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691-700 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：

Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method

Learning Diffusion Model from Noisy Measurement using Princi...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Bai, Weimin Tang, Weiheng Ye, Enze Chen, Siyi Chen, Wenzheng Sun, He Academy for Advanced Studies Peking University China School of Physics Peking University China College of Future Technology Peking University China Wangxuan Institute of Computer Technology Peking University China

ISBN: (纸本)9798350368741

Diffusion models have demonstrated exceptional ability in modeling complex image distributions, making them versatile plug-and-play priors for solving imaging inverse problems. However, their reliance on large-scale clean datasets for training limits their applicability in scenarios where acquiring clean data is costly or impractical. Recent approaches have attempted to learn diffusion models directly from corrupted measurements, but these methods either lack theoretical convergence guarantees or are restricted to specific types of data corruption. In this paper, we propose a principled expectation-maximization (EM) framework that iteratively learns diffusion models from noisy data with arbitrary corruption types. Our framework employs a plug-and-play Monte Carlo method to accurately estimate clean images from noisy measurements, followed by training the diffusion model using the reconstructed images. This process alternates between estimation and training until convergence. We evaluate the performance of our method across various imaging tasks, including inpainting, denoising, and deblurring. Experimental results demonstrate that our approach enables the learning of high-fidelity diffusion priors from noisy data, significantly enhancing reconstruction quality in imaging inverse problems. © 2025 IEEE.

关键词： Bayesian inference Computational imaging diffusion models image priors inverse problems

来源：评论

学校读者我要写书评

暂无评论

VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-view 3D reconstruction 17th

VIPNet: Combining Viewpoint Information and Shape Priors fo...

引用

17th Asian conference on Computer Vision, ACCV 2024

作者： Ye, Weining Li, Zhixuan Jiang, Tingting School of Computer Science Peking University Beijing100871 China College of Computing and Data Science Nanyang Technological University Singapore Singapore National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science National Biomedical Imaging Center Peking University Beijing100871 China

ISBN: (纸本)9789819609680

While the multi-view 3D reconstruction task has made significant progress, existing methods simply fuse multi-view image features without effectively leveraging available auxiliary information, especially the viewpoint information for guiding and associating features of different views. To this end, we propose to enhance multi-view 3D reconstruction with the power of viewpoint information. Specifically, a simple-yet-effective viewpoint estimator is designed to learn and provide comprehensive viewpoint knowledge for locating and associating learned features from different views. Moreover, to improve the 3D reconstruction quality when 2D images of only very few viewpoints are available, we propose to learn the shape prior knowledge to provide sufficient shape information for compensating the limited 2D observations. Overall, we present VIPNet, benefiting from Viewpoint Information and Shape Prior learning for high-quality multi-view 3D reconstruction. Extensive experiments validate the effectiveness of the proposed VIPNet, which achieves state-of-the-art performance on challenging datasets and shows well generalization ability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

A Pose-Aware Auto-Augmentation Framework for 3D Human Pose and Shape Estimation from Partial Point Clouds 7th

A Pose-Aware Auto-Augmentation Framework for 3D Human Pose a...

引用

7th Chinese conference on Pattern Recognition and Computer Vision

作者： Wang, Kangkan Yin, Sliihao Fang, Chenghao Nanjing Univ Sci & Technol Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China

ISBN: (纸本)9789819785070;9789819785087

This work mainly addresses the challenges in 3D human pose and shape estimation from real partial point clouds. Existing 3D human estimation methods from point clouds usually have limited generalization ability on real data due to factors such as self-occlusion and random noise and domain gap between real data and synthetic data. In this paper, we propose a pose-aware auto-augmentation framework for 3D human pose and shape estimation from partial point clouds. Specifically, we design an occlusion-aware module for the estimator network that can obtain refined features to accurately regress human pose and shape parameters from partial point clouds, even if the point clouds are self-occlusive. Based on the pose parameters and global features of the point clouds from estimator network, we carefully design a learnable augmentor network that can intelligently drive and deform real data to enrich data diversity during the training of estimator network. To guide the augmentor network to generate challenging augmented samples, we adopt an adversarial learning strategy according to the error feedback of the estimator. The experimental results on real data and synthetic data demonstrate that the proposed approach can accurately estimate the 3D human pose and shape from partial point clouds and outperform prior works in terms of reconstruction accuracy.

关键词： 3D human pose and shape estimation Pose-aware auto-augmentation Occlusion-aware network Partial point clouds Real data

来源：评论

学校读者我要写书评

暂无评论

SV-HaRF: a scene representation method for sparse image view synthesis

SV-HaRF: a scene representation method for sparse image view...

引用

2023 International conference on Computer Graphics, Artificial Intelligence, and data Processing, ICCAID 2023

作者： Liu, Wei Zhang, Yu Zou, Xuechao Ma, Rui Tao, Pin Department of Computer Technology and Applications Qinghai University China Department of Computer Science and Technology Tsinghua University China Key Laboratory of Pervasive Computing Ministry of Education China

ISBN: (纸本)9781510677685

Existing view synthesis algorithms often require dozens or even hundreds of photographs taken from different angles to capture more intricate details in the resulting 3D model. While increasing the number of angles can yield better model parameters, it also significantly increases the training cost. Therefore, there is a need to reduce the quantity of input images with different angles while maintaining comparable results. In this paper, we propose SV-HaRF, which aims to reconstruct scenes by using a sparse set of angles (typically less than 100 but not less than 10) to ensure scene model integrity, as the original training sets often consist of over 100 angles. To address this issue, SV-HaRF employs hash encoding on the input sparse image resolutions to enhance the spatial constraint of these viewpoint positions during the scene reconstruction process, thereby improving the ability to restore scene information. SV-HaRF not only demonstrates outstanding performance in synthesizing sparse viewpoints for reducing model angles but also exhibits superior enhancement, compared to existing NeRF and its related variants, when the input image viewpoints remain unchanged. We conducted experiments on the NeRF Blender Synthetic dataset, showcasing significant improvements in scene synthesis achieved by SV-HaRF. © 2024 SPIE.

关键词： image resolution

来源：评论

学校读者我要写书评

暂无评论

Multiband remote 3D-ViT data fusion 30

Multiband remote 3D-ViT data fusion

引用

conference on Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXX

作者： Kurz, Aidan G. Depoian, Arthur C., II Bailey, Colleen P. Univ North Texas Dept Elect Engn Denton TX 76207 USA

ISBN: (纸本)9781510673816;9781510673809

Satellites are equipped with diverse sensors, capable of capturing detailed information across a multitude of wavelengths. The fusion of multispectral data is pivotal to amplify the visual representation of the area of interest. The improvement of information representation allows for enhanced processing, analysis, and other crucial tasks for numerous fields of study, including remote sensing, defense, and material characterization. Previous solutions often utilize traditional signal processing techniques, including principal component analysis (PCA), to accomplish data fusion. By performing fusion on a feature level, extracted information about the area of interest texture and boundaries are combined. The introduction of neural network techniques improved the reconstruction of data similar to the results obtained by conventional inference of humans. For example, the use of deep learning algorithms in conjunction with PCA allowed for refined reduction of redundancy and distortion of spectral data, in comparison to traditional methods alone. The introduction of the Vision Transformer (ViT) architecture, originally developed for two-dimensional image data, has revolutionized image processing tasks, vastly improving performance at the cost of a large quantity of trainable parameters. Recent experimentation has proven that optimizing ViT for efficiency allows for comparable or even superior performance while lessening the computational cost. The transition from 2D to 3D information via utilization of additional depth and spatial data has also led to superior results as the added information allows for better representation of terrain features, making it invaluable for satellite imagery analysis. Combining the principles of ViT and 3D information to process complex satellite data can result in more effective data fusion to achieve a superior level of data visualization of multispectral satellite imagery in an efficient manner.

关键词： data Fusion Multispectral Fusion Remote Sensing Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Semantics-enhanced Cross-modal Masked image Modeling for Vision-Language Pre-training 30

Semantics-enhanced Cross-modal Masked Image Modeling for Vis...

引用

Joint 30th International conference on Computational Linguistics and 14th International conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Liu, Haowei Shi, Yaya Xu, Haiyang Yuan, Chunfeng Ye, Qinghao Li, Chenliang Yan, Ming Zhang, Ji Huang, Fei Li, Bing Hu, Weiming MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China University of Science and Technology of China China Alibaba Group China School of Information Science and Technology ShanghaiTech University China

ISBN: (纸本)9782493814104

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and text is not sufficiently involved in masked modeling. These two drawbacks limit the effect of MIM in facilitating cross-modal semantic alignment. In this work, we propose a semantics-enhanced cross-modal MIM framework (SemMIM) for vision-language representation learning. Specifically, to provide more semantically meaningful supervision for MIM, we propose a local semantics enhancing approach, which harvest high-level semantics from global image features via self-supervised agreement learning and transfer them to local patch encodings by sharing the encoding space. Moreover, to achieve deep involvement of text during the entire MIM process, we propose a text-guided masking strategy and devise an efficient way of injecting textual information in both masked modeling and reconstruction target acquisition. Experimental results validate that our method improves the effectiveness of the MIM task in facilitating cross-modal semantic alignment. Compared to previous VLP models with similar model size and data scale, our SemMIM model achieves state-of-the-art or competitive performance on multiple downstream vision-language tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Label-Visual Correlation Hashing for Multi-label image Retrieval 1

引用

6th Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International conference on Web and Big data (APWeb-WAIM)

作者： Liu, Yu Xie, Yanzhao Song, Jingkuan Wei, Rukai Zhou, Ke Huazhong Univ Sci & Technol Wuhan Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (数字)9783031251986

ISBN: (纸本)9783031251979;9783031251986

Perceiving multiple objects within an image without the labels' supervision is the challenge of multi-label image hashing tasks. Existing unsupervised hashing approaches do reconstruction or contrastive learning for the representation of the object of interest but ignore the other objects in the image. We propose to use pseudo labels to provide candidate objects, making the image match the possible objects' features by the co-occurrence correlations between labels. As a result, we explore the co-occurrence correlations based on empirical models and design a data augmentation strategy in a self-supervised learning framework to learn label-level embeddings. We also build the image visual correlations and design a dual overlapping group sum-pooling (OGSP) component to fuse label-level and visual-level embeddings into image representations, alleviating noise from empirical models. Extensive experiments on public multi-label image datasets using pseudo labels demonstrate that our self-supervised label-visual correlation hashing framework outperforms state-of-the-art label-free hashing algorithms for retrieval. GitHub address: https://***/lzHZWZ/***.

关键词： Multi-label image hashing Self-supervised learning Co-occurrence correlations

来源：评论

学校读者我要写书评

暂无评论

Multi-IMU with Online Self-consistency for Freehand 3D Ultrasound reconstruction 26th

Multi-IMU with Online Self-consistency for Freehand 3D Ultra...

引用

26th International conference on Medical image Computing and Computer-Assisted Intervention (MICCAI)

作者： Luo, Mingyuan Yang, Xin Yan, Zhongnuo Li, Junyu Zhang, Yuanji Chen, Jiongquan Hu, Xindi Qian, Jikuan Cheng, Jun Ni, Dong Shenzhen Univ Sch Biomed Engn Hlth Sci Ctr Natl Reg Key Technol Engn Lab Med Ultrasound Shenzhen Peoples R China Shenzhen Univ Med Ultrasound Image Comp MUSIC Lab Shenzhen Peoples R China Shenzhen Univ Marshall Lab Biomed Engn Shenzhen Peoples R China Shenzhen RayShape Med Technol Inc Shenzhen Peoples R China

ISBN: (纸本)9783031439063;9783031439070

Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities. Freehand 3D US is a technique that provides a deeper understanding of scanned regions without increasing complexity. However, estimating elevation displacement and accumulation error remains challenging, making it difficult to infer the relative position using images alone. The addition of external lightweight sensors has been proposed to enhance reconstruction performance without adding complexity, which has been shown to be beneficial. We propose a novel online self-consistency network (OSCNet) using multiple inertial measurement units (IMUs) to improve reconstruction performance. OSCNet utilizes a modal-level self-supervised strategy to fuse multiple IMU information and reduce differences between reconstruction results obtained from each IMU data. Additionally, a sequence-level self-consistency strategy is proposed to improve the hierarchical consistency of prediction results among the scanning sequence and its sub-sequences. Experiments on large-scale arm and carotid datasets with multiple scanning tactics demonstrate that our OSCNet outperforms previous methods, achieving state-of-the-art reconstruction performance.

关键词： Multiple IMU Online Learning Freehand 3D Ultrasound

来源：评论

学校读者我要写书评

暂无评论

Wheat Disease Recognition Based on a Fusion Model with Improved Spatial and Channel reconstruction Convolution Combined with Contextual Transformer 5

Wheat Disease Recognition Based on a Fusion Model with Impro...

引用

5th International conference on Computer Vision, image and Deep Learning, CVIDL 2024

作者： Yang, Zicong Jin, Aitong Wang, Junxi Xie, Haifan Zhan, Xin Li, Qiaolin Zhuhai College of Science and Technology Department of Computer Zhuhai China Zhuhai College of Science and Technology Department of Statistics and Data Science Zhuhai China Zhuhai College of Science and Technology Department of Mechanical Engineering Zhuhai China Fujian University of Traditional Chinese Medicine School of Traditional Chinese Medicine Fuzhou China

ISBN: (纸本)9798350373820

Crop diseases cause loss of agricultural products and have a critical impact on society, the economy, and the environment, so it is crucial for early defending the wheat disease. However, seeking an expert diagnosis can contribute to delays and higher costs. Therefore, this paper proposes a deep learning neural network with improved spatial and channel reconstruction convolution combined with CoT Attention module, named SCCoT-WheatNet. This innovated neural network can recognize wheat disease. The experimental dataset was obtained from the Internet and some publicly available datasets using web crawler was technology. This modification is based on the VGG13 model. In the final two sections of the VGG13 model, feature extraction replaces conventional convolutional layers with Contextual Transformer module and spatial and channel reconstruction convolution block. The experiment adopts a cross-fold approach. In the first fold test, the results show that the average recognition accuracy of the SCCoT-WheatNet network is 9 6. 9 4%, which is higher than the classical VGG network and the Vision Transformer models of the last two years. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

data Masking Analysis Based on Masked Autoencoders Architecture for Leaf Diseases Classification 1

引用

18th International conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Li, Li-Hua Tanone, Radius Department of Information Management Chaoyang University of Technology Taichung City Taiwan Fakultas Teknologi Informasi Universitas Kristen Satya Wacana Salatiga Indonesia

ISBN: (数字)9789819906055

ISBN: (纸本)9789819906048

Agriculture is one of the sectors that drives the economy of a country, including Indonesia. However, the prevention of plant diseases that can be classified through leaves must also be considered by farmers to produce good yields. In this study, we conducted an experiment by implementing self-supervised learning on plant disease recognition. We built the Masked Autoencoders model from scratch on the leaf diseases dataset (strawberry, potato, and tomato) to perform the downstream task, namely classification. In this experiment, we masked the input image with portions of 50%, 75% and 90% to analyse how the model works in reconstructing the missing pixels to resemble the original image. To see the performance of our experiment, metrics such as accuracy, SSIM and PSNR are used to see the effectiveness of the algorithm in image reconstruction. The results obtained in this experiment are that the more classes in the dataset, the downstream accuracy using the pre-trained MAE model is relatively small. On the other hand, a small number of classes will result in linear probing accuracy above 75% when classifying leaf disease recognition. For the SSIM and PSNR results, we identified that the image similarity results depended on the shape of the image where a more varied leaf shape would help the reconstruction process to resemble the original image. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image reconstruction

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 << < 66 67 68 69 70 71 72 73 74 75 > >>

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：