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

13,890 篇 会议
856 篇 期刊文献
31 册 图书
29 篇 学位论文
3 篇 专利

馆藏范围

14,808 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,807 篇 工学
- 4,071 篇 计算机科学与技术...
- 2,274 篇 电气工程
- 2,009 篇 软件工程
- 1,274 篇 生物医学工程（可授...
- 1,054 篇 信息与通信工程
- 991 篇 光学工程
- 659 篇 控制科学与工程
- 640 篇 仪器科学与技术
- 626 篇 核科学与技术
- 571 篇 机械工程
- 440 篇 电子科学与技术（可...
- 401 篇 生物工程
- 238 篇 测绘科学与技术
- 156 篇 材料科学与工程（可...
- 116 篇 航空宇航科学与技...
- 113 篇 建筑学
- 113 篇 土木工程
3,763 篇 理学
- 2,655 篇 物理学
- 1,105 篇 数学
- 469 篇 生物学
- 316 篇 统计学（可授理学、...
- 184 篇 化学
- 165 篇 系统科学
2,631 篇 医学
- 1,608 篇 临床医学
- 1,261 篇 特种医学
- 265 篇 基础医学(可授医学...
- 114 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

7,686 篇 image reconstruc...
1,032 篇 cameras
874 篇 three-dimensiona...
784 篇 computed tomogra...
714 篇 image segmentati...
621 篇 reconstruction a...
611 篇 positron emissio...
561 篇 surface reconstr...
547 篇 shape
516 篇 image resolution
466 篇 training
464 篇 magnetic resonan...
456 篇 data mining
375 篇 imaging phantoms
363 篇 detectors
359 篇 deep learning
355 篇 image coding
348 篇 solid modeling
333 篇 attenuation
333 篇 compressed sensi...

机构

91 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...
18 篇 univ chicago dep...
17 篇 washington univ ...
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

84 篇 pan xiaochuan
33 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

14,473 篇 英文
204 篇 其他
122 篇 中文
11 篇 土耳其文
2 篇 俄文
1 篇 德文
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 14809 条记录，以下是411-420 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：

Visualization of Irregular Tree Canopy Centerline data from a Depth Camera Based on an Optimized Spatial Straight-Line Fitting 40th

Visualization of Irregular Tree Canopy Centerline Data from ...

引用

40th Computer Graphics International conference (CGI)

作者： Gu, Hairong Wang, Jiale Hu, Yanhui Wang, Jixiang Sun, Lishun Ahamed, Mostak Changan Univ Xian Shaanxi Peoples R China

ISBN: (纸本)9783031500718;9783031500725

We propose a new method to visualize the centerline of a single tree canopy based on a depth camera. Firstly, the depth camera captures the image of the target tree to obtain the 3D point cloud data, which is filtered and denoised. Then, we used the Poisson surface reconstruction method to reconstruct the 3D spatial surface of the point cloud data to restore the real scene accurately. In addition, we used Random Sampling Consensus (RANSAC) and Least Square Circle (LSC) in MATLAB software to fit circles to the 3D point cloud. We proposed a new spatial straight-line fitting method to visualize the centerline of the tree crown. The method has the advantage of no error in the spatial scattering Z-coordinate, and the fitted straight line is perpendicular to the xoy plane. The new method produces a smaller root mean square error (RMSE) than the traditional spatial straight line fitting method. This method can be effectively applied to practical applications such as tree crown pruning, providing accurate positional information for the positioning of tools during the pruning process. Ultimately, the pruning time can be shortened, and the accuracy of the pruning process can be improved.

关键词： 3D reconstruction Point cloud Poisson surface reconstruction Circle fitting Spatial straight-line fitting

来源：评论

学校读者我要写书评

暂无评论

DIRE for Diffusion-Generated image Detection

DIRE for Diffusion-Generated Image Detection

引用

IEEE/CVF International conference on Computer Vision (ICCV)

作者： Wang, Zhendong Bao, Jianmin Zhou, Wengang Wang, Weilun Hu, Hezhen Chen, Hong Li, Houqiang Univ Sci & Technol China EEIS Dept CAS Key Lab GIPAS Langfang Peoples R China Microsoft Res Asia Beijing Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China Merchants Union Consumer Finance Co Beijing Peoples R China

ISBN: (纸本)9798350307184

Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from diffusiongenerated images. We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data. To address this issue, we propose a novel image representation called DIffusion reconstruction Error (DIRE), which measures the error between an input image and its reconstruction counterpart by a pre-trained diffusion model. We observe that diffusion-generated images can be approximately reconstructed by a diffusion model while real images cannot. It provides a hint that DIRE can serve as a bridge to distinguish generated and real images. DIRE provides an effective way to detect images generated by most diffusion models, and it is general for detecting generated images from unseen diffusion models and robust to various perturbations. Furthermore, we establish a comprehensive diffusion-generated benchmark including images generated by various diffusion models to evaluate the performance of diffusion-generated image detectors. Extensive experiments on our collected benchmark demonstrate that DIRE exhibits superiority over previous generated-image detectors.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

GAN based ROI conditioned Synthesis of Medical image for data Augmentation

GAN based ROI conditioned Synthesis of Medical Image for Dat...

引用

conference on Medical Imaging - image Processing

作者： Kim, Yisak Lee, Jong Hyuk Kim, Changi Jin, Kwang Nam Park, Chang Min Seoul Natl Univ Grad Sch Interdisciplinary Program Bioengn 103 Daehak Ro Seoul South Korea Seoul Natl Univ Grad Sch Integrated Major Innovat Med Sci 103 Daehak Ro Seoul South Korea Seoul Natl Univ Hosp Dept Radiol 101 Daehak Ro Seoul South Korea Seoul Metropolitan Govt Seoul Natl Univ Boramae M Dept Radiol 20 Boramae Ro 5 Gil Seoul South Korea Seoul Natl Univ Coll Med Dept Radiol 103 Daehak Ro Seoul South Korea

ISBN: (纸本)9781510660335;9781510660342

Synthetic data is considered to be a promising solution for data privacy and scarcity. Some studies have shown that synthetic data generated from a simple GAN-based model enables privacy-preserving data sharing and data augmentation also in the medical imaging field. However, there are some limitations in applying this approach to real world situations: 1) Since generative models needs large amount of data to be trained, it is hard to be applied for small data situation. 2) Even after successfully training generative models, it is hard to guarantee which class the synthesized data corresponds to, especially for non-conditional generative models, so it needs to be re-labeled. Here, we propose GAN based ROI conditioned synthesis of medical image for data augmentation. We used StyleGAN2 to learn the distribution of CXR and Bayesian image reconstruction for ROI-conditioned synthesis from the distribution. In the 4-class classification of CXRs showing normal, pneumonia, pleural effusion, and pneumothorax, using synthetic data for data sharing showed comparable performance to centralized learning, slightly better in terms of AUROC. Also, using synthetic data for augmentation, the accuracy and AUROC showed up to 6.5% and 8.9% increases, respectively.

关键词： Synthetic data Augmentation Generative Model Bayesian reconstruction Chest X-ray

来源：评论

学校读者我要写书评

暂无评论

A BREGMAN MAJORIZATION-MINIMIZATION FRAMEWORK FOR PET image reconstruction 29

A BREGMAN MAJORIZATION-MINIMIZATION FRAMEWORK FOR PET IMAGE ...

引用

IEEE International conference on image Processing (ICIP)

作者： Rossignol, Claire Sureau, Florent Chouzenoux, Emilie Comtat, Claude Pesquet, Jean-Christophe Univ Paris Saclay CentraleSupelec CVN INRIA Gif Sur Yvette France Univ Paris Saclay CNRS BioMaps CEASHFJ Gif Sur Yvette France

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Positron emission tomography (PET) is a quantitative imaging modality widely used in oncology, neurology, and pharmacology. The data acquired by a PET scanner correspond to projections of the concentration activity, assumed to follow a Poisson distribution. The reconstruction of images from tomographic projections corrupted by Poisson noise is a challenging ill-posed large-scale inverse problem. Several available solvers use the majorization-minimization (MM) principle, though relying on various construction strategies with a lack of unifying framework. This work fills the gap by introducing the concept of Bregman majorization. This leads to a unified view of MM-based methods for image reconstruction in the presence of Poisson noise. from this general approach, we exhibit three algorithmic solutions and compare their computational efficiency on a problem of dynamic PET image reconstruction, either using GPU or CPU processing.

关键词： PET image reconstruction Poisson noise Majorization-Minimisation Bregman divergence GPU implementation

来源：评论

学校读者我要写书评

暂无评论

Occluded image reconstruction under Single Sample Condition Using Diffusion Models Aiming Facial Recognition 9

Occluded Image Reconstruction under Single Sample Condition ...

引用

9th International conference on image, Vision and Computing, ICIVC 2024

作者： da Silva Alvez, Uendel Diego Leher, Quefren Oliveira Bezerra, Emili Silva Mafalda, Salomão Paixão, Thuanne Alvarez, Ana Beatriz University of Acre UFAC Rio Branco Brazil

ISBN: (纸本)9798350385991

In view of the indisputable power of the inpainting technique for filling out visual information in images, this paper presents an approach for reconstructing occluded images from a single sample using the inpainting technique based on a diffusion model for facial recognition. The experiments were carried out in five different scenarios, each with an assigned occlusion percentage ranging from 35% to 50%. The face recognition is based on the VGG Face Descriptor and its behavior is evaluated using cosine similarity and Euclidean distance values. The experimental results indicate that the approach can effectively reconstruct the information in a facial image for subsequent recognition. For all the scenarios tested, the cosine similarity and Euclidean distance values of the reconstructed images are below the established thresholds, 0.40 and 95, respectively, indicating effectiveness in the process. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

3D Shape Estimation from RGB data Using 2.5D Features and Deep Learning 4

3D Shape Estimation from RGB Data Using 2.5D Features and De...

引用

4th International conference on Advancements in Computational Sciences, ICACS 2023

作者： Ashfaq, Hamid Jalal, Ahmad Air University Dept. of Creative Technologies Islamabad Pakistan

ISBN: (纸本)9781665463775

Creation of 3D models from a single RGB image is challenging problem in image processing these days, as the technology is in its early development stage. However, the demands for 3D technology and 3D reconstruction have been rapidly increasing nowadays. The traditional approach of computer graphics is to create a geometric model in 3D and try to reproduce it onto a 2D image with rendering. The major aim of the study is to create 3D models from 2D RGB image using machine learning techniques to be less computationally complex as compared to any deep learning algorithm. The proposed model has been based on three different modules such as: 2.5D features extraction, mesh generation, and 3D boundary detection. The ShapeNet dataset has been used for comparison. The testing results has shown an accuracy of 90.77 % in the plane class, 85.72% in the chair class, and 72.14% in the automobile class. The proposed model could be applicable to problems where reconstruction of 3D models is required such as: variations in geometric scale, mix of textured, uniformly colored, and reflective surfaces. © 2023 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Investigating the impact of data consistency in task-informed learned image reconstruction method

Investigating the impact of data consistency in task-informe...

引用

2025 conference on Medical Imaging

作者： Shao, Zhuchen Lu, Changjie Li, Kaiyan Li, Hua Anastasio, Mark A. Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA Univ Illinois Dept Bioengn Urbana IL 61801 USA Washington Univ St Louis Dept Radiat Oncol St Louis MO 63130 USA

ISBN: (纸本)9781510685963;9781510685970

Various supervised learning-based medical image reconstruction methods have been developed with the goal of improving image quality (IQ). These methods typically use loss functions that minimize pixel-level differences between the reconstructed and high-quality target images. While they may seemingly perform well based on traditional image quality metrics such as mean squared error, they do not consistently improve objective IQ measures based on diagnostic task performance. This work introduces a task-informed learned image reconstruction method. To establish the method, a measure of signal detection performance is incorporated in a hybrid loss function that is used for training. The proposed method is inspired by null space learning, and a task-informed data-consistent (DC) U-Net is utilized to estimate a null space component of the object that enhances task performance, while ensuring that the measurable component is stably reconstructed using a regularized pseudo-inverse operator. The impact of changing the specified task or observer at inference time to be different from that employed for model training, a phenomenon we refer to as "task-shift" or "observer-shift", respectively, was also investigated.

关键词： Task-informed image reconstruction objective image quality assessment

来源：评论

学校读者我要写书评

暂无评论

DDEM: Deepfake Detection Enhanced Model for image Forgery Detection Combat Academic Misconduct 11

DDEM: Deepfake Detection Enhanced Model for Image Forgery De...

引用

11th IEEE International conference on Behavioural and Social Computing, BESC 2024

作者： Ding, Junpeng Liu, Jianhua Shi, Jiayi Hu, Xinyang Qiao, Xiaodong Haihong, E. School of Computer Science Beijing University of Posts and Telecommunications Beijing China Beijing Wanfang Data Co. Ltd. Beijing China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9798331531904

image forgery, as a classic form of academic mis-conduct, has garnered increasing interest from researchers in the field of research integrity. Concurrently, automated detection and localization methods for image forgery have been making steady progress. However, the rapid advancement of image generation and image inpainting methods based on diffusion models presents new threats to the task of image forgery detection. Existing approaches are finding it difficult to identify forgery images that have been spliced by deepfake images and authentic photographs. To tackle this challenge, we propose the Deepfake Detection Enhanced Model (DDEM), which learns image features from both the RGB domain and frequency domain using the HRNet backbone. Furthermore, we introduce diffusion reconstruction error to enhance deepfake detection capabilities in our model. Fi-nally, we conduct experiments on public datasets and a self-made dataset generated by the image inpainting model, demonstrating that our proposed method outperforms the state-of-the-art in terms of image tampering detection and localization. © 2024 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion

What Decreases Editing Capability? Domain-Specific Hybrid Re...

引用

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

作者： Cao, Pu Yang, Lu Liu, Dongxv Yang, Xiaoya Huang, Tianrui Song, Qing Beijing Univ Posts & Telecommun Beijing Peoples R China Metavatar Beijing Peoples R China

ISBN: (纸本)9798350318920;9798350318937

Recently, inversion methods have been exploring the incorporation of additional high-rate information from pretrained generators (such as weights or intermediate features) to improve the refinement of inversion and editing results from embedded latent codes. While such techniques have shown reasonable improvements in reconstruction, they often lead to a decrease in editing capability, especially when dealing with complex images that contain occlusions, detailed backgrounds, and artifacts. To address this problem, we propose a novel refinement mechanism called Domain-Specific Hybrid Refinement (DHR), which draws on the advantages and disadvantages of two mainstream refinement techniques. We find that the weight modulation can gain favorable editing results but is vulnerable to these complex image areas and feature modulation is efficient at reconstructing. Hence, we divide the image into two domains and process them with these two methods separately. We first propose a Domain-Specific Segmentation module to automatically segment images into in-domain and out-of-domain parts according to their invertibility and editability without additional data annotation, where our hybrid refinement process aims to maintain the editing capability for in-domain areas and improve fidelity for both of them. We achieve this through Hybrid Modulation Refinement, which respectively refines these two domains by weight modulation and feature modulation. Our proposed method is compatible with all latent code embedding methods. Extension experiments demonstrate that our approach achieves state-of-the-art in real image inversion and editing. Code is available at https://***/caopulan/Domain-Specific_Hybrid_Refinement_Inversion.

关键词： 3D Algorithms Algorithms Computational photography etc Generative models for image image and video synthesis video

来源：评论

学校读者我要写书评

暂无评论

German conference on Medical image Computing, 2025

German Conference on Medical Image Computing, 2025

引用

German conference on Medical image Computing, 2025

ISBN: (纸本)9783658474218

The proceedings contain 79 papers. The special focus in this conference is on Medical image Computing. The topics include: Keynote: Autonomous Surgery from a Surgeon’s Perspective;image Registration for a Dynamic Breathing Model;surrogate-based Respiratory Motion Estimation using Physics-enhanced Implicit Neural Representations;comparison of Framewise Video Classification in Laryngoscopies;real-time Fiberscopic image Improvement for Automated Lesion Detection in the Urinary Bladder;robust Statistical Shape Modelling with Implicit Neural Representations;iRBSM: A Deep Implicit 3D Breast Shape Model;Diffusion Models for Conditional Brain Tumor MRI Generation with Tumor-induced Deformations;LLM-driven Baselines for Medical image Segmentation: A Systematic Analysis;efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models;is Self-supervision Enough?: Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification;look, No Convs! Permutation- and Rotation-invariance for MetaFormers;evaluating the Fidelity of Explanations for Convolutional Neural Networks in Alzheimer’s Disease Detection;real-time Landmark Guidance for Radial Head Localization in Ultrasound Imaging;ultrasound-based 3D reconstruction of Residual Limbs using Electromagnetic Tracking;autocalibration for 3D Ultrasound reconstruction in Infant Hip Dysplasia Screening;Weakly Supervised Segmentation of Hyper-reflective Foci with Compact Convolutional Transformers and SAM 2;Bridging Gaps in Retinal Imaging: Fusing OCT and SLO Information with Implicit Neural Representations for Improved Interpolation and Segmentation;Histologic dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br);preservation of image Content in Stain-to-stain Translation for Digital Pathology;Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology;Anatomy-aware data Augmentation for Multi-organ Segmentation in CT: AnatoMix.

关键词：

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 << < 38 39 40 41 42 43 44 45 46 47 > >>

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：