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

13,834 篇 会议
850 篇 期刊文献
29 篇 学位论文
9 册 图书
3 篇 专利

馆藏范围

14,724 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,768 篇 工学
- 4,049 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

7,671 篇 image reconstruc...
1,030 篇 cameras
871 篇 three-dimensiona...
785 篇 computed tomogra...
714 篇 image segmentati...
620 篇 reconstruction a...
606 篇 positron emissio...
561 篇 surface reconstr...
547 篇 shape
516 篇 image resolution
463 篇 training
462 篇 magnetic resonan...
455 篇 data mining
375 篇 imaging phantoms
363 篇 detectors
356 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...
21 篇 department of en...
20 篇 univ chinese aca...
17 篇 washington univ ...
17 篇 univ chicago dep...
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...
14 篇 peng cheng lab p...
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
19 篇 g.t. gullberg
18 篇 yuxiang xing
18 篇 j.a. fessler
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

14,451 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 14725 条记录，以下是191-200 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：

Integration of Depth Normal Consistency and Depth Map Refinement for MVS reconstruction 17th

Integration of Depth Normal Consistency and Depth Map Refine...

引用

17th Chinese conference on image and Graphics Technologies and Applications, IGTA 2022

作者： Yang, Lifang Bai, Zhengyao Liu, Huijie School of Information Science and Engineering Yunnan University Kunming650500 China

ISBN: (纸本)9789811950957

To address the problem of incomplete Multi-view Stereo (MVS) reconstruction, the initial depth and loss function of the depth residual iterative network are investigated, and a new multi-view stereo reconstruction network integrating depth normal consistency and depth map thinning is presented. Firstly, downsampling the input image to create an image pyramid and extracting a feature map from the image pyramid;Then, constructing a cost volume from the 2D feature map, adding the depth normal consistency to the initial cost volume to optimize the depth map. On the DTU data set, the network is tested and compared to traditional reconstruction approaches and MVS networks based on deep learning. The experimental results show that the proposed MVS reconstruction network was produced the better results in completeness and increased the quality of MVS reconstruction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Transformer Encoder-Decoder Mask reconstruction in Industrial image Anomaly Localization 6

Transformer Encoder-Decoder Mask Reconstruction in Industria...

引用

6th International conference on Communications, Information System and Computer Engineering, CISCE 2024

作者： Luo, Xuhong Liu, Yongchun Chu, Guoming Sichuan University of Science and Engineering Yibin China Artificial Intelligence Key Laboratory of Sichuan Province Yibin China

ISBN: (纸本)9798350353174

Acquiring a substantial amount of high-quality data for industrial image detection poses significant challenges in the field of computer vision. The imbalance between normal and anomalous samples, where normal samples far outnumber anomalies, complicates the training of traditional supervised detection methods, limiting their ability to exhibit robust detection performance on industrial image datasets. Unsupervised anomaly detection methods based on image reconstruction train exclusively on normal samples. These methods employ encoders and decoders to map and reconstruct images, assessing deviations from the distribution by evaluating unseen instances of both normal and anomalous cases. We propose a method for anomaly localization in industrial images using Transformer Encoder-Decoder Mask reconstruction. The self-attention mechanism of the Transformer enables better attention to different positions within the entire input image in both the encoder and decoder, capturing long-range dependencies in the image and more accurately learning crucial features. Additionally, to train a stable and efficient image reconstruction network, we introduce a block-wise reconstruction approach involving masking the input images. To validate the algorithm's generality in industrial images, experiments are conducted on the MVTecAD and a custom crankshaft bearing datasets. Experimental results demonstrate the algorithm's excellent detection performance, surpassing previous state-of-the-art methods and confirming its effectiveness. © 2024 IEEE.

关键词： Crankshafts

来源：评论

学校读者我要写书评

暂无评论

Edge-based Denoising image Compression 32

Edge-based Denoising Image Compression

引用

32nd European Signal Processing conference (EUSIPCO)

作者： Morita, Ryugo Nishimura, Hitoshi Watanabe, Ko Dengel, Andreas Zhou, Jinjia Hosei Univ Fac Sci & Engn Tokyo Japan KDDI Res Inc Saitama Japan RPTU Kaiserslautern Landau & DFKI GmbH Kaiserslautern Germany

ISBN: (纸本)9789464593617;9798331519773

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address these issues, we propose a novel compression model that incorporates a denoising step with diffusion models, significantly enhancing image reconstruction fidelity by sub-information(e.g., edge and depth) from leveraging latent space. Empirical experiments demonstrate that our model achieves superior or comparable results in terms of image quality and compression efficiency when measured against the existing models. Notably, our model excels in scenarios of partial image loss or excessive noise by introducing an edge estimation network to preserve the integrity of reconstructed images, offering a robust solution to the current limitations of image compression.

关键词： image compression diffusion model inpainting

来源：评论

学校读者我要写书评

暂无评论

ANIM: Accurate Neural Implicit Model for Human reconstruction from a single RGB-D image

ANIM: Accurate Neural Implicit Model for Human Reconstructio...

引用

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

作者： Pesavento, Marco Xu, Yuanlu Sarafianos, Nikolaos Maier, Robert Wang, Ziyan Yao, Chun-Han Volino, Marco Boyer, Edmond Hilton, Adrian Tung, Tony Univ Surrey CVSSP Guildford Surrey England UC Merced Merced CA USA Meta Real Labs Sausalito CA USA

ISBN: (纸本)9798350353013;9798350353006

Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the re-constructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addi-tion, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstruction from real-world human capture. https://***/ANIM/

关键词： 3D Digital Avatars 3D Human reconstruction Computer Vision Neural Implicit Model

来源：评论

学校读者我要写书评

暂无评论

STFP: Automatic Video Occlusion Detection and reconstruction via Spatial-Temporal Feature Propagation 2

STFP: Automatic Video Occlusion Detection and Reconstruction...

引用

2nd International conference on Algorithm, image Processing and Machine Vision, AIPMV 2024

作者： Zheng, Yanhan Hubin Middle School Xiamen China

ISBN: (纸本)9798350390254

With the maturity of computer networks and camera equipment, video data in the Internet is growing exponentially. However, video resource usually exhibits hole-like missing or occlusion, which may affect the visual content presentation. Occlusion detection and reconstruction is an effective way for general missing problem, which aims to recognize all the missing areas and fill them with appropriate pixels to complete the reconstruction task. The technology is still challenging due to the difficulties of high computational complexity, complex occluded shapes and high requirement on the spatial-temporal consistency between sequential video frames. In this paper, we propose a novel method called STFP to automatically detect the occlusions or missing regions in the video frames and complete the corresponding content reconstruction based on spatial-temporal feature propagation. Specifically, we make full reference to the feature values of adjacent pixels in temporal and spatial frames to estimate coarse pixels in the occluded regions, and then we formulate the occlusion reconstruction as a feature-interpolated optimization problem by filling and propagating the best-match pixels from the candidate content. Experimental results indicate that the proposed STFP can produce competitive results, both in objective and subjective quality. It outperforms competing method significantly with an average PSNR and SSIM as high as 39.60 and 0.92, respectively. © 2024 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Flow reconstruction of Single-Phase Planar Jet from Sparse Temperature Measurements

Flow Reconstruction of Single-Phase Planar Jet from Sparse T...

引用

Saudi International conference on Nuclear Power Engineering (SCOPE)

作者： Wang, Xicheng Chan, YiMeng Wong, KinWing Grishchenko, Dmitry Kudinov, Pavel KTH Royal Inst Technol Stockholm Sweden

ISBN: (纸本)9783031643613;9783031643620

Measurement of the velocity field in thermal-hydraulic experiments is of great importance for phenomena interpretation and code validation. Direct measurement by means of Particle image Velocimetry (PIV) is challenging in some multiphase's tests where the measurement system would be strongly affected by the phase interaction. A typical example can refer to the test with steam injection into a water pool where the rapid collapse of bubbles and significant temperature gradient makes it impossible to obtain main flow information in a relatively large steam flux. The goal of this work is to investigate the capability of the use of machine learning for the flow reconstruction of the jet induced by steam condensation from sparse temperature measurement with ThermoCouples (TCs). Two frameworks of (i) 'FDD' using pure data-driven modeling and (ii) 'FPINN' combining data-driven and Physics-Informed Neural Networks (PINN) are proposed and investigated. The frameworks are applied to a single-phase turbulent planar jet with data generated by CFD simulations.

关键词： data-driven Flow reconstruction Physics-informed neural network Sparse measurement

来源：评论

学校读者我要写书评

暂无评论

Dynamic image reconstruction in Electrical Resistance Tomography Using LVB-KF Algorithm

Dynamic Image Reconstruction in Electrical Resistance Tomogr...

引用

IEEE International Instrumentation and Measurement Technology conference (I2MTC) - Rising Above Covid-19

作者： Du, Yundan Liang, Guanghui Dong, Feng Tianjin Univ Sch Elect & Informat Engn Tianjin Key Lab Proc Measurement & Control Tianjin Peoples R China

ISBN: (纸本)9781665453837

A dynamic image reconstruction method considering the spatiotemporal evolution characteristics of time-varying distribution is proposed for electrical resistance tomography (ERT). The dynamic inversion problem of ERT is constructed by state-space modeling method with state evolution and observation update equations, and is solved by Kalman filter. To accurately describe the state evolution process of time-vary parameters, the latent variable based statistical modeling method is proposed to construct the state evolution equation. The potential characteristics of the state parameters in the dynamic change process are fully explored and characterized from the data with multivariate regression methods. Numerical and experimental results show that the proposed dynamic image reconstruction method can improve the imaging quality of ERT for time-varying distribution.

关键词： dynamic image reconstruction latent variable Kalman filter state-space modeling electrical resistance tomography

来源：评论

学校读者我要写书评

暂无评论

Deep Insights into 3D Face reconstruction from Blurred 2D Inputs: A Comprehensive Framework 2

Deep Insights into 3D Face Reconstruction from Blurred 2D In...

引用

2nd IEEE International conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Pastay, Sphurti Joseph, Alwin Kumar, Ramesh Christ Deemed to Be University Department of Data Science Lavasa Pune India

ISBN: (纸本)9798350384277

This framework outlines a multi-stage methodology for 3D face reconstruction driven by advancements in deep learning. The process involves image preprocessing with deblurring techniques and subsequent feature extraction using CNNs alongside traditional methods. Deep learning adapts to diverse image challenges, ensuring accuracy in 3D reconstructions. In medical imaging, the proficiency of 3D CNNs and GANs shines in extracting structures from MRI and CT scans. Post-processing steps encompass mesh smoothing and texture mapping for enhanced visual quality. Evaluation metrics (MAE, RMSE, IoU) guarantee the precision of depth estimations. Applications of deep learning span across CNNs, 3DMM, GANs, and networks for landmark detection and dense correspondence. Challenges include optimizing eye reconstruction, expanding applications, and addressing concerns related to data quality, privacy, and hardware requirements. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent optimization image recognition algorithm in computer-aided 3D modeling 4

Research on intelligent optimization image recognition algor...

引用

4th IEEE International conference on data Science and Computer Application, ICDSCA 2024

作者： Xu, Zhihua Xu, Chao School of Design and Art Jingdezhen Ceramic University Jingdezhen China School of Design Jiangnan University Wuxi China

ISBN: (纸本)9798350368239

How to generate and recognize 3D models efficiently and accurately is a key problem in image recognition. To solve this problem, Cubes Cycle Particle Swarm (CCPS), a new method combining CycleGAN, Marching Cubes (MC) and Particle Swarm Optimization (PSO), is proposed in this paper. CCPS method can capture key features in the image to achieve the conversion from 2D image to 3D model through CycleGAN, and Marching Cubes algorithm is used to generate smooth 3D surface according to voxel data. At the same time, PSO is used for intelligent optimization, and the optimal solution is found through particle swarm collaborative search, so as to ensure high reconstruction accuracy and improve the robustness and recognition efficiency of the model. Finally, through the comparison experiment and analysis with traditional image recognition algorithms, the experimental results show that CCPS method has significant advantages in improving image recognition accuracy, image recognition effect and enhancing system robustness. Especially in complex model reconstruction, CCPS method can generate and identify 3D models more accurately, and reduce the error rate and missing rate. This fully verifies the feasibility and effectiveness of this architecture in intelligent optimization of image recognition algorithm in computer-aided 3D modeling. ©2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

FedAutoMRI: Federated Neural Architecture Search for MR image reconstruction 26th

FedAutoMRI: Federated Neural Architecture Search for MR Imag...

引用

26th International conference on Medical image Computing and Computer-Assisted Intervention (MICCAI) / 8th ISIC Workshop / 1st Care-AI Workshop / 1st MedAGI Workshop / 4th DeCaF Workshop

作者： Wu, Ruoyou Li, Cheng Zou, Juan Wang, Shanshan Chinese Acad Sci Shenzhen Inst Adv Technol Paul C Lauterbur Res Ctr Biomed Imaging Shenzhen 518055 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Xiangtan Univ Sch Phys & Optoelect Xiangtan 411105 Peoples R China

ISBN: (纸本)9783031474002;9783031474019

Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions. Federated learning, a distributed collaborative training scheme, can utilize multi-center data without the need to transfer data between institutions. However, existing federated learning MR image reconstruction methods rely on manually designed models which have extensive parameters and suffer from performance degradation when facing heterogeneous data distributions. To this end, this paper proposes a novel FederAted neUral archiTecture search approach fOr MR image reconstruction (FedAutoMRI). The proposed method utilizes differentiable architecture search to automatically find the optimal network architecture. In addition, an exponential moving average method is introduced to improve the robustness of the client model to address the data heterogeneity issue. To the best of our knowledge, this is the first work to use federated neural architecture search for MR image reconstruction. Experimental results demonstrate that our proposed FedAutoMRI can achieve promising performances while utilizing a lightweight model with only a small number of model parameters compared to the classical federated learning methods.

关键词： Magnetic resonance imaging (MRI) Federated learning Neural architecture search

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 << < 16 17 18 19 20 21 22 23 24 25 > >>

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：