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571-580 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：

Dual AxAtGAN: A Feature Intregrate BCI Model for image reconstruction 13

Dual AxAtGAN: A Feature Intregrate BCI Model for Image Recon...

引用

13th International conference on Information Technology in Medicine and Education, ITME 2023

作者： Zhao, Xuan Guo, Yina Taiyuan University of Science and Technology Shanxi Taiyuan China

ISBN: (纸本)9798350319156

The visual stimulus-oriented brain activity reconstruction method based on BCI technology has the advantages of high transmission rate and easy operation. However, the problem of losing feature information due to vector dimensionality reduction still exists in existing visual evoked EEG reconstruction algorithms. This motivates us to design an end-to-end model, Dual AxAtGAN, where the network is nested using two Dual GAN as the basic framework, which is able to directly perform the task of reconstructing from video-evoked EEG to the corresponding video. In addition, existing reconstruction algorithms are based on convolutional neural networks, which can only focus on a local subset of a pixel point in an image, and leads to the model's lack of understanding of the long-range dependence of the EEG signal features, and consequently it is unable to reconstruct the corresponding image or video. To address the above challenges, inspired by the transformer block, we modified the axial multi-head self-attention module instead of the CNN blocks, which improves the model's understanding of the long-range dependence of EEG signals. In addition, we train the data from two branches, global and local, which in turn improves the performance of the model, and finally reconstruct the videos corresponding to the evoked EEG. To test the reconstruction effect of the model, we design a supervised paradigm that meets the requirements of this experiment to obtain the dataset of video-evoked EEG. Compared with the existing methods, our proposed model can better perform the task of video-evoked EEG reconstruction. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Research on the reconstruction of Observational Geometry for Scanning Multispectral image 11th

Research on the Reconstruction of Observational Geometry for...

引用

11th International conference on Signal and Information Processing, Network and Computers, ICSINC 2023

作者： Wang, Guanzhu Pan, Zhiqiang Zhang, Haoping Yu, Wenyong China Centre for Resources Satellite Data and Application Beijing China

ISBN: (纸本)9789819721153

Most of the scanning multispectral data from domestic land observation satellites only provide the imaging geometry of the scene center, missing the geometry of other pixels. This paper proposes a method for the reconstruction of observational geometry and verify the method using images with observational geometry. The result shows that the relative deviations of the reconstructed observation zenith and azimuth are less than 5%, combined with the Ross-Li BRDF model, it can significantly improve the accuracy of directional surface reflectance and of the calibration coefficients. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Correction of Secret images Reconstructed from Noised Shared images 11

Correction of Secret Images Reconstructed from Noised Shared...

引用

11th International conference on image Processing Theory, Tools and Applications (IPTA)

作者： Bertojo, Laura Puech, William Univ Montpellier LIRMM Montpellier France

ISBN: (纸本)9781665469647

Protecting sensitive images is nowadays a key issue in information security domain. As such, numerous techniques have emerged to securely transmit or store such multimedia data, as encryption, steganography or secret sharing. Most of today's secret image sharing methods relie on the polynomialbased scheme proposed by Shamir. However, some of the shared images distributed to the participants may be noised between their creation and their use to retrieve the secret image. Noise can be added to a shared image during transmission, storage or JPEG compression for example. However, to our knowledge, to date no analysis has been made on the impact of using a noised shared image in the reconstruction process of a secret image. In this paper, we propose a method to correct the errors during the reconstruction of a secret image using noised shared images.

关键词： Poynomial secret image sharing Noised shared image Error correction

来源：评论

学校读者我要写书评

暂无评论

A Multi-scale Framework towards Human-Machine Friendly Remote Sensing image Coding 6

A Multi-scale Framework towards Human-Machine Friendly Remot...

引用

6th ACM International conference on Multimedia in Asia, MMAsia 2024

作者： He, Yingkai Zhang, Zhen Xiao, Jing School of Computer Science Wuhan University Hubei Province Wuhan City China

ISBN: (纸本)9798400712739

With the increasing availability of remote sensing data and the development of machine learning-based collaborative interpretation techniques, remote sensing image transmission needs to serve both human and machine vision, in addition to achieving high-efficiency compression. However, existing compression methods that are optimized for pixel-level representation often suffer from performance degradation when confronted with downstream machine analysis *** address this issue, we propose a feature-domain-optimized, human-machine friendly remote sensing image compression framework. We design a compact multi-scale feature extractor to transform images into a feature domain representation, and then compress the compact feature for efficient transmission. During the decoding process, the compressed feature is directly used for machine analysis, which avoids the trade-off between human and machine vision requirements. To reconstruct visually pleasing images, we exploit the synergy between tasks and enhance the image reconstruction process with features from high-level *** results on the AID and NWPU-RESISC45 datasets demonstrate that our proposed method outperforms existing compression techniques in terms of analytical performance, while maintaining equivalent visual effects. This work highlights the importance of designing compression methods that are tailored to the needs of both human interpreters and machine analysis tasks in the context of remote sensing image processing. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Passive non-line-of-sight imaging for hidden target detection 2

Passive non-line-of-sight imaging for hidden target detectio...

引用

2nd Advanced Imaging and Information Processing conference, AIIP 2024

作者： Wang, Hailu Chen, Minsun Liu, Hao Lai, Wenchang Lei, Guozhong Han, Kai College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha410073 China Nanhu Laser Laboratory National University of Defense Technology Changsha410073 China

ISBN: (纸本)9781510683068

The rapidly developing non-line-of-sight (NLOS) imaging technology in recent years is capable of intelligent visual perception of concealed targets, holding broad application prospects in security, emergency rescue, autonomous driving, etc. Compared to active methods, passive NLOS imaging is promising to in real-world scenarios due to its low cost. This paper uses the long-wave infrared (LWIR) to detect multiple hidden targets. In contrast to the visible band, LWIR exhibits a higher proportion of specular reflection scattering on common relay surface but cannot represent details such as texture. Furthermore, passive NLOS imaging reconstruction is an ill-posed problem, leading to sparse and blurred features, which poses significant challenges for multi-target detection tasks. To address this, the paper proposes a deep learning method for collaborative multi-task image reconstruction and detection. The detection loss is backpropagated and fused with the imaging enhancement loss to guide the NLOS target reconstruction process towards high-quality detection results. Comparative experiments are conducted in multi-person target scenarios between the latest target detection methods and our method. The results indicate that our proposed method exhibits the best performance in terms of detection accuracy, recall rate, and the F1-score. Additionally, this paper demonstrates the generalization of the proposed method at different distances ranging from 10 to 20 meters. The related results provide data and methodological support for the advancement of NLOS imaging towards practical applications. © 2024 SPIE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Automatic Cranial Defect reconstruction with Self-Supervised Deep Deformable Masked Autoencoders 46

Automatic Cranial Defect Reconstruction with Self-Supervised...

引用

46th Annual International conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Wodzinski, Marek Hemmerling, Daria Daniol, Mateusz Agh University of Krakow Department of Measurement and Electronics Krakow Poland Institute of Informatics Sierre Switzerland

ISBN: (纸本)9798350371499

Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to searching for algorithms whose goal is to automatize the process. The problem can be formulated as volumetric shape completion and solved by deep neural networks dedicated to supervised image segmentation. However, such an approach requires annotating the ground-truth defects which is costly and time-consuming. Usually, the process is replaced with synthetic defect generation. However, even the synthetic ground-truth generation is time-consuming and limits the data heterogeneity, thus the deep models' generalizability. In our work, we propose an alternative and simple approach to use a self-supervised masked autoencoder to solve the problem. This approach by design increases the heterogeneity of the training set and can be seen as a form of data augmentation. We compare the proposed method with several state-of-the-art deep neural networks and show both the quantitative and qualitative improvement on the SkullBreak and SkullFix datasets. The proposed method can be used to efficiently reconstruct the cranial defects in real time. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

SOFT image SEGMENTATION USING GRADIENT GRAPH LAPLACIAN REGULARIZER 49

SOFT IMAGE SEGMENTATION USING GRADIENT GRAPH LAPLACIAN REGUL...

引用

49th IEEE International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chen, Fei Cheung, Gene Zhang, Xue Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China York Univ Dept EECS Toronto ON Canada Shandong Univ Sci & Technol Qingdao Peoples R China

ISBN: (纸本)9798350344868;9798350344851

We revisit the well-studied image segmentation problem from a soft labeling perspective: instead of estimating integer labels per pixel indicating a finite set of classes, each pixel is assigned a real number that conveys the level of uncertainty in the estimated class label. Soft labels are useful, for example, for subsequent human editing or composition. Specifically, given a set of pre-computed super-pixel labels and feature vectors per pixel, we formulate a convex optimization objective regularized by signal-dependent gradient graph Laplacian regularizers (GGLR), which promotes piecewise planar (PWP) signal reconstruction. Unlike a previous well-known soft segmentation scheme that requires expensive computation of the first 100 eigenvectors, our optimization can be solved efficiently in linear time via conjugate gradient (CG). Experimental results show that our method produces satisfactory soft labels per pixel for images in two public datasets at a reduced computation cost compared to the previous soft segmentation scheme.

关键词： image segmentation graph signal processing gradient graph Laplacian regularizer

来源：评论

学校读者我要写书评

暂无评论

Decoding natural image stimuli from fMRI data with a surface-based convolutional network 6

Decoding natural image stimuli from fMRI data with a surface...

引用

6th International conference on Medical Imaging with Deep Learning (MIDL)

作者： Gu, Zijin Jamison, Keith Kuceyeski, Amy Sabuncu, Mert Cornell Univ Sch Elect & Comp Engn New York NY 14853 USA Cornell Tech New York NY 10044 USA Weill Cornell Med Dept Radiol New York NY USA

Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we propose a novel approach for this task, which we call Cortex2image, to decode visual stimuli with high semantic fidelity and rich fine-grained detail. In particular, we train a surface-based convolutional network model that maps from brain response to semantic image features first (Cortex2Semantic). We then combine this model with a high-quality image generator (Instance-Conditioned GAN) to train another mapping from brain response to fine-grained image features using a variational approach (Cortex2Detail). image reconstructions obtained by our proposed method achieve state-of-the-art semantic fidelity, while yielding good fine-grained similarity with the ground-truth stimulus. Our code is available on https://***/zijin-gu/***.

关键词： functional MRI neural decoding image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Reinforced Learning for Label-Efficient 3D Face reconstruction

Reinforced Learning for Label-Efficient 3D Face Reconstructi...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Mohaghegh, Hoda Rahmani, Hossein Laga, Hamid Boussaid, Farid Bennamoun, Mohammed Univ Western Australia Sch Comp Sci & Software Engn Crawley Australia Univ Lancaster Dept Comp & Commun Lancaster England Murdoch Univ Informat Technol Discipline Perth WA Australia Univ Western Australia Sch Engn Elect Elect & Comp Engn Crawley Australia

ISBN: (纸本)9798350323658

3D face reconstruction plays a major role in many human-robot interaction systems, from automatic face authentication to human-computer interface-based entertainment. To improve robustness against occlusions and noise, 3D face reconstruction networks are often trained on a set of in-the-wild face images preferably captured along different viewpoints of the subject. However, collecting the required large amounts of 3D annotated face data is expensive and time-consuming. To address the high annotation cost and due to the importance of training on a useful set, we propose an Active Learning (AL) framework that actively selects the most informative and representative samples to be labeled. To the best of our knowledge, this paper is the first work on tackling active learning for 3D face reconstruction to enable a label-efficient training strategy. In particular, we propose a Reinforcement Active Learning approach in conjunction with a clustering-based pooling strategy to select informative view-points of the subjects. Experimental results on 300W-LP and AFLW2000 datasets demonstrate that our proposed method is able to 1) efficiently select the most influencing view-points for labeling and outperforms several baseline AL techniques and 2) further improve the performance of a 3D Face reconstruction network trained on the full dataset.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on dataset Mixtures with Uncalibrated Stereo data

Single-Stage 3D Geometry-Preserving Depth Estimation Model T...

引用

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

作者： Patakin, Nikolay Vorontsova, Anna Artemyev, Mikhail Konushin, Anton Samsung AI Ctr Moscow Russia Skolkovo Inst Sci & Technol Skoltech Moscow Russia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Nowadays, robotics, AR, and 3D modeling applications attract considerable attention to single-view depth estimation (SVDE) as it allows estimating scene geometry from a single RGB image. Recent works have demonstrated that the accuracy of an SVDE method hugely depends on the diversity and volume of the training data. However, RGB-D datasets obtained via depth capturing or 3D reconstruction are typically small, synthetic datasets are not photorealistic enough, and all these datasets lack diversity. The large-scale and diverse data can be sourced from stereo images or stereo videos from the web. Typically being uncalibrated, stereo data provides disparities up to unknown shift (geometrically incomplete data), so stereo-trained SVDE methods cannot recover 3D geometry. It was recently shown that the distorted point clouds obtained with a stereo-trained SVDE method can be corrected with additional point cloud modules (PCM) separately trained on the geometrically complete data. On the contrary, we propose GP(2), General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting. Through experiments on different dataset mixtures, we prove that GP(2)-trained models outperform methods relying on PCM in both accuracy and speed, and report the state-of-the-art results in the general-purpose geometry-preserving SVDE. Moreover, we show that SVDE models can learn to predict geometrically correct depth even when geometrically complete data comprises the minor part of the training set.

关键词： Training Point cloud compression Phase change materials Geometry Solid modeling Three-dimensional displays Computational modeling

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 << < 54 55 56 57 58 59 60 61 62 63 > >>

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：