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

4,146 篇 会议
73 篇 期刊文献
10 册 图书

馆藏范围

4,229 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,938 篇 工学
- 2,152 篇 计算机科学与技术...
- 1,311 篇 软件工程
- 717 篇 信息与通信工程
- 481 篇 电气工程
- 452 篇 光学工程
- 398 篇 生物医学工程（可授...
- 350 篇 生物工程
- 287 篇 控制科学与工程
- 203 篇 电子科学与技术（可...
- 188 篇 机械工程
- 188 篇 仪器科学与技术
- 128 篇 测绘科学与技术
- 120 篇 化学工程与技术
- 111 篇 材料科学与工程（可...
- 99 篇 土木工程
- 89 篇 建筑学
- 82 篇 航空宇航科学与技...
- 81 篇 环境科学与工程（可...
- 71 篇 安全科学与工程
- 68 篇 网络空间安全
1,312 篇 理学
- 521 篇 数学
- 512 篇 物理学
- 384 篇 生物学
- 173 篇 统计学（可授理学、...
- 139 篇 化学
488 篇 管理学
- 285 篇 图书情报与档案管...
- 223 篇 管理科学与工程(可...
445 篇 医学
- 364 篇 临床医学
- 187 篇 基础医学(可授医学...
- 134 篇 药学(可授医学、理...
71 篇 农学
64 篇 法学
25 篇 经济学
23 篇 教育学
12 篇 艺术学
10 篇 军事学
7 篇 文学
1 篇 哲学

主题

281 篇 image reconstruc...
238 篇 image segmentati...
214 篇 feature extracti...
188 篇 deep learning
180 篇 data mining
170 篇 image processing
133 篇 image classifica...
126 篇 training
118 篇 convolutional ne...
110 篇 accuracy
106 篇 data models
92 篇 image recognitio...
88 篇 image enhancemen...
81 篇 remote sensing
73 篇 image analysis
72 篇 computer vision
68 篇 image color anal...
65 篇 machine learning
63 篇 computational mo...
61 篇 visualization

机构

13 篇 chitkara univers...
12 篇 chitkara univ in...
6 篇 school of comput...
6 篇 chitkara univers...
6 篇 school of data a...
5 篇 vishwakarma inst...
5 篇 graphic era deem...
5 篇 uttaranchal univ...
4 篇 beijing institut...
4 篇 china academy of...
4 篇 chennai
4 篇 wuhan univ sch r...
4 篇 center for earth...
4 篇 univ chinese aca...
4 篇 computer science...
4 篇 geomatics engine...
4 篇 cccc big data te...
4 篇 university of ch...
4 篇 sun yat sen univ...
4 篇 waseda universit...

作者

8 篇 li jonathan
7 篇 wang cheng
7 篇 zhang wei
6 篇 sharma neha
6 篇 li li
6 篇 wang wei
6 篇 wang yan
6 篇 li yan
6 篇 chen yen-wei
5 篇 wang jing
5 篇 gupta rupesh
5 篇 b. solaiman
5 篇 m.s. bouhlel
5 篇 rueckert daniel
5 篇 zhang jun
4 篇 vibhute amol d.
4 篇 zhang lei
4 篇 gill kanwarparta...
4 篇 xie bin
4 篇 chen chen

语言

4,038 篇 英文
168 篇 其他
33 篇 中文
2 篇 法文
1 篇 泰文

检索条件"任意字段=2nd Conference on Image Reconstruction from Incomplete Data"

共 4229 条记录，以下是421-430 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：

Moral Storytelling Model Using Artificial Intelligence-Driven image-to-Text Synthesis 2

Moral Storytelling Model Using Artificial Intelligence-Drive...

引用

2nd IEEE International conference on data Science and Network Security, ICDSNS 2024

作者： Rao, Abhishek S. Rakesh Kumar, B. Ranganatha, K. Poojary, Ramaprasad Karthik Pai, B.H. Lisa Bojamma, M.S. Jaleesh, Jeeva Nmam Institute of Technology Department of Information Science and Engineering Nitte India St. Aloysius Deemed to Be University Department of M.Sc Big Data Analytics Aimit Mangaluru India Canara Engineering College Department of Information Science & Engineering Benjanapadavu India School of Engineering & It Manipal Academy of Higher Education Dubai United Arab Emirates

ISBN: (纸本)9798350373110

Artificial intelligence in storytelling often struggles with conveying complex moral narratives due to its reliance on short and simplistic captions. This study introduces a novel approach to overcome this challenge by developing a model designed to craft more extensive and profound moral stories. Utilizing unsupervised deep learning techniques, the proposed model autonomously learns from a diverse corpus of short stories and images to generate extended narratives without requiring explicit human guidance. The study highlights three primary contributions: the creation of an autonomous model for generating moral stories with minimal human intervention, the development of a substantial reservoir of moral narratives for comprehensive training, and the empirical validation of the model's superior ability to produce innovative and captivating stories compared to existing methodologies. The proposed model exhibits remarkable accuracy, achieving 91.0% on the COCO dataset and 88% on the Flickr30K dataset, outperforming models such as Encoder-Decoder, Informative Cross-modal, LSTM, and AESOP. Additionally, the model's performance was evaluated using the BLEU and CIDEr scores, yielding 0.81 and 0.75, respectively. This model not only enhances the depth and quality of AI-generated moral stories but also has potential applications in education, entertainment, and virtual assistants, providing richer and more engaging content for users. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved Pattern Recognition Techniques for Monitoring Human Activity Recognition in Digital Platforms through image Processing Techniques 2

Improved Pattern Recognition Techniques for Monitoring Human...

引用

2nd International conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Sumathi, V. Vanathi, D. Musale, Jitendra Chandrakant Gowtham Prasad, T.V.S. Singh, Amit Raj Sri Sai Ram Engineering College Department of Mathematics Chennai44 India Nandha Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Shri Jagdishprasad Jhabarmal Tibrewala University University in Jhunjhunu Department of Computer Science and Engineering Rajasthan India Sree Vidyanikethan Engineering College Department of Ece Andhra Pradesh India Graphic Era Hill University Department of Physics Dehradun India

ISBN: (纸本)9798350325799

With the rapid advancement of digital platforms and the increasing prevalence of visual data, the need for accurate and efficient human activity recognition has become paramount. In this paper, a novel approach that leverages image processing and hybrid deep learning techniques to enhance pattern recognition for monitoring human activity in digital platforms is proposed. The proposed framework begins with a sensor-captured image to the preprocessing step where raw image data is cleaned, normalized, and transformed into suitable feature representations. Various image processing techniques such as image enhancement, noise reduction, and feature extraction are employed to enhance the discriminative power of the input data. A hybrid deep learning architecture is developed that combines the benefits of various deep learning models to accomplish robust and accurate human activity recognition. Convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention mechanisms are specifically combined to extract both spatial and temporal information from the input images. The CNNs are in charge of picking up spatial features, while the RNNs and attention mechanisms, respectively, record temporal relationships and emphasize significant areas in the images. To train and evaluate the proposed framework, large-scale datasets containing diverse human activities are utilized. Experimental results demonstrate the superior performance of the proposed approach compared to state-of-the-art methods in terms of accuracy, precision, and recall. The hybrid deep learning architecture effectively handles complex human activity recognition tasks, accurately identifying and categorizing various activities in digital platforms. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Coherent Integration with Multi-pass Synthetic Aperture Radar images 2

Coherent Integration with Multi-pass Synthetic Aperture Rada...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Hu, Zihan Li, Gen Wang, Yifan Sun, Chuanxv Zhai, Yiming Dong, Zehua Beijing Institute of Technology School of Information and Electronics Beijing China

ISBN: (纸本)9798331515669

Synthetic aperture radar (SAR) can be used to acquire high-resolution images of huge areas and has been widely used in planetary exploration. However, in earth-based SAR imaging of the moon, the effect of additive noise is not ignorable and the restricted temporal window for single observation limits the potential for image denoising through integration methods. To address this issue, a method to achieve coherent integration with multi-pass SAR images for additive noise removal is proposed. The proposed method achieves envelope alignment through sub-pixel level image registration and phase alignment by compensating the flat earth phase and topographic phase, thus satisfying the requirement of coherent integration. The signal-to-noise (SNR) gain resulting from this method is given by a function of the correlation. The effectiveness of the method and the correctness of the function are verified by the simulation experiments. © 2024 IEEE.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised image Segmentation Workflow for Extraction of Left Coronary Artery from X-Ray Coronary Angiography 1

引用

2nd Serbian International conference on Applied Artificial Intelligence (SICAAI)

作者： Dasic, Lazar Pavic, Ognjen Geroski, Tijana Filipovic, Nenad Univ Kragujevac Inst Informat Technol Jovana Cvijica Bb Kragujevac 34000 Serbia Bioengn Res & Dev Ctr BioIRC Prvoslava Stojanovica 6 Kragujevac 34000 Serbia Univ Kragujevac Fac Engn Sestre Janjic 6 Kragujevac 34000 Serbia

ISBN: (数字)9783031608407

ISBN: (纸本)9783031608391;9783031608407

Coronary heart disease (CHD) is a serious cardiovascular illness that is among the top causes of death worldwide. Using X-ray coronary angiography, it is possible to detect and monitor CHD by visualizing coronary vessels. One of the most important steps in analyzing angiographic images is image segmentation, where the coronary arteries are separated from the background. In this paper, we propose an unsupervised image segmentation workflow that uses different filters in order to minimize the limitations of X-ray coronary angiography and achieve satisfactory segmentation of the left coronary artery. During the preprocessing step, the X-ray angiographic image of the coronary artery is processed with CLAHE, the Wiener filter and gamma correction in order to overcome the shortcomings of the X-ray imaging data. These preprocessing steps greatly reduce the background noise and improve the separation of the artery from the rest of the image. The preprocessed image is then segmented using Otsu's thresholding method, which results in a binarized image. This image has left coronary artery successfully segmented, but unfortunately a lot of non-vessel segments have been wrongly labeled as well. In the postprocessing step, connected components are obtained, and then using information about their size the largest connected component represents a segmented left coronary artery, while the rest is marked as background.

关键词： left coronary artery unsupervised image segmentation x-ray coronary angiography

来源：评论

学校读者我要写书评

暂无评论

image Editing based on Diffusion Model for Remote Sensing image Change Captioning 2

Image Editing based on Diffusion Model for Remote Sensing Im...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Cai, Miaoxin Chen, He Li, Can Gan, Shuyu Chen, Liang Zhuang, Yin Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

Remote Sensing image Change Captioning (RSICC) is a task that utilizes natural language to describe changes in remote sensing images of the same area captured at different times. However, the significant temporal intervals between multi-temporal images, the infrequency of observable changes, and the limitations on observation locations make it difficult to acquire and annotate a large and diverse dataset for analyzing change in multi-temporal images. The scarcity of labeled data hinders the training of RSICC models, leading to poor generalization. Compared to annotated registered bi-temporal image, single-temporal data is easier to obtain. Therefore, to tackle the issue of poor generalization of RSICC models under limited annotated sample conditions, a text-guided image pairs generation (TGIPG) method is proposed to create synthetic RSICC datasets from single-temporal data and randomly sampled text instructions via a diffusion-based controllable image editing model. This approach generates more valid pairs of multi-temporal samples to address the constraints of limited change information. Specifically, this method utilizes language instructions to introduce change information into the diffusion process, gradually transforming the pre-phase image into the post-phase image. Our experiments on the LEVIR-CC dataset show that synthetic data can significantly enhance the performance of any RSICC model, with a restricted number of training samples, by employing this plug-and-play TGIPG method. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Unified image Restoration with Convolutional Autoencoder 2

Unified Image Restoration with Convolutional Autoencoder

引用

2nd International conference on Networking, Communications and Information Technology, NetCIT 2022

作者： Liu, Yuanzhu Li, Chuang Zhao, Yong Xu, Junli School of Mathematical Sciences Ocean University of China Qingdao China School of Mathematics and Physics Qingdao University of Science and Technology Qingdao China

ISBN: (纸本)9781665492737

Convolutional autoencoders are widely used in image processing, and have achieved remarkable success. This paper proposes a unified framework for image restoration problems based on convolutional autoencoder. Our framework can deal with denoising, dehazing, and text elimination effectively. For each problem, we train a restoration model by establishing a mapping between a set of corrupted images and their corresponding clean images. These models are obtained in a data-driven manner, which are simple and practical for these restoration problems. A variety of experiments show that the proposed framework can generate satisfactory results even under high corruptions. © 2022 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Spider Monkey Optimization-Based image data Forgery Detection Over Vehicular Cloud Computing 2nd

Spider Monkey Optimization-Based Image Data Forgery Detectio...

引用

2nd International conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Manasa, M. Chaudhari, Shilpa S. Ramaiah Institute of Technology Bangalore India Visvesvaraya Technological University Karnataka Belagavi India

ISBN: (纸本)9789819977109

images are commonly shared through various mediums such as newspapers, magazines, Internet, and scientific journals. But with the accessibility of software like Photoshop, GIMP, and Coral Draw, it has become increasingly difficult to differentiate between an original and a forged image. Traditional methods for detecting image forgery rely on handcrafted features, but they are limited in their ability to identify specific types of tampering based on certain features in the image. To overcome this obstacle, deep learning methods have been employed. Increased vehicular networking image data faces this challenge. The proposed image forgery detection uses hybrid model of convolution neural networks (CNN), spider monkey optimization technique (SMO), and support vector machines (SVMs). CNN extracts deep semantic features of images transferred as vehicular data over the vehicular cloud using error level analysis (ELA) techniques. SMO chooses the optimal features from deep semantic features. Binary classifications based on SVM provide whether the image is original or forged. The results demonstrate that the proposed method achieves a recognition accuracy of 96%, which is significantly higher than the same model without SMO, which achieved an accuracy of 93%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Advancing Age Estimation from Facial images Using Deep Learning Approaches and Ethical Considerations 2

Advancing Age Estimation from Facial Images Using Deep Learn...

引用

2nd International conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Jayadharshini, P. Vasuki, C. Santhiya, S. Sudharshan, S. Sudheksha, K. Rithanya, M. Department of Artificial Intelligence Kongu Engineering College Tamilnadu Perundurai Erode India Department of Information Technology Nandha Engineering College Tamilnadu Erode India

ISBN: (纸本)9798331541217

Estimation of age from facial images is an important application in various fields, like biometrics, forensics, and personalized healthcare. The proposed work investigated the use of a machine learning approach to predict human age from facial features only, obtained from images. Our method used Convolutional Neural Networks (CNNs) in feature extraction and then combined regression models for age estimation. The used dataset is images of faces from different demographic groups, which makes the model robust and generalizable. All critical challenges related to variations in lighting, facial expression, and age distribution are adequately covered. The preprocessing steps, which include normalization and data augmentation, were properly applied to improve the performance of the models and reduce overfitting. Measures to report on prediction accuracy are also reported by using metrics such as Mean Absolute Deviation (MAD) and Root Mean Square Deviation (RMSD). The approach CNN-based shows a higher accuracy and computation rate compared to the baseline methods. Additionally, it presents practical applications of the models in missing people cases or for age-sensitive services. Ethical concerns such as privacy and control of bias are also of high concern and thus point to the need for clear and equitable use of such technology. This research seriously tests deep learning and shows its effectiveness in improving the estimation of age from facial images, providing important insights in relation to biometric solutions and more. © 2024 IEEE.

关键词： Age Estimation Convolutional Neural Networks (CNN) Facial Recognition image processing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Segmentation of Thyroid Nodules: An Enhancement Deep Neural Network Framework 2

Ultrasound Segmentation of Thyroid Nodules: An Enhancement D...

引用

2nd International conference on Electrical Engineering and Automatic Control (ICEEAC)

作者： Bouhdiba, Kamar Meddeber, Lila Meddeber, Mohammed Zouagui, Tarik Univ Sci & Technol Oran Mohamed Boudiaf USTO MB Signals Syst & Data Lab LSSD Oran Algeria Univ Sci & Technol Oran Mohamed Boudiaf USTO MB Intelligent Syst Res Lab LARESI Oran Algeria Univ Sci & Technol Oran Mohamed Boudiaf USTO MB Elect Dept Oran Algeria Univ Hosp Ctr Oran Mohamed Boudiaf CHUO Radiol Dept Oran Algeria

ISBN: (纸本)9798350349740;9798350349757

Thyroid nodules are prevalent in the human population, often identified during routine ultrasound examinations. Accurate segmentation of these nodules is crucial for diagnosing and managing potential thyroid malignancies. Nevertheless, the accurate delineation of intricate thyroid tissue poses a significant challenge attributable to the inadequate contrast and substantial noise present in ultrasound imagery. Several traditional segmentation approaches to detect thyroid nodules suffer from imprecise localization issues, while deep learning techniques offer promising solutions. This study proposes a new deep hybrid architecture that combines the encoder-decoder structure of UNet with residual blocks to enhance the model's capacity for identifying thyroid nodules. The proposed approach demonstrates the impact of introducing residual blocks to UNet architecture, and its capability to effectively capture both local and global information for accurate image segmentation because it is particularly important in thyroid nodule segmentation. The model was trained and verified using the public TN3K dataset, which consists of 3493 thyroid nodule images. Our approach was found to significantly improve the accuracy of semantic segmentation, achieving 93.56% with an IOU of 94.97% compared to state-of-the-art methods.

关键词： Ultrasound imaging thyroid nodules artificial intelligence deep learning convolutional neural networks (CNN)

来源：评论

学校读者我要写书评

暂无评论

Generative Inpainting for Shapley-Value-Based Anomaly Explanation 2nd

Generative Inpainting for Shapley-Value-Based Anomaly Explan...

引用

2nd World conference on Explainable Artificial Intelligence (xAI)

作者： Tritscher, Julian Lissmann, Philip Wolf, Maximilian Krause, Anna Hotho, Andreas Schloer, Daniel CAIDAS Ctr Artificial Intelligence & Data Sci Wurzburg Germany Julius Maximilians Univ Wurzburg Wurzburg Germany Coburg Univ Appl Sci Coburg Germany

ISBN: (纸本)9783031637865;9783031637872

Feature relevance explanations currently constitute the most used type of explanation in anomaly detection related tasks such as cyber security and fraud detection. Recent works have underscored the importance of optimizing hyperparameters of post-hoc explainers which show a large impact on the resulting explanation quality. In this work, we propose a new method to set the hyperparameter of replacement values within Shapley-value-based post-hoc explainers. Our method leverages ideas from the domain of generative image inpainting, where generative machine learning models are used to replace parts of a given input image. We show that these generative models can also be applied to tabular replacement value generation for Shapley-value-based feature relevance explainers. Experimentally, we train a denoising diffusion probabilistic model for generative inpainting on two tabular anomaly detection datasets from the domains of network intrusion detection and occupational fraud detection, and integrate the generative inpainting model into the SHAP explanation framework. We empirically show that generative inpainting may be used to achieve consistently strong explanation quality when explaining different anomaly detectors on tabular data.

关键词： Feature Relevance XAI SHAP Diffusion Perturbation

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423页 << < 39 40 41 42 43 44 45 46 47 48 > >>

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：