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

3,155 篇 会议
40 篇 期刊文献
33 册 图书

馆藏范围

3,228 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,685 篇 工学
- 1,175 篇 计算机科学与技术...
- 858 篇 软件工程
- 637 篇 信息与通信工程
- 271 篇 电气工程
- 192 篇 光学工程
- 184 篇 控制科学与工程
- 181 篇 生物工程
- 133 篇 电子科学与技术（可...
- 128 篇 机械工程
- 114 篇 生物医学工程（可授...
- 108 篇 仪器科学与技术
- 70 篇 化学工程与技术
- 60 篇 网络空间安全
- 47 篇 建筑学
- 47 篇 土木工程
- 44 篇 材料科学与工程（可...
- 39 篇 安全科学与工程
800 篇 理学
- 428 篇 物理学
- 254 篇 数学
- 194 篇 生物学
- 74 篇 统计学（可授理学、...
- 69 篇 化学
- 61 篇 系统科学
335 篇 管理学
- 196 篇 图书情报与档案管...
- 157 篇 管理科学与工程(可...
- 56 篇 工商管理
180 篇 医学
- 160 篇 临床医学
- 55 篇 基础医学(可授医学...
- 43 篇 药学(可授医学、理...
65 篇 法学
- 61 篇 社会学
36 篇 教育学
24 篇 农学
23 篇 文学
16 篇 经济学
14 篇 军事学
2 篇 艺术学
1 篇 历史学

主题

489 篇 visualization
287 篇 visual communica...
201 篇 image processing
193 篇 feature extracti...
152 篇 image coding
115 篇 training
91 篇 accuracy
90 篇 semantics
88 篇 multimedia commu...
83 篇 cameras
82 篇 computer vision
81 篇 deep learning
78 篇 signal processin...
78 篇 computational mo...
78 篇 humans
78 篇 streaming media
75 篇 image segmentati...
64 篇 image reconstruc...
63 篇 wireless communi...
63 篇 image color anal...

机构

24 篇 school of commun...
21 篇 institute of ima...
20 篇 communication un...
19 篇 school of inform...
16 篇 communication un...
15 篇 school of electr...
14 篇 school of inform...
12 篇 school of inform...
12 篇 institute of ima...
8 篇 school of remote...
8 篇 lanzhou universi...
8 篇 institute of inf...
7 篇 information engi...
7 篇 communication un...
7 篇 graduate institu...
7 篇 institute of ima...
6 篇 institute of inf...
6 篇 institute for in...
6 篇 state key labora...
6 篇 peng cheng labor...

作者

25 篇 guangtao zhai
15 篇 sumei li
14 篇 xiongkuo min
11 篇 xiaokang yang
10 篇 zhenzhong chen
9 篇 zhai guangtao
9 篇 zhongpai gao
9 篇 shan liu
7 篇 lu yu
7 篇 wen gao
6 篇 ping an
6 篇 wenjun zhang
6 篇 hongliang li
6 篇 yang yang
6 篇 dorothea kolossa
6 篇 khursheed khursh...
6 篇 li yu
5 篇 jiang wei
5 篇 li zhang
5 篇 fei su

语言

3,163 篇 英文
42 篇 其他
22 篇 中文
4 篇 土耳其文

检索条件"任意字段=Conference on Visual Information Processing and Communication"

共 3228 条记录，以下是51-60 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：

Enhancing Data Security Through Cryptographic Transformation Using a Graph CNN and LSTM Based Model

Enhancing Data Security Through Cryptographic Transformation...

引用

visual Analytics and Data visualization (ICVADV), International conference on

作者： Yamini Kalva Senthil Kumar S Senthilnathan S A. Sasi Kumar Kavitha C T Srikanth Pulipeti Department of CSE (Cybersecurity & IoT) Sri Ramachandra Institute of Higher Education and Research Tamilnadu India Department of Management Studies SNS college of Technology Tamilnadu India Department of Information Technology Bannari Amman Institute of Technology Sathyamangalam Tamilnadu India Department of Computer Applications (BCA & MCA) School of Science and Computer Studies (SSCS) CMR University Karnataka India Department of ECE St. Joseph's Institute of Technology OMR Chennai Tamilnadu India Department of IT MPSTME SVKM's NMIMS University Maharashtra India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

These days, with more and more people using the internet, cloud computing, and other types of networked information systems, protecting people's and companies' privacy and security is crucial. Looking at it this way, encryption is a sort of efficient technology that can secure the transport of public information and hence satisfy these demands. The researchers achieved their objectives by making use of a wide variety of encryption methods tailored to the requirements of this area. In order to safeguard sensitive data while minimizing the possibility of assaults, it also focused on complex mathematical challenges to create an extremely complex encrypted communication mechanism. The proposed method consists of three phases, which are preprocessing, feature selection, and model training. The formulation of the sample data and group data is necessary to establish the model's setup prior to primary processing. When reducing the dimensionality of a dataset for feature selection, Principal Component Analysis (PCA) is often used. The model was trained using the GCNN-LSTM. On average, our suggested model has a 95.33% accuracy rate, which is better than competing methods such as GCNN and CNN.

关键词： Training Cloud computing Privacy Machine learning algorithms Computational modeling Feature extraction Data models Mathematical models Convolutional neural networks Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Transforming Healthcare with AI: Multimodal VQA Systems and LLMs

Transforming Healthcare with AI: Multimodal VQA Systems and ...

引用

International conference on Signal processing and communication (ICSC)

作者： Sowthika Semmandampalayam Vengatachalam Thamilselvan Rakkiannan Computer Science and Engineering Kongu Engineering College Erode India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

In Multimodal Large Language Models (LLMs), visual Question Answering in Medicine (VQA) is an essential activity that allows for clinically acceptable answers to questions concerning medical imagery. This could alleviate pressure on healthcare systems, especially in resource-limited countries. However, the medical VQA datasets available today are tiny, mostly focused on basic classification tasks, and devoid of semantic reasoning and clinical expertise. Our previous work proposed a VQA technique using three distinct relationship graphs—implicit, spatial, and semantic—based on the Medical-CXR-VQA dataset, mainly focuses on chest X-ray images that achieving 62% accuracy. By training an LLM technique, we improved label extraction accuracy to 80%. The labels were also thoroughly reviewed with two clinical specialists for greater accuracy. We then introduced a larger dataset, Medical VQA-RAD dataset (VQA-Radiology), which focuses on radiology images (including X-ray, CT scan, MRIs and Ultrasounds) that includes detailed inquiries about anomalies, locations, severity, and types. Based on this dataset, We created a novel chain-of-thought and prompt engineering bio-medical multi-modal VQA technique, refined from the Llama-3-8B model using the bespoke dataset. This approach combines curated and synthesized biological data, offering significant benefits to researchers, doctors, and biomedical professionals, by improving the comprehension and generation of content related to a wide range of biological topics.

关键词： visualization Accuracy Ultrasonic imaging Large language models Biological system modeling Medical services Question answering (information retrieval) Prompt engineering X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Bi-CANet: Bidirectional Contextual Alignment with Multimodal Decoder for Image Captioning

Bi-CANet: Bidirectional Contextual Alignment with Multimodal...

引用

Disruptive Technologies (ICDT), International conference on

作者： Himanshu Sharma Devanand Padha Yashwant Singh School of CSET Bennett University Greater Noida India Department of CSE Model Institute of Engineering and Technology Jammu India Department of CSIT Central University of Jammu Jammu India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Image captioning is an approach for precisely summarizing image contents using natural language processing. Leveraging cutting-edge feature extraction, multimodal encoding, and fusion strategies, visual and textual fragments are correlated within a latent space. These multimodal segments are analyzed by a deep sequential model for phrase decoding. The widely used CNN-LSTM encoder-decoder pipeline is central to image captioning frameworks. However, current architectures suffer from two major limitations: (1) existing frameworks employ a unidirectional fusion and sequential decoding process, failing to capture the semantic context against both the preceding and following tokens; and (2) static multimodal translation fails to grasp and align critical information accurately, limiting its effectiveness when training on diverse datasets with varied visual and linguistic samples. Consequently, the models fail to capture the expansive and intricate context, leading to the production of short and abstract captions. To address these limitations, we propose Bi-CANet, an end-to-end bidirectional multimodal contextual alignment network for image captioning. Bi-CANet employs a dual-directional fusion of visual details with textual phrases along with a bidirectional decoder, thereby aligning the rich semantic and spatial context over both the preceding and subsequent phrases. Experimental analysis shows that Bi-CANet is more effective in generating comprehensive captions when trained on diverse datasets. Specifically, it achieves BLEU-1 scores of 54.02%, and METEOR scores of 33.11% on the Flickr 8K dataset.

关键词： Training visualization Image databases Semantics Robustness Decoding Meteors Web sites Multimedia communication Context modeling

来源：评论

学校读者我要写书评

暂无评论

Enhanced Satellite Image Fusion Using Deep Learning and Feature Extraction Techniques: A Survey 1st

Enhanced Satellite Image Fusion Using Deep Learning and Feat...

引用

1st International conference on Intelligent Systems in Computing and communications, ISCComm 2023

作者： Nallagachu, Swathi Sandanalakshmi, R. Department of Electronics and Communication Engineering Puducherry Technological University Puducherry India

ISBN: (纸本)9783031756047

This paper presents an overview and analysis of numerous research projects on image fusion methods, with a particular emphasis on deep learning-based methods. The research analyses the inadequacies of current fusion models and suggests novel methods for feature extraction, visual sensor networks, remote sensing applications, medical imaging, and multi-resolution image fusion. The study demonstrates the advantages of deep learning techniques for image fusion tasks, including Convolutional Neural Networks (CNNs), Stacked Auto encoders, and Convolutional Sparse Representation (CSR). These methods provide better fusion quality, fast processing, and better visual perception. Numerous studies provide novel methods, such as the rapid Integer Lifting Wavelet Transform (ILWT), Dual-Tree Complex Contourlet Transform (DT-CCT), and hybrid fusion methods that combine Discrete Cosine Transform (DCT) and Integer Lifting Wavelet Transform (ILWT) techniques. The review literature survey shows how these techniques can improve fusion outcomes while introducing little information distortion. In general, this paper brings together improvements in feature extraction and image fusion techniques, demonstrating the strength and potential of deep learning-based approaches. It is a useful tool for academics and professionals working in various fields who want to comprehend and advance these fields of study. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

DATA-VSR: Dynamic Trajectory Attention and Texture Adaptive Rooter for Video Super-Resolution

DATA-VSR: Dynamic Trajectory Attention and Texture Adaptive ...

引用

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

作者： Linfeng He Meiqin Liu Qi Tang Chao Yao Yao Zhao Institute of Information Science Beijing Jiaotong University Beijing China Visual Intelligence + X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Video Super-Resolution (VSR) is essential for reconstructing high-definition sequences from correlated video frames. While Transformer-based VSR methods have improved reconstruction quality, they require substantial computational resources, limiting deployment on resource-constrained devices. To tackle this issue, we propose a novel framework named Dynamic Trajectory Attention and Texture Adaptive Rooter for Video Super-Resolution (DATA-VSR). There are two key innovations: the Temporal Redundancy-aware Alignment Network (TRAN) and the Spatial Redundancy-aware Refinement Network (SRRN). Specifically, features are aligned by focusing on dynamic temporal trajectories instead of static redundancies in TRAN, and then features are adaptively refined based on the texture complexity of different regions in SRRN. Additionally, the Dual-Domain Enhancement Block (DDEB) is incorporated to effectively capture global dependencies in the frequency domain and enhance the representation of local features in the spatial domain. The experimental results on standard VSR benchmarks show that DATA-VSR achieves competitive performance with fewer parameters, lower FLOPs, and a specific reduction of 17%.

关键词： Technological innovation Limiting Superresolution Redundancy Transformers Trajectory Speech processing Spatial resolution Standards Signal resolution

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on Electronic Governance with Emerging Technologies, EGETC 2024

3rd International Conference on Electronic Governance with E...

引用

3rd International conference on Electronic Governance with Emerging Technologies, EGETC 2024

ISBN: (纸本)9783031770289

The proceedings contain 17 papers. The special focus in this conference is on Electronic Governance with Emerging Technologies. The topics include: Ecological Development of a Novel Machine Learning Technique for Electricity Consumption and Cost Prediction in Cloud Computing;blockchain Based Decentralized Approach for Securing Fog Computing Environment;Enhancing Face Spoofing Detection Via CNN Model Integration with Normalized Features;Study of ZigBee-Based communication to Share Operative Weather information Between UASs in the Frame of Smart Cities Concept;automating Exam Assessment Through Digital Transformation and Image processing;an Analysis of Ethical Dimension of Machine Learning Models in Software Defect Prediction in Healthcare Sector;leaf Diseases Detection in Peach Using EfficientNet;medInsight: A Personalized Prescription Recommendation Using Machine Learning;intelligent Machine Learning for Cybersecurity: Anomaly Detection in Network Intrusion Systems and Beyond;Enhancing Cyber Resilience: Implementing DFMCAI for Threat Detection and Analysis;forecasting Future Credit Card Delinquencies: Leveraging Data Tables and visual Analysis for Enhanced Accuracy;navigating the Strategic Landscape: An In-Depth Review of the Strategic Planning Process;exploring Text Vectorization on the Polarity Detection of Spanish Comments;Evolutionary Optimization Techniques for the Design of Three-Dimensional UAV’s Antenna Arrays;cooperative Multi-agent Pursuit-Evasion Using Convolutional Neural Networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ALIC: Adaptive Fusion Entropy Model for Learned Image Compression

ALIC: Adaptive Fusion Entropy Model for Learned Image Compre...

引用

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

作者： Lingxue Li Meiqin Liu Yifan Zhang Qi Tang Chao Yao Yao Zhao Institute of Information Science Beijing Jiaotong University Beijing China Visual Intelligence + X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recently, learned image compression algorithms have achieved significant performance. The entropy model is crucial for improving the rate-distortion performance by estimating the probability distribution of latent representation. In this paper, we propose an adaptive fusion entropy model for learned image compression (ALIC). To explore the correlation between channel and global spatial features, an adaptive fusion entropy model (AFEM) is designed. AFEM first slices the latent representation along the channels and leverages the adaptive channel fusion context module (ACFC) to capture correlations between the decoded and current slices. Subsequently, AFEM uses the adaptive spatial fusion context module (ASFC) to further divide the current slice into encoding pixels and reference pixels, thus improving the accuracy of probability estimation. The attention map and modulation parameter are introduced in ACFC and ASFC to interact with channel and spatial features. In addition, the variable-rate residual transformer (VResFormer) is proposed to control dynamic bit-rate by selectively modulating the high-frequency component according to coefficient weight and bias. Experimental results indicate that our ALIC outperforms other learned image compression algorithms. Our ALIC saves 5.89% bit-rate compared with VVC (4:4:4) on Kodak dataset.

关键词： Adaptation models Image coding Correlation Signal processing algorithms Rate-distortion Modulation Transformers Entropy Probability distribution Speech processing

来源：评论

学校读者我要写书评

暂无评论

Deep Steganography Using SteganoGAN

Deep Steganography Using SteganoGAN

引用

Integrated Circuits and communication Systems (ICICACS), IEEE International conference on

作者： Devidas Bhat Suraj B Madagaonkar Vinayak G Pai Deepthi J. Shetty Information Science & Engineering NMAMIT Nitte Karnataka India Computer Science and Engineering IIT Dharwad Karnataka India Computer Science and Engineering Manipal Institute of Technology Manipal Karnataka India Department of CSE Nitte Meenakshi Institute of Technology Bangalore Karnataka India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

An improved method for covertly embedding secret messages within images is deep steganography utilizing SteganoGAN, which combines steganography and deep learning. SteganoGAN employs Generative Adversarial Networks (GANs) to create realistic images that can safely conceal secret data. The concealed message is integrated into the image pixels and encoded as a binary stream, which can be retrieved using a decoder, ensuring the final image maintains visual integrity. This technique provides strong security, as it is difficult to detect the hidden data, making it ideal for applications like digital water-marking, copyright protection, and private data transfer. The deep learning architecture enhances processing speed, increases data embedding capacity, and improves security. Experimental results using the Div2k dataset showed that models trained with a data depth of 4 achieved the highest bits per pixel (RS-BPP), demonstrating a balance between data embedding capacity and image quality (PSNR and SSIM). Despite its strengths, SteganoGAN faces challenges, such as vulnerability to attacks by adversaries familiar with the technique, emphasizing the need for continuous innovation to improve security.

关键词： Deep learning Training Steganography Ethics visualization Technological innovation Watermarking Generative adversarial networks Data models Security

来源：评论

学校读者我要写书评

暂无评论

Integrating Inception v3 and Retinex Enhancement for Accurate Diagnosis of Age-Related Macular Degeneration

Integrating Inception v3 and Retinex Enhancement for Accurat...

引用

International conference on Wireless communications, Signal processing and Networking (WiSPNET)

作者： Senthil K Sivagami S Vijaya Lakshmi R Sree Dedeepya B Department of Computer Science and Engineering Saveetha School of Engineering Saveetha UniversitySIMATS Chennai Tamil Nadu India Department of Information Technology Saveetha School of Engineering Saveetha UniversitySIMATS Chennai Tamil Nadu Department of AI&DS Saveetha School of Engineering Saveetha UniversitySIMATS Chennai Tamil Nadu

ISBN: (数字)9798331524227

ISBN: (纸本)9798331524234

Proactive identification of eye conditions remains essential to stop conditions from advancing and to enable proper medical treatment of retina-related disturbances. Over the recent past, scientists have dedicated significant attention to diagnosing eye diseases. visual impairments create enormous obstacles that reduce patients' overall life satisfaction because they affect their ability to complete daily duties. Age-related macular Degeneration (AMD) is one of the prevalent reasons behind permanent central vision loss in both eyes that affects people progressively without causing discomfort. The proposed model architecture applies pre-processing to fundus images, which are then integrated into a Retinex algorithm before combining them with InceptionV3 to obtain AMD diagnosis results. The algorithm manifests its capability to enhance contrast and noise reduction, and its procedures necessary imaging parameters for drusen diagnosis. The InceptionV3 architecture principles are integrated to boost the diagnostic accuracy of the research outcomes. The proposed model receives training through an Open Access Series of Images Reading database consisting of 5,000 images that contain various types of eye diseases. The accuracy achieved during 10-fold cross-validation measures 95.67%. The automated method for AMD detection requires consideration for its diagnostic value, which should help professionals initiate timely medical assistance.

关键词： Macular degeneration Deep learning Wireless communication Training Accuracy Signal processing Feature extraction Spatial resolution Medical diagnostic imaging Testing

来源：评论

学校读者我要写书评

暂无评论

Development of Web Platform for Home Screening of Neurological Disorders Using Artificial Intelligence

Development of Web Platform for Home Screening of Neurologic...

引用

Advances in Computer Science, Electrical, Electronics, and communication Technologies (CE2CT), International conference on

作者： S. Bama Praveen Kumar Maroju Subash Banala Sunil Kumar Sehrawat Mohanarajesh Kommineni Divya Kodi Department of CSE Velammal Engineering College Surapet Chennai Clientserver Technology Solutions Financial Services & Cloud Technologies Bausch Health Companies TEKsystems Global Services LLC Truist Financial

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Millions of people worldwide suffer with Parkinson's disease (PD), one of the most prevalent neurological illnesses. The diagnosis of PD has changed significantly over the last 25 years; at first, autopsy and neurological exams were the only methods accessible. Impaired handwriting has been shown to be a significant early indicator for this disease's identification. The purpose of this study was to use machine learning techniques to provide a quick and easy method of differentiating PD patients from controls using handwriting activities. It developed a telemonitoring technology based on user-friendly drawing tablet software that gave the subject visual feedback on the screen and enabled us to gather data in real time about the location, pressure, and tilt of the digital pen throughout the procedure. This paper created a procedure that included writing and drawing exercises, including ones in Italian, and we gathered information from ten PD patients and twenty healthy participants. With a 93.4% accuracy rate, the current research developed a machine learning (ML) framework that automatically separates PD patients from healthy control people using signals and data from a previous database.

关键词： Neurological diseases visualization Accuracy Databases Machine learning Writing Signal processing Particle measurements Software Real-time systems

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323页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：