergence of supervised training even faster (1.40x) and ultimately produce a higher dice score;ii) predicting raw voxel values with a high masking ratio and a relatively smaller patch size is non-trivial self-supervised pretext-task for medical images modeling;iii) a lightweight decoder or projection head design for reconstruction is robust for masked image modeling on 3D medical images which speeds up training and reduce cost;iv) finally, we also investigate the effectiveness of MIM methods under different practical scenarios where different image resolutions and labeled data ratios are applied. Anonymized codes are available at https://***/ZEKAICHEN/MIM-Med3D.

关键词： Training Solid modeling Analytical models image segmentation Three-dimensional displays Self-supervised learning Predictive models

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63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：