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

4,415 篇 会议
232 篇 期刊文献
55 册 图书
10 篇 学位论文
3 篇 资讯

馆藏范围

4,715 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,617 篇 工学
- 1,496 篇 计算机科学与技术...
- 883 篇 电气工程
- 771 篇 软件工程
- 462 篇 信息与通信工程
- 331 篇 控制科学与工程
- 290 篇 生物医学工程（可授...
- 221 篇 光学工程
- 210 篇 机械工程
- 160 篇 电子科学与技术（可...
- 143 篇 仪器科学与技术
- 126 篇 生物工程
- 87 篇 材料科学与工程（可...
- 68 篇 测绘科学与技术
- 58 篇 化学工程与技术
- 32 篇 土木工程
- 27 篇 建筑学
- 25 篇 力学（可授工学、理...
1,476 篇 理学
- 922 篇 物理学
- 651 篇 数学
- 429 篇 统计学（可授理学、...
- 228 篇 系统科学
- 138 篇 生物学
- 63 篇 化学
757 篇 医学
- 593 篇 临床医学
- 220 篇 特种医学
- 78 篇 基础医学(可授医学...
- 44 篇 药学(可授医学、理...
214 篇 管理学
- 119 篇 管理科学与工程(可...
- 103 篇 图书情报与档案管...
- 25 篇 工商管理
23 篇 农学
17 篇 法学
13 篇 教育学
12 篇 经济学
10 篇 艺术学
9 篇 文学
2 篇 军事学

主题

547 篇 image processing
460 篇 image segmentati...
390 篇 stochastic proce...
365 篇 statistical anal...
258 篇 feature extracti...
231 篇 bayesian methods
224 篇 image reconstruc...
188 篇 signal processin...
187 篇 image analysis
141 篇 pixel
135 篇 image restoratio...
109 篇 statistics
106 篇 pattern recognit...
105 篇 image edge detec...
103 篇 hidden markov mo...
103 篇 image coding
99 篇 noise reduction
97 篇 robustness
96 篇 testing
95 篇 histograms

机构

10 篇 school of electr...
8 篇 indian statistic...
7 篇 univ penn dept r...
7 篇 department of el...
7 篇 department of el...
7 篇 univ waterloo de...
7 篇 univ michigan de...
6 篇 nanyang technol ...
6 篇 smart computer v...
6 篇 computer vision ...
5 篇 georgia inst tec...
5 篇 microsoft resear...
5 篇 carnegie mellon ...
5 篇 signal and image...
5 篇 peng cheng lab p...
4 篇 google res mount...
4 篇 texas a&m univ.
4 篇 department of sy...
4 篇 ivan kozhedub kh...
4 篇 tokyo metropolit...

作者

9 篇 landman bennett ...
8 篇 vorapoj patanavi...
8 篇 dougherty er
8 篇 h. krim
7 篇 yannick berthoum...
7 篇 a.s. willsky
7 篇 sang hwa lee
6 篇 astola jaakko t.
6 篇 prince jerry l.
6 篇 umapada pal
6 篇 alexander wong
6 篇 udupa jk
6 篇 nam ik cho
6 篇 w. pieczynski
6 篇 fessler jeffrey ...
6 篇 w.c. karl
6 篇 pesquet jean-chr...
6 篇 pal umapada
6 篇 jong-il park
6 篇 pieczynski w

语言

4,633 篇 英文
39 篇 其他
31 篇 中文
13 篇 土耳其文
1 篇 西班牙文
1 篇 法文
1 篇 俄文

检索条件"任意字段=Conference on Statistical and Stochastic Methods for Image Processing"

共 4715 条记录，以下是201-210 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：

LOCALLY OPTIMAL DETECTION OF stochastic TARGETED UNIVERSAL ADVERSARIAL PERTURBATIONS

LOCALLY OPTIMAL DETECTION OF STOCHASTIC TARGETED UNIVERSAL A...

引用

IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Goel, Amish Moulin, Pierre Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA

ISBN: (纸本)9781728176055

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test based detector for detecting stochastic targeted universal adversarial perturbations to a classifier's input. We employ a two-stage process to learn the detector's parameters, which involves unsupervised maximum likelihood estimation followed by supervised training and demonstrates better performance of the detector compared to other detection methods on several popular image classification datasets.

关键词： image classification Neural networks Locally optimal tests Universal adversarial perturbations

来源：评论

学校读者我要写书评

暂无评论

Research on atmospheric turbulence-degraded image restoration based on Generative Adversarial Networks 1

Research on atmospheric turbulence-degraded image restoratio...

引用

1st International conference on Spatial Atmospheric Marine Environmental Optics, SAME 2023

作者： Cheng, Jiuming Li, Jianyu Dai, Congming Ren, Yichong Xu, Gang Li, Shuai Chen, Xiaowei Zhu, Wenyue Key Laboratory of Atmospheric Optics Anhui Institute of Optics and Fine Mechanics HFIPS Chinese Academy of Sciences Hefei230031 China Science Island Branch of Graduate School University of Science and Technology of China Hefei230026 China Advanced Laser Technology Laboratory of Anhui Province Hefei230037 China

ISBN: (纸本)9781510666337

The imaging equipment working in the atmosphere will not only be limited by the performance of the imaging system, but also be affected by turbulence. In the fields of astronomical observation, ground-based remote sensing and remote monitoring, there is an urgent need for corresponding methods and technologies to eliminate the impact of atmospheric turbulence and obtain clear images. With the development of computer technology, atmospheric optics theory and image processing technology, more and more researchers hope to combine deep learning technology with atmospheric turbulence theory to reduce the impact of turbulence on imaging and obtain clear and stable images. In this paper, a turbulence image restoration technique based on Generative Adversarial Networks(GAN) is proposed, which is divided into generator network and discriminator network. The generator network is used to convert blurred images affected by turbulence into clear images. The discriminator network is used to compare the converted image with the real clear image to determine whether the image is real or generated. After the whole GAN is optimized and trained, the image transformed by the generator and the real and clear image can not be distinguished from each other. Because the training of the GAN requires a large number of corresponding samples, it is difficult to obtain the images affected and unaffected by turbulence at the same time in real life, so this paper uses the statistical characteristics of turbulence to simulate a large number of images affected by turbulence. We used the trained GAN model to simulate turbulence image restoration and got some achievements. © 2023 SPIE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Noisy image Restoration Based on Conditional Acceleration Score Approximation

Noisy Image Restoration Based on Conditional Acceleration Sc...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Ziqiang Shi Rujie Liu Fujitsu R&D Center Beijing China

In recent years, score-based generative models (SGM) have achieved state-of-the-art (SOTA) performance in noisy image restoration [1], [2]. But at present, most of these methods are performed in the position space, and there is a lack in modeling of the velocity and acceleration of the image on the restoration path. In this paper, we propose a new image restoration method called conditional acceleration score approximation (CASA), which introduces velocity and acceleration variables on top of the data position along the recovery path. Guided by the degraded image, CASA can effectively and dynamically control the direction and speed of motion along the diffusion path in the reverse-time stochastic differential equation. Therefore, the key to this process is how to inject the degraded image as a guidance into the third-order reverse-time process in this position-velocity-acceleration space, especially in the evolution direction of the diffusion path. We propose a strategy for approximating the conditional acceleration score by decomposing the true posterior CAS into a priori CAS and an observed acceleration score for the measurement at the current moment. Experiments on 3 different datasets and 7 kinds of restoration tasks show that CASA is better than other methods and achieves a new SOTA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADVERSARIAL TRAINING WITH stochastic WEIGHT AVERAGE

ADVERSARIAL TRAINING WITH STOCHASTIC WEIGHT AVERAGE

引用

IEEE International conference on image processing (ICIP)

作者： Hwang, Joong-won Lee, Youngwan Oh, Sungchan Bae, Yuseok Elect & Telecommun Res Inst Daejeon South Korea

ISBN: (纸本)9781665441155

Although adversarial training is the most reliable method to train robust deep neural networks so far, adversarially trained networks still show large gap between their accuracies on clean images and those on adversarial images. In conventional classification problem, one can gain higher accuracy by ensembling multiple networks. However, in adversarial training, there are obstacles to adopt such ensemble method. First, as inner maximization is expensive, training multiple networks adversarially becomes overburden. Moreover, the naive ensemble faces dilemma on choosing target model to generate adversarial examples with. Training adversarial examples of the members causes covariate shift, while training those of ensemble diminishes the benefit of ensembling. With these insights, we adopt stochastic weight average methods and improve it by considering overfitting nature of adversarial training. Our method take the benefit of ensemble while avoiding the described problems. Experiments on CIFAR10 and CIFAR100 shows our method improves the robustness effectively.

关键词： Adversarial training stochastic Weight Average Ensemble Robustness Hard Example Mining

来源：评论

学校读者我要写书评

暂无评论

Bayesian Deep Unfolding with Graph Attention for Dual-Peak Single-Photon Lidar Imaging

Bayesian Deep Unfolding with Graph Attention for Dual-Peak S...

引用

European Signal processing conference (EUSIPCO)

作者： JaKeoung Koo Abderrahim Halimi Stephen McLaughlin School of Computing Gachon University Seongnam South Korea School of Engineering and Physical Sciences Heriot-Watt University Edinburgh UK

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Single-photon Lidar is a promising 3D imaging technique, but it is challenging to deploy in real-world applications due to high noise levels and the presence of multiple surfaces per pixel. Existing statistical methods are interpretable, but limited by the assumed model. Data-driven approaches show excellent performance, but with limited interpretability, preventing their use in critical applications. In this paper, we propose an interpretable deep learning architecture with graph attention networks for the reconstruction of dual peaks per pixel in single photon Lidar. Instead of the conventional image-based representation, we represent the solution as point clouds, allowing reconstruction of more than one surface per pixel. The proposed architecture is based on a statistical Bayesian algorithm, whose iterative steps are converted into neural network layers. This approach combines the advantages of both statistical and learning-based frameworks, providing good estimates with improved network interpretability. Experimental results demonstrate the effectiveness of the proposed method.

关键词： Point cloud compression Surface reconstruction Laser radar Three-dimensional displays statistical analysis Imaging Signal processing algorithms Signal processing Bayes methods image reconstruction

来源：评论

学校读者我要写书评

暂无评论

TransDocUNet: A Transformer-based UNet Architecture for Degraded Document image Binarization 14

TransDocUNet: A Transformer-based UNet Architecture for Degr...

引用

14th Indian conference on Computer Vision, Graphics and image processing, ICVGIP 2023

作者： Biswas, Risab Sarkhel, Soumik Roy, Swalpa Kumar Pal, Umapada Optiks Innovations Pvt. Ltd. Maharashtra Mumbai India Alipurduar Government Engineering and Management College West Bengal India Indian Statistical Institute West Bengal Kolkata India

ISBN: (纸本)9798400716256

The enhancement of historical document images is critical for improving the quality and legibility of scanned or captured document images. Convolutional-based techniques previously generated competitive results for document image binarization, however, due to their inherent locality, these models are often limited in explicitly expressing long-range dependency. Transformers (ViT) have evolved as an alternative design with a global self-attention mechanism to tackle this issue, however, they can result in restricted localization capabilities due to a lack of low-level details. To address this problem, we propose TransDocUNet, a CNN-Transformer hybrid UNet architecture for document image binarization that merits both attention and convolution capabilities in a U-Net architecture and serves as a strong alternative to the existing solutions. The experimental results, obtained using the DIBCO/H-DIBCO datasets, highlight that our proposed method outperforms all the existing competing methods in terms of both objective quality metrics and visual quality assessment, achieving state-of-the-art performance in document image binarization. In addition, we undertake an ablation study to understand the role of dilation in the CNN to capture feature dependencies while reducing the computational cost as well. The findings helped us arrive at the final model and provide valuable insights into the importance of acquiring both global and local contextual information for tasks like enhancing document images. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

PATCH STEGANALYSIS: A SAMPLING BASED DEFENSE AGAINST ADVERSARIAL STEGANOGRAPHY 47

PATCH STEGANALYSIS: A SAMPLING BASED DEFENSE AGAINST ADVERSA...

引用

47th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Qin, Chuan Zhao, Na Zhang, Weiming Yu, Nenghai Univ Sci & Technol China Sch Cyber Sci & Technol Beijing Peoples R China Chinese Acad Sci Key Lab Electromagnet Space Informat Beijing Peoples R China

ISBN: (纸本)9781665405409

In recent years, the classification accuracy of CNN (convolutional neural network) steganalyzers has rapidly improved. However, as general CNN classifiers will misclassify adversarial samples, CNN steganalyzers can hardly detect adversarial steganography, which combines adversarial samples and steganography. Adversarial training and preprocessing are two effective methods to defend against adversarial samples. But literature shows adversarial training is ineffective for adversarial steganography. Steganographic modifications will also be destroyed by preprocessing, which aims to wipe out adversarial perturbations. In this paper, we propose a novel sampling based defense method for steganalysis. Specifically, by sampling image patches, CNN steganalyzers can bypass the sparse adversarial perturbations and extract effective features. Additionally, by calculating statistical vectors and regrouping deep features, the impact on the classification accuracy of common samples is effectively compressed. The experiments show that the proposed method can significantly improve the robustness against adversarial steganography without adversarial training.

关键词： Steganalysis adversarial steganography sampling image patch

来源：评论

学校读者我要写书评

暂无评论

Speckle correlometry processing algorithms in application to randomly inhomogeneous media study

Speckle correlometry processing algorithms in application to...

引用

2022 International conference Laser Optics, ICLO 2022

作者： Isaeva, E.A. Isaeva, A.A. Zimnyakov, D.A. Yuri Gagarin Saratov State Technical University Saratov Russia Institute of Precision Mechanics and Control Ras Saratov Russia

ISBN: (数字)9781665466646

ISBN: (纸本)9781665466646

The modern coherent-optical methods based on the processing of the detected multiple-scattered by randomly inhomogeneous media signals. The statistical analysis of the stochastic intensity distributions caused by the multiple scattered radiation (evaluating such characteristic as flicker index, contrast, structural and correlation functions, etc.) give the opportunity to evaluate the structural morphology of the investigate media (concentration and shape of inhomogeneities, features of the organization of the structure) and the dynamic processes occurring inside the media. In this work the investigation of the water solutions of technical or food gelatin with added TiO2 nanoparticles and foamy phantoms by use of the full field speckle correlometry method is represented. © 2022 IEEE.

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Optimality of variational inference for stochastic block model with missing links 35

Optimality of variational inference for stochastic block mod...

引用

35th Annual conference on Neural Information processing Systems (NeurIPS)

作者： Gaucher, Solenne Klopp, Olga Univ Paris Saclay Dept Math Orsay Orsay France ESSEC Business Sch Cergy France CREST ENSAE Palaiseau France

ISBN: (纸本)9781713845393

Variational methods are extremely popular in the analysis of network data. statistical guarantees obtained for these methods typically provide asymptotic normality for the problem of estimation of global model parameters under the stochastic block model. In the present work, we consider the case of networks with missing links that is important in application and show that the variational approximation to the maximum likelihood estimator converges at the minimax rate. This provides the first minimax optimal and tractable estimator for the problem of parameter estimation for the stochastic block model with missing links. We complement our results with numerical studies of simulated and real networks, which confirm the advantages of this estimator over current methods.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Stable Test-Time Training for Semantic Segmentation with Output Contrastive Loss

Stable Test-Time Training for Semantic Segmentation with Out...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yunlong Zhang Zhongyi Shui Honglin Li Yuxuan Sun Chenglu Zhu Lin Yang Zhejiang University Hangzhou China Westlake University Hangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep learning-based models have achieved impressive performance on public segmentation benchmarks, yet generalizing to unseen environments remains challenging. Test-time training (TTT) addresses this by adapting source-pretrained models during evaluation. While existing TTT methods have shown promise in image classification, they often exhibit instability with small test batches and class imbalance—challenges that intensify in semantic segmentation tasks. To tackle this issue, we present Output Contrastive Loss (OCL) to improve the stability of contrastive loss when applied to TTT for segmentation. OCL applies contrastive loss directly to the output space, avoiding the need for extra regularization, and employs a high temperature to prevent model collapse. To further stabilize the TTT process, we integrate BN statistics Modulation and stochastic Restoration techniques. Extensive experiments across diverse datasets, settings, architectures, and pretrained methods demonstrate consistent performance improvements, achieving a 7.5 mIoU gain on the GTA→CS benchmark and showing effectiveness even with domain adaptation pretraining. Code is available at https://***/dazhangyul23/OCL.

关键词： Training Adaptation models Semantic segmentation stochastic processes Modulation Benchmark testing Stability analysis image restoration Speech processing Thermal stability

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472页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：