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711-720 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：

image Restoration under Semantic Communications 15

Image Restoration under Semantic Communications

引用

15th International conference on Advanced Technologies for Communications, ATC 2022

作者： Van Chien, Trinh Phong, Le Hong Phuc, Dao Xuan Hoa, Nguyen Tien Hanoi University of Science and Technology Viet Nam School of Electronic and Electrical Engineering Hanoi University of Science and Technology Viet Nam Hanoi Open University Faculty of Electrical and Electronic Engineering Viet Nam

ISBN: (数字)9781665451888

ISBN: (纸本)9781665451888

Semantic communication has emerged as the break-through beyond the Shannon theorem by transmitting and receiving semantic information instead of data bits or symbols regardless of its content. This paper proposes a two-stage reconstruction process to boost the system's performance. In the first phase, the image information is first decoded from the noisy received data by exploiting the channel knowledge. The decoded image is enhanced by a post-filter and image statistics. Different metrics are exploited to evaluate the image restoration quality of our considered model. Numerical results are obtained using natural images that verify the superior improvements of the proposed two-stage reconstruction process over the traditional decoded data. Moreover, the different metrics assessing the system performance based on their criteria can be conflicted with each other. © 2022 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

LFS-GAN: Lifelong Few-Shot image Generation

LFS-GAN: Lifelong Few-Shot Image Generation

引用

IEEE/CVF International conference on Computer Vision (ICCV)

作者： Seo, Juwon Kang, Ji-Su Park, Gyeong-Moon Kyung Hee Univ Yongin South Korea KLleon Tech Seoul South Korea

ISBN: (纸本)9798350307184

We address a challenging lifelong few- shot image generation task for the first time. In this situation, a generative model learns a sequence of tasks using only a few samples per task. Consequently, the learned model encounters both catastrophic forgetting and overfitting problems at a time. Existing studies on lifelong GANs have proposed modulation-based methods to prevent catastrophic forgetting. However, they require considerable additional parameters and cannot generate high-fidelity and diverse images from limited data. On the other hand, the existing few-shot GANs suffer from severe catastrophic forgetting when learning multiple tasks. To alleviate these issues, we propose a framework called Lifelong Few-Shot GAN (LFS-GAN) that can generate high-quality and diverse images in lifelong few-shot image generation task. Our proposed framework learns each task using an efficient task-specific modulator - Learnable Factorized Tensor (LeFT). LeFT is rank-constrained and has a rich representation ability due to its unique reconstruction technique. Furthermore, we propose a novel mode seeking loss to improve the diversity of our model in low-data circumstances. Extensive experiments demonstrate that the proposed LFS-GAN can generate high-fidelity and diverse images without any forgetting and mode collapse in various domains, achieving state-of-the-art in lifelong few-shot image generation task. Surprisingly, we find that our LFS-GAN even outperforms the existing few-shot GANs in the few-shot image generation task. The code is available at Github.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthetic aperture radar imaging from sub-Nyquist samples by using deep priors of image

Synthetic aperture radar imaging from sub-Nyquist samples by...

引用

IEEE Radar conference (RadarConf)

作者： An, Hongyang Jiang, Ruili Zuo, Haowen Wu, Junjie Li, Zhongyu Yang, Jianyu Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Peoples R China

ISBN: (纸本)9781665436694

As an active microwave imaging technology, synthetic aperture radar (SAR) has extensive application prospects in remote sensing, surveying, and mapping. How to reconstruct SAR images from the subsampled echo data has always been a challenging issue. Compressed sensing technology attempts to use the sparse characteristics of SAR images to recover the SAR images from the compressed samples. However, in practical applications, SAR images do not always meet the characteristic of sparsity. In this paper, we propose an imaging method from sub-Nyquist sampled data based on deep priors of SAR images. First, we use a generative flow network to model the deep prior information of the images based on the existing SAR image datasets. Then, the pre-trained network modeling deep prior information of images is embedded in a typical compressed sensing method, i.e., the Iterative Shrinkage-Thresholding Algorithm (ISTA), to replace the sparse shrinkage function of it. Meanwhile, in order to improve the accuracy and convergence speed of reconstruction, we used the subsampled echo data to fine-tune the iterative parameters of the embedded ISTA method. The results of the experiments show that through the use of the deep prior information of the images, this method can accurately reconstruct non-sparse SAR images from the subsampled echoes, even if only a few echo samples are available.

关键词： SAR imaging method sub-Nyquist deep priors of image unfolding.

来源：评论

学校读者我要写书评

暂无评论

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°

引用

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

作者： An, Sizhe Xu, Hongyi Shi, Yichun Song, Guoxian Ogras, Umit Y. Luo, Linjie ByteDance Inc Culver City CA 90230 USA Univ Wisconsin Madison Madison WI 53706 USA

ISBN: (纸本)9798350301298

Synthesis and reconstruction of 3D human head has gained increasing interests in computer vision and computer graphics recently. Existing state-of-the-art 3D generative adversarial networks (GANs) for 3D human head synthesis are either limited to near-frontal views or hard to preserve 3D consistency in large view angles. We propose PanoHead, the first 3D-aware generative model that enables high-quality view-consistent image synthesis of full heads in 360 degrees. with diverse appearance and detailed geometry using only in-the-wild unstructured images for training. At its core, we lift up the representation power of recent 3D GANs and bridge the data alignment gap when training from in-the-wild images with widely distributed views. Specifically, we propose a novel two-stage self-adaptive image alignment for robust 3D GAN training. We further introduce a tri-grid neural volume representation that effectively addresses front-face and backhead feature entanglement rooted in the widely-adopted triplane formulation. Our method instills prior knowledge of 2D image segmentation in adversarial learning of 3D neural scene structures, enabling compositable head synthe- sis in diverse backgrounds. Benefiting from these designs, our method significantly outperforms previous 3D GANs, generating high-quality 3D heads with accurate geometry and diverse appearances, even with long wavy and afro hairstyles, renderable from arbitrary poses. Furthermore, we show that our system can reconstruct full 3D heads from single input images for personalized realistic 3D avatars.

关键词： image and video synthesis and generation

来源：评论

学校读者我要写书评

暂无评论

Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI using Swin Transformer-based Masked Auto Encoder 7

Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI usi...

引用

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

作者： Rashmi, Kumari Das, Ayantika Gayathri, Matcha Naga Ram, Keerthi Sivaprakasam, Mohanasankar Indian Institute of Technology Madras India HealthCare Technology Innovation Center India

The advanced deep learning-based Autoencoding techniques have enabled the introduction of efficient Unsupervised Anomaly Detection (UAD) approaches. Several autoencoder-based approaches have been used to solve UAD tasks. However, most of these approaches do not have any constraints to ensure the removal of pathological features while restoring the healthy regions in the pseudo-healthy image reconstruction. To minimize the occurrence of pathological features, we propose to utilize an Autoencoder which deploys a masking strategy to reconstruct images. Additionally, the masked regions need to be meaningfully inpainted to enforce global and local consistency in the generated images which makes transformer-based masked autoencoder a potential approach. Although the transformer models can incorporate global contextual information, they are often computationally expensive and dependent on a large amount of data for training. Hence we propose to employ a Swin transformer-based Masked Autoencoder (MAE) for anomaly detection (Ano-swinMAE) in brain MRI. Our proposed method Ano-swinMAE is trained on a healthy cohort by masking a certain percentage of information from the input images. While inferring, a pathological image is given to the model, and different segments of the brain MRI slice are sequentially masked, and their corresponding generation is accumulated to create a map indicating potential locations of pathologies. We have quantitatively and qualitatively validated the performance increment of our method on the following publicly available datasets: BraTS (Glioma), MSLUB (Multiple Sclerosis), and White Matter Hyperintensities (WMH). We have also empirically evaluated the generalization capability of the method in a cross-modality data setup. © 2024 CC-BY 4.0, K. Rashmi, A. Das, M.N. Gayathri, K. Ram & M.S.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

ENERGY-INSPIRED SELF-SUPERVISED PRETRAINING FOR VISION MODELS 11

ENERGY-INSPIRED SELF-SUPERVISED PRETRAINING FOR VISION MODEL...

引用

11th International conference on Learning Representations, ICLR 2023

作者： Wang, Ze Wang, Jiang Liu, Zicheng Qiu, Qiang Purdue University United States Microsoft Corporation United States

Motivated by the fact that forward and backward passes of a deep network naturally form symmetric mappings between input and output representations, we introduce a simple yet effective self-supervised vision model pretraining framework inspired by energy-based models (EBMs). In the proposed framework, we model energy estimation and data restoration as the forward and backward passes of a single network without any auxiliary components, e.g., an extra decoder. For the forward pass, we fit a network to an energy function that assigns low energy scores to samples that belong to an unlabeled dataset, and high energy otherwise. For the backward pass, we restore data from corrupted versions iteratively using gradient-based optimization along the direction of energy minimization. In this way, we naturally fold the encoder-decoder architecture widely used in masked image modeling into the forward and backward passes of a single vision model. Thus, our framework now accepts a wide range of pretext tasks with different data corruption methods, and permits models to be pretrained from masked image modeling, patch sorting, and image restoration, including super-resolution, denoising, and colorization. We support our findings with extensive experiments, and show the proposed method delivers comparable and even better performance with remarkably fewer epochs of training compared to the state-of-the-art self-supervised vision model pretraining methods. Our findings shed light on further exploring self-supervised vision model pretraining and pretext tasks beyond masked image modeling. © 2023 11th International conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

PHYSICS-INFORMED image ANALYSIS FOR MECHANICAL STRESS reconstruction IN FOOD SYSTEMS 13th

PHYSICS-INFORMED IMAGE ANALYSIS FOR MECHANICAL STRESS RECONS...

引用

13th International conference on Simulation and Modelling in the Food and Bio-Industry, FOODSIM 2024

作者： Chen, Han Hayert, Murielle Guthrie, Brian Vitrac, Olivier INRAE AgroParisTech Paris-Saclay University Palaiseau91120 France Global Core R and D Cargill R and D WayzataMN55391 United States

ISBN: (纸本)9789492859297

In our latest development of an open-source simulation framework, we introduce the innovative concept of "food-atoms" for simulating mechanical phenomena in food systems, covering a broad spectrum from product design to oral processing and digestion [submitted to Food Res. Int.]. These mesoscopic entities, extending beyond the colloidal scale, are equipped with precisely defined interactions, enabling them to accurately emulate the intricate dynamics among diverse food components. Anchored in a sophisticated adaptation of Smoothed Particle Hydrodynamics (SPH) methods, our framework facilitates the versatile modeling of both liquid and solid states in food materials. This paper presents the application of food-atoms in interpreting mechanical aspects of static or dynamic food images obtained via confocal microscopy. We illustrate our approach with three compelling case studies. The first describes the emergence of shear and pressure drag forces from pairwise interactions between Lagrangian particles. The second involves transforming a static emulsion image into a dynamic simulation that vividly captures droplet disruption, achieved by converting image voxels into food-atoms using fluorescence labeling. The third study reconstructs pairwise interactions among larger food-atoms from dynamic observations of a Couette flow containing fluorescent polystyrene beads. In this scenario, the food-atoms, larger in size, are derived from analyzed velocity fields and streamline data. The stress distribution within the flow is meticulously assessed through the virial theorem. These case studies validate not only the practicality and versatility of our framework but also its potential for integrating static imaging data with dynamic mechanical simulations. This novel methodology promises significant advancements in understanding and predicting the mechanical behaviors of food materials under various processing and consumption conditions. © 2024, EUROSIS-ETI. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Development of an image Processing Techniques for Vehicle Classification Using OCR and SVM

Development of an Image Processing Techniques for Vehicle Cl...

引用

2023 International conference on Science, Engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Joshua, Ishola Oluwaseun Arowolo, Michael Olaolu Adebiyi, Marion O. Oluwaseun, Ogundokun Roseline Gbolagade, Kazeem Alagbe Landmark University Department of Computer Science Omu Aran Nigeria University of Missouri Department of Electrical Engineering and Computer Science Columbia United States Institute of Professional and Continuous Education Kwara State University Department of Computer Science Malete Nigeria

ISBN: (纸本)9798350324785

image processing is a method for enhancing unprocessed images from cameras on aircraft, spacecraft, and satellites as well as images taken regularly for a variety of uses. In general, the following strategies can be used to categorize all image processing operations: images are represented in several ways, which are referred to as image representation, image preprocessing, image enhancement, image restoration, image analysis, picture reconstruction, and image data compression. The first radiometric normalization, geometric distortion correction, and noise removal of the raw image data been discussed in the past. The goal of the information extraction procedures is to automate the identification of tone in a scene by replacing the visual examination of image data with quantitative techniques. This entails analyzing multispectral image data and establishing the earth cover identification of each pixel in an image using statistically based decision procedures. The goal of the classification procedure is to sort all of the pixels in a digital image into one of several different earth cover classes or themes. The purpose of this study is to examine various image processing approaches and algorithms, many sorts of image processing algorithms: Optical Character Recognition (OCR) and Supporting Vector Machine (SVM) a feature extraction technique, on the vehicle classification dataset and had accurate results of 90% for SVM and 95% for OCR, to further improve the performance of machine algorithms in terms of accuracy for image processing technique using a vehicle. This study can be used for vehicle classification research, it also advances and improves the performance of the system in terms of accurate detection. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional autoencoders for image reconstruction from incomplete fourier amplitude measurements.

Deep convolutional autoencoders for image reconstruction fro...

引用

International conference on Transparent Optical Networks

作者： G. Pellegrini J. Bertolotti Dipartimento di Fisica Via Bassi 6 Universitàdegli studi di Pavia Pavia Italy Department of Physics and Astronomy Exeter Devon EX4 4QL University of Exeter UK

ISBN: (数字)9798350377323

ISBN: (纸本)9798350377330

Phase-retrieval approaches seek to recover an original signal using only the modulus of its Fourier transform, which is often much easier to detect than its phase, but normal iterative techniques frequently fail when only a portion of the modulus information is available [1]. We demonstrate that a neural network can be trained to perform phase retrieval with partial information, and we analyze the benefits and drawbacks of this technique. In practice we consider a reconstruction problem where we wish to recover the image of a concealed object from an estimate of its autocorrelation, obtained from the analysis of the spatial correlations of the speckle image. We perform the image retrieval task on a synthetic dataset and under different conditions, where the autocorrelation information may be either fully available or, more interestingly, partially removed [2].

关键词： Autocorrelation Optical imaging Integrated optics image reconstruction Convolution Adaptive optics Task analysis

来源：评论

学校读者我要写书评

暂无评论

Proceedings of ICWITE 2024: IEEE International conference for Women in Innovation, Technology and Entrepreneurship

Proceedings of ICWITE 2024: IEEE International Conference fo...

引用

2nd IEEE International conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

ISBN: (纸本)9798350383287

The proceedings contain 128 papers. The topics discussed include: a study on multimodal approach for early detection of dementia using deep learning;market analysis of various types of rapid testing glucose level equipments;optimal feature selection using enhanced bacterial foraging optimization for healthcare application based big data;transformer based lightweight model for punctuation restoration and truecasing;fuzzy based energy management strategy for battery and fuel cell hybrid vehicles;upgrade better accuracy by analyzing the behavior of classifying algorithm to detect intrusion in network traffic;enhanced pothole detection in road condition assessment using YOLOv8;towards efficient encrypted medical image retrieval from heterogeneous multi cloud environment;and enhancing medical imaging resolution: exploring SRGAN for high-quality medical image reconstruction.

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 << < 68 69 70 71 72 73 74 75 76 77 > >>

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：