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

171 篇 会议
7 篇 期刊文献
3 册 图书

馆藏范围

181 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

116 篇 工学
- 100 篇 计算机科学与技术...
- 72 篇 软件工程
- 39 篇 光学工程
- 35 篇 信息与通信工程
- 19 篇 生物工程
- 12 篇 化学工程与技术
- 11 篇 电气工程
- 11 篇 控制科学与工程
- 10 篇 生物医学工程（可授...
- 8 篇 安全科学与工程
- 5 篇 力学（可授工学、理...
- 4 篇 交通运输工程
- 3 篇 仪器科学与技术
- 3 篇 材料科学与工程（可...
- 3 篇 电子科学与技术（可...
- 3 篇 建筑学
- 3 篇 土木工程
- 3 篇 航空宇航科学与技...
75 篇 理学
- 43 篇 物理学
- 38 篇 数学
- 19 篇 生物学
- 12 篇 化学
- 6 篇 统计学（可授理学、...
17 篇 管理学
- 13 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
10 篇 医学
- 9 篇 临床医学
- 6 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
5 篇 法学
- 5 篇 社会学
4 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 文学
1 篇 军事学

主题

38 篇 computer vision
16 篇 feature extracti...
15 篇 deep learning
13 篇 accuracy
12 篇 computational mo...
11 篇 image segmentati...
8 篇 object detection
7 篇 convolution
7 篇 partial differen...
6 篇 variational meth...
6 篇 transformers
6 篇 training
5 篇 image enhancemen...
5 篇 face recognition
5 篇 visualization
5 篇 image color anal...
5 篇 attention mechan...
4 篇 image edge detec...
4 篇 semantics
4 篇 image processing

机构

4 篇 univ saarland fa...
4 篇 department of ma...
3 篇 school of comput...
3 篇 school of comput...
3 篇 department of bi...
2 篇 computer and inf...
2 篇 school of comput...
2 篇 polytechnic inst...
2 篇 tel aviv univ de...
2 篇 faculty of elect...
2 篇 school of comput...
2 篇 wuhan university...
2 篇 department of co...
2 篇 univ mannheim de...
2 篇 seqwater brisban...
2 篇 modern finance i...
2 篇 computer science...
2 篇 guizhou mobile i...
2 篇 institute of int...
2 篇 computer vision ...

作者

7 篇 weickert joachim
5 篇 duits remco
5 篇 kimmel ron
4 篇 sochen nir
3 篇 hu xiaojuan
3 篇 weickert j
2 篇 unsalan cem
2 篇 bresson xavier
2 篇 farhaoui yousef
2 篇 vandergheynst pi...
2 篇 zhao jie
2 篇 thiran jean-phil...
2 篇 beril sirmaçek
2 篇 wang da-han
2 篇 bruhn andres
2 篇 cem ünsalan
2 篇 sirmacek beril
2 篇 pock thomas
2 篇 solem jan erik
2 篇 kleefeld andreas

语言

179 篇 英文
2 篇 其他

检索条件"任意字段=5th International Conference on Scale-Space and PDE Methods in Computer Vision"

共 181 条记录，以下是91-100 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：

A Multi-Layer Attention Network for Visual Commonsense Reasoning 5

A Multi-Layer Attention Network for Visual Commonsense Reaso...

引用

5th international conference on Data Science and Information Technology, DSIT 2022

作者： Zhang, Wenqi Gao, Yongchao Qian, Heng Lyu, Hongli School of Computer Science and Technology Qilu University of Technology Jinan China Jinan China Lakehead University Thunder Bay Department of Engineering Canada

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

Visual Commonsense Reasoning (VCR) is a challenging multimodal task involving several research fields such as vision, cognition, and reasoning, which combines images and natural language for reasoning. Existing VCR methods focus on global attention or use pre-training models, but these methods lack attention to local features of visual and language. In this paper, a multi-layer attention network is proposed for the VCR task, including an intra-modal attention module and an inter-modal attention module. the intra-modal attention module complements important features of visual and language modalities with fine-grained visual attention to improve the relevance of visual and language. the inter-modal attention module captures the internal dependencies between visual and language. Finally, the two modules are integrated into an end-to-end reasoning framework. Experiments on the VCR large-scale dataset show that the proposed method exhibits a decent improvement in the VCR task and illustrates the effectiveness of the method on three subtasks. © 2022 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Multi-scale network combined with multi-loss optimization for low-light image super-resolution reconstruction 5

Multi-scale network combined with multi-loss optimization fo...

引用

5th international conference on computer vision and Data Mining, ICCVDM 2024

作者： Liu, Bofeng Yu, Haiyang Hu, Xiaojuan Li, Yanfeng School of Computer Science and Technology Changchun University of Science and Technology Jilin Changchun130022 China Key Laboratory of Photoelectric Measurement & Control and Optical Information Transfer Technology Ministry of Education Changchun University of Science and Technology Jilin Changchun130022 China

ISBN: (纸本)9781510682863

the proposed super resolution reconstruction method aims to address the issues of missing detailed information in low light environments and poor recovery of high frequency details in reconstructed images. To fully extract the retained features of low-light images, a multi-scale feature fusion learning network is introduced, which utilizes convolution to extract shallow features and then extracts deep features through multiple cascaded multi-scale feature extraction modules. Additionally, an attention mechanism is incorporated to adaptively learn the importance of each channel and finally fuse the obtained shallow and multi-scale features. Furthermore, perceptual loss and edge loss are integrated into the loss function to optimize the network for high frequency texture details in the recovered image. Experimental results demonstrate that this method yields clearer edge structures and texture details after super-resolution reconstruction of images acquired in low light environments, outperforming other existing methods both visually and objectively. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Geodesic Tracking of Retinal Vascular Trees with Optical and TV-Flow Enhancement in SE(2) 9th

Geodesic Tracking of Retinal Vascular Trees with Optical a...

引用

9th international conference on scale space and Variational methods in computer vision, SSVM 2023

作者： van den Berg, Nicky J. Zhang, Shuhe Smets, Bart M. N. Berendschot, Tos T. J. M. Duits, Remco CASA Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands Ophthalmology Department Maastricht University Maastricht Netherlands

ISBN: (纸本)9783031319747

Retinal images are often used to examine the vascular system in a non-invasive way. Studying the behavior of the vasculature on the retina allows for noninvasive diagnosis of several diseases as these vessels and their behavior are representative of the behavior of vessels throughout the human body. For early diagnosis and analysis of diseases, it is important to compare and analyze the complex vasculature in retinal images automatically. In previous work, pde-based geometric tracking and pde-based enhancements in the homogeneous space of positions and orientations have been studied and turned out to be useful when dealing with complex structures (crossing of blood vessels in particular). In this article, we propose a single new, more effective, Finsler function that integrates the strength of these two pde-based approaches and additionally accounts for a number of optical effects (dehazing and illumination in particular). the results greatly improve both the previous left-invariant models and a recent data-driven model, when applied to real clinical and highly challenging images. Moreover, we show clear advantages of each module in our new single Finsler geometrical method. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Application of the deep learning approach for identification and face recognition in real-time video 5

Application of the deep learning approach for identification...

引用

5th international conference on Intelligent Systems and computer vision, ISCV 2022

作者： El Hadi, Moulay Lhabib Nasri, M'Barek Farhaoui, Yousef Ellaoui, Ahmad Mohammed I University MATSI EST - Oujda BP 717 Oujda60000 Morocco Moulay Ismail University Faculty of sciences and Technic Department of Computer Science B.P 509 Boutalamine Errachidia Morocco

ISBN: (纸本)9781665495585

the use of facial recognition technology has increased strongly during the past period by many countries in many areas, and this technology has become the most secure tool at the level of countries, institutions, or on a personal level, as this technology is considered one of the modern systems for identifying people in digital images or frames Video. these systems do not need any dependencies such as key and card but only a facial image is needed. Many methods have been created and developed in order to perform face detection. One of the most popular methods is the ViolaJones Haar Cascade Classifier(V-J). But this method has several limitations in front of the following factors: across scale, non-frontal face, and low light intensity. In this article, we propose a classifier based on the Histogram of the Oriented Gradients (HOG) algorithm through deep learning that solves the previous limits. Experimental results are provided to demonstrate the robustness and accuracy of our system © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Road detection from remotely sensed images using color features

Road detection from remotely sensed images using color featu...

引用

international conference on Recent Advances in space Technologies

作者： Sirmacek, Beril Unsalan, Cem Remote Sensing Technology Institute Weling 82234 Germany Computer Vision Research Laboratory Yeditepe University Istanbul 34755 Turkey

ISBN: (纸本)9781424496143

Urban regions are dynamic environments. Especially their road maps change by the expansion of the urban region. therefore, automatic detection of roads from very high resolution aerial and satellite images is a very important research field. Unfortunately, the solution is not straightforward by using basic image processing and computer vision algorithms. therefore, advanced methods are needed for road network detection from aerial and satellite images. In this study, we propose a novel method for automatic detection of road segments from very high resolution color aerial and satellite images. Our method depends on choosing a training set from the input image manually. We use color chroma values of pixels as the discriminative features. Since road pixels have similar color characteristics, the distribution of color chroma feature values of the training region have a peak at a certain point in the feature space which shows the road class. Using this information and one-class classification methodology, we label road segments in a given remotely sensed image. Finally, we fit a road network shape on the detected segment. Experimental results on color aerial and Ikonos satellite images show the importance of color features in road detection applications. © 2011 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Mapping fMRI voxel activations to CNN feature space for ease of categorization 5

Mapping fMRI voxel activations to CNN feature space for ease...

引用

5th international conference on Informatics and Computing, ICIC 2020

作者： Krishnamurthy, Bhargav Subramanian, Sudha Anna University Ceg Campus Department of Computer Science and Engineering Chennai600025 India

ISBN: (纸本)9781728180472

We observe the impact of using category averaged feature vectors as intermediaries in predicting object categories from fMRI(Functional Magnetic Resonance Imaging) voxel activations. the validation accuracy of state-of-art prediction methods falls drastically when multiple classes are used at the same time, pointing towards the overlapping nature of representations in the voxel activations. To overcome this disadvantage, we map these overlapping representation to a more separable representation. the equivalent of these representations in the field of computer vision is a Convolutional Neural Network(CNN) feature vector. After taking into consideration the structural trade-offs the Ventral Temporal Cortex possesses to achieve efficient categorization, we designed a model whose architecture tries to mimic these functional nuances. there are two parts to the implementation - Estimation of feature vectors and efficient category prediction from the estimated feature vectors. We inspected the perceptual similarity of the estimated feature vectors by the use of Annoy tree. We found that Deep ReLU-MLP(Rectified Linear Unit-Multilayer Perceptron) performs better at decoding fMRI voxel activations compared to Sparse Linear Regressor. While inspecting the perceptual neighborhood of the decoded feature vector, we found a significantly higher percentage of the feature vectors predicted from visual perception experiments mapped to the correct neighborhood than in the case of visual imagery experiment. © 2020 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction from Image Sensing (Remote) : Image Segmentation 5

Feature Extraction from Image Sensing (Remote) : Image Segme...

引用

5th IEEE international conference on Advances in Computing, Communication Control and Networking, ICAC3N 2023

作者： Chauhan, Kaushal Tomar, Harshit Kamal, Kushagra Goel, Pallavi Galgotias College Of Engineering And Technology Department Of Computer Science And Engineering Greater Noida India

ISBN: (纸本)9798350330861

In this research paper, an overview of computer methods for segmenting continuous-tone images into meaningful parts and characterizing these parts with 'features' is presented. Image segmentation is an essential pre-processing step in computer vision and image processing softwares. this paper discusses various techniques and algorithms used for image segmentation, including both supervised and unsupervised methods. the performance of these techniques is evaluated on different test images, and future research directions are proposed. Feature extraction from image sensing is a critical step in multimedia processing. this paper explores the process of feature extraction from remotely sensed images. With the increasing use of remote sensing technology, it is crucial to have effective and accurate methods for extracting features from remotely sensed data, which are utilized in various applications such as land-use mapping, environmental proctoring, and in natural-disaster management. this paper discusses several techniques for feature extraction, including pixel-based, object-based, and machine learning-based approaches. Additionally, it highlights the difficulties associated with feature extraction from remote sensing data, such as atmospheric effects, radiometric and geometric distortions, and the presence of noise. the paper concludes by discussing future directions in remote sensing feature extraction, including the integration of deep learning methods and the development of more robust methods has the ability of handling large-scale datasets. With the help of deep learning methods and algorithms, especially CNN's, has tremendously improved the accuracy of image scene classification. In this study, a CNN model which is already trained was utilized to fetch-out deep features from images at various network layers, including the average pooling layer. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Progressive Growing of Generative Adversarial Network for Multi-scale Masked Fusion Network in Precise 3D Medical Image Segmentation 5

Progressive Growing of Generative Adversarial Network for Mu...

引用

5th international conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Swapna, J. Kiruba, R. Roselin Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600062 India

ISBN: (纸本)9798350379945

Image segmentation is a vital computer vision technique, simplifying image representation and aiding object recognition. In medical imaging, generating 3D volumetric images involves a complex process integrating image acquisition, segmentation, and volumetric reconstruction. this work proposes a novel and comprehensive methodology, addressing challenges associated with spatial and temporal dependencies in 3D medical image synthesis. the proposed method unfolds in three stages. Firstly, a multi-label segmentation strategy is employed to meticulously delineate anatomical or pathological structures within 3D medical images, resulting in detailed 3D masks. these masks serve as foundational elements for subsequent image synthesis. Secondly, a conditional medical image generation model utilizes these masks as input conditions to produce synthetic images aligning precisely with specified labels. this ensures the portrayal of anatomical and pathological features consistent with the input segmentation. the crux of the proposed methodology lies in the third stage, involving the sequential and autoregressive generation of 3D mask sequences. this intricate process captures spatial dependencies and intricate patterns within the 3D volumetric space. Evaluation against state-of-the-art methods, including Vid2Vid, 3D-a-WGAN, and DDPM, uses metrics such as Learned Perceptual Image Patch Similarity (LPIPS) and Frechet Inception Distance (FID). Results indicate the proposed method's superiority, particularly in terms of anatomical fidelity and perceptual quality. the work contributes significantly to advancing medical image synthesis, with potential applications in pathology detection, treatment planning, and quantitative analysis. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Solving minimal surface problems on surfaces and point clouds 5

Solving minimal surface problems on surfaces and point cloud...

引用

5th international conference on scale space and Variational methods in computer vision, SSVM 2015

作者： Tenbrinck, Daniel Lozes, François Elmoataz, Abderrahim Institute for Computational and Applied Mathematics Westfälische Wilhelms-Universität Münster Einsteinstr. 62 Münster48149 Germany UMR6072 GREYC ENSICAEN Caen France

ISBN: (纸本)9783319184609

Minimal surface problems play an important role not only in physics or biology but also in mathematical signal and image processing. Although the computation of respective solutions is well-investigated in the setting of discrete images, only little attention has been payed to more complicated data, e.g., surfaces represented as meshes or point clouds. In this work we introduce a novel family of discrete total variation seminorms for weighted graphs based on the upwind gradient and incorporate them into an efficient minimization algorithm to perform total variation denoising on graphs. Furthermore, we demonstrate how to utilize the latter algorithm to uniquely solve minimal surface problems on graphs. To show the universal applicability of this approach, we illustrate results from filtering and segmentation of 3D point cloud data. © Springer international Publishing Switzerland 2015.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Landmark Localization Network for 3D Facial Point Clouds 2021

Multi-scale Landmark Localization Network for 3D Facial Poin...

引用

5th international conference on Digital Signal Processing, ICDSP 2021

作者： Guo, Longteng Ai, Danni Song, Hong Yang, Jian Laboratory of Beijing Engineering Research Center of Mixed Reality and Advanced Display School of Optics and Photonics Beijing Institute of Technology Beijing100081 China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781450389365

Facial landmark localization on 3D point clouds has been a major concern in the field of computer vision. Recent methods do not feature data containing multiple faces with large-scale variance, which has become increasingly common with the rapid development and wide application of 3D imaging technology. In this paper, we propose a Multi-scale Landmark Localization network for 3D facial point *** evaluate the proposed method on the dataset synthesized by appending and scaling the data in the public dataset BU3DFE to demonstrate the robustness and efficiency. Upon comparing the proposed method with other methods on the standard dataset BU3DFE, in which data only contain one face with smallscale variance, we find that the proposed method shows higher or comparable performance with mean localization errors of 3.34 2.19 mm. © 2021 Association for Computing Machinery. All rights reserved.

关键词： Deep learning

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19页 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：