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

1,047 篇 会议
39 篇 期刊文献
6 册 图书

馆藏范围

1,092 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

470 篇 工学
- 329 篇 计算机科学与技术...
- 211 篇 软件工程
- 85 篇 电气工程
- 64 篇 控制科学与工程
- 51 篇 机械工程
- 33 篇 信息与通信工程
- 26 篇 生物医学工程（可授...
- 25 篇 动力工程及工程热...
- 25 篇 石油与天然气工程
- 23 篇 仪器科学与技术
- 21 篇 土木工程
- 20 篇 化学工程与技术
- 16 篇 电子科学与技术（可...
- 15 篇 生物工程
- 14 篇 光学工程
- 14 篇 建筑学
- 14 篇 安全科学与工程
- 13 篇 测绘科学与技术
191 篇 理学
- 107 篇 数学
- 70 篇 物理学
- 27 篇 统计学（可授理学、...
- 22 篇 系统科学
- 17 篇 化学
- 16 篇 生物学
79 篇 管理学
- 61 篇 管理科学与工程(可...
- 31 篇 工商管理
- 25 篇 图书情报与档案管...
58 篇 医学
- 47 篇 临床医学
- 16 篇 特种医学
12 篇 经济学
- 12 篇 应用经济学
7 篇 教育学
5 篇 农学
4 篇 法学
3 篇 艺术学

主题

510 篇 visualization
250 篇 optimization
109 篇 data visualizati...
68 篇 accuracy
62 篇 feature extracti...
59 篇 computational mo...
58 篇 training
45 篇 three-dimensiona...
43 篇 robustness
41 篇 cameras
40 篇 real-time system...
35 篇 deep learning
31 篇 machine learning
30 篇 data models
28 篇 measurement
27 篇 predictive model...
27 篇 optimization met...
27 篇 solid modeling
26 篇 image color anal...
23 篇 rendering (compu...

机构

3 篇 department of cs...
3 篇 school of comput...
3 篇 school of comput...
3 篇 college of compu...
3 篇 maharishi school...
3 篇 university of br...
3 篇 department of co...
3 篇 new york univers...
2 篇 univ granada dep...
2 篇 univ texas texas...
2 篇 vrvis res ctr au...
2 篇 halliburton unit...
2 篇 department of co...
2 篇 centre of resear...
2 篇 nanjing universi...
2 篇 seoul natl univ
2 篇 chongqing munici...
2 篇 school of comput...
2 篇 department of co...
2 篇 department of co...

作者

3 篇 ertl thomas
3 篇 vladislav golyan...
3 篇 grimme christian
3 篇 r. raja subraman...
3 篇 qu huamin
3 篇 kerschke pascal
2 篇 takeshi hatanaka
2 篇 yasuyuki matsush...
2 篇 zhou chenn q.
2 篇 brian c. lovell
2 篇 a. sakly
2 篇 nassir navab
2 篇 bobick a
2 篇 barthel kai uwe
2 篇 velasco f
2 篇 vucinic dean
2 篇 gaither kelly p.
2 篇 xi wang
2 篇 lin ming c.
2 篇 rubio-sanchez m.

语言

1,078 篇 英文
12 篇 其他
3 篇 中文
1 篇 法文
1 篇 俄文

检索条件"任意字段=Conference on Visualization and Optimization Techniques"

共 1092 条记录，以下是1001-1010 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：

Two Stages of Algebraic Matrix Decomposition in Optimal Image Steganographic Approach

Two Stages of Algebraic Matrix Decomposition in Optimal Imag...

引用

International conference on Engineering Technology and their Applications (IICETA)

作者： bJumana Waleed Ihab Mahdi Almaameri Areej M. Abduldaim Waleed Al-Azzawi Department of Computer Science College of Science University of Diyala Iraq Department of Computer Technical Engineering College of Technical Engineering The Islamic University Najaf Iraq Applied Sciences Department Mathematics and Computer Applications University of Technology Baghdad Iraq Medical Technical College Al-Farahidi University Baghdad Iraq

ISBN: (数字)9781665472159

ISBN: (纸本)9781665472166

With the evolution of social networks, the necessitate of providing information security methods becomes increasingly significant. Therefore, these methods should be studied and analyzed for presenting more secure and appropriate techniques. Since the images represent the most common and widely utilized visual formats, an optimized approach of image steganography based on algebraic matrix decomposition has been proposed in this paper. In particular, matrix decomposition methods represent a significant tool for increasing the security of the whole blent of digital steganographic approaches. In this paper, two stages of the Hessenberg matrix decomposition are implemented on the original image using modulo operation to show the impact of the matrix decomposition in the steganographic process. Additionally, a Chameleon Swarm optimization (CSO) algorithm is utilized to appoint the optimal positions in the embedding stage. The obtained results have been evaluated to show the difference between the utilization of decomposition or not.

关键词： Wavelet transforms Resistance Steganography visualization Social networking (online) Information security Robustness

来源：评论

学校读者我要写书评

暂无评论

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation

More than the Sum of Its Parts: Ensembling Backbone Networks...

引用

International Joint conference on Neural Networks (IJCNN)

作者： Nico Catalano Alessandro Maranelli Agnese Chiatti Matteo Matteucci Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Semantic segmentation is a key prerequisite to robust image understanding for applications in Artificial Intelligence and Robotics. Few Shot Segmentation, in particular, concerns the extension and optimization of traditional segmentation methods in challenging conditions where limited training examples are available. A predominant approach in Few Shot Segmentation is to rely on a single backbone for visual feature extraction. Choosing which backbone to leverage is a deciding factor contributing to the overall performance. In this work, we interrogate on whether fusing features from different backbones can improve the ability of Few Shot Segmentation models to capture richer visual features. To tackle this question, we propose and compare two ensembling techniques—Independent Voting and Feature Fusion. Among the available Few Shot Segmentation methods, we implement the proposed ensembling techniques on PANet. The module dedicated to predicting segmentation masks from the backbone embeddings in PANet avoids trainable parameters, creating a controlled ‘in vitro’ setting for isolating the impact of different ensembling strategies. Leveraging the complementary strengths of different backbones, our approach outperforms the original single-backbone PANet across standard benchmarks even in challenging one-shot learning scenarios. Specifically, it achieved a performance improvement of +7.37% on PASCAL-5 i and of +10.68% on COCO-20 i in the top-performing scenario where three backbones are combined. These results, together with the qualitative inspection of the predicted subject masks, suggest that relying on multiple backbones in PANet leads to a more comprehensive feature representation, thus expediting the successful application of Few Shot Segmentation methods in challenging, data-scarce environments.

关键词： Training visualization Adaptation models Semantic segmentation Feature extraction Transformers Task analysis

来源：评论

学校读者我要写书评

暂无评论

EfficientNet-Based Deepfake Detection: A Robust Approach for Real and Fake Media Classification

EfficientNet-Based Deepfake Detection: A Robust Approach for...

引用

Communications and Information Technologies (GCCIT), Global conference on

作者： Eshika Jain Danish Kundra Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Deepfakes are an up-and-coming form of synthetic media-previously unrealistically realistic video, image, audio, or even live broadcast montaging faces or voices to create an impression of likeness. While opening new ways of creative expression, deepfakes create serious problems in many domains: misinformation, identity theft, defamation-the list increasingly goes on-jeopardizing the reliability of visual evidence in the modern world. As manipulations grow more and more sophisticated, the need to apply effective detection methods is critical. The present work is devoted to the application of the deep convolutional neural network EfficientNetB0 for deepfake detection. EfficientNetB0 is a scalable and computationally efficient architecture that will be applied in the differentiation of real and manipulated images by subtle irregularities in facial features and textures often invisible to the human naked eye. This model is trained on both real and deepfake images, with its optimized configuration to find these minute differences. Data augmentation techniques combined with regularization techniques, including dropout and global average pooling, enhance the capability of the model for generalization over diverse datasets. It achieved 90% on both training and validation, hence did a great job in detecting deepfakes. The confusion matrix further justifies the efficiency of the model in correctly classifying real and fake images. EfficientNetB0 has tremendous potential and can be very useful as a tool in mitigating risks due to manipulated media by helping one contribute toward preserving digital information integrity in an ever-evolving landscape.

关键词： Training Deepfakes visualization Solid modeling Accuracy Solids Data models Robustness optimization Overfitting

来源：评论

学校读者我要写书评

暂无评论

Bandwidth-Efficient Image Transmission in Autonomous Vehicles Using Super-Resolution techniques

Bandwidth-Efficient Image Transmission in Autonomous Vehicle...

引用

International conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET)

作者： Mokhammad Mirza Etnisa Haqiqi Ajib Setyo Arifin Arief Suryadi Satyawan Anindya Afina Carmelya Salita Ulitia Prini Department of Electrical Engineering Faculty of Engineering Universitas Indonesia Depok Indonesia Research Center for Telecommunication National Research and Innovation Agency Bandung Indonesia Department of Electrical Engineering Universitas Nurtanio Bandung Indonesia Department of Telecommunication System Universitas Pendidikan Indonesia Bandung Indonesia

ISBN: (数字)9798350389920

ISBN: (纸本)9798350389937

The rapid advancement in autonomous vehicle technology promises significant improvements in driving efficiency, safety, and comfort. A crucial aspect of these systems is the real-time processing of visual data to ensure accurate object identification and environmental awareness. However, transmitting high-resolution visual data from vehicles to central server encounters challenges due to bandwidth limitations and network latency. Super-resolution methods, leveraging machine learning, present a viable solution by enhancing image resolution without increasing data transmission bandwidth. This study explores the application of super-resolution techniques for bandwidth optimization in image transmission within autonomous vehicles. By transmitting lower resolution images and enhancing them upon reception, the system reduces network load, ensuring efficient data transfer. The analysis demonstrates the trade-off between image quality and transmission efficiency, emphasizing the potential of super-resolution in bandwidth-limited environments. Implementing the SRCNN architecture shows promising results in maintaining image quality with minimal bandwidth usage, contributing to the development of more efficient and reliable autonomous vehicle systems.

关键词： Image quality Microwave antennas visualization Image communication Superresolution Transportation Bandwidth Radar antennas Data transfer Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

DRDnet22: Advanced convolutional techniques for early diabetic retinopathy detection in retinal images

DRDnet22: Advanced convolutional techniques for early diabet...

引用

International conference on Computing and Networking Technology (ICCNT)

作者： Md. Sakib Ali Mazumder F M Javed Mehedi Shamrat Imran Mahmud Sharmin Sharmin Tanzim Hossain Ekramul Kabir Biplab Department of Software Engineering Daffodil International University Dhaka Bangladesh Department of Computer System and Technology Universiti Malaya Kuala Lumpur Malaysia Institute of Information Technology University of Dhaka Dhaka Bangladesh

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Diabetic Retinopathy (DR) is a prevalent eye complication among individuals with diabetes. Early detection of DR can prevent vision loss and lower associated problems. Manual diagnosis via retinal fundus images requires the expertise of medical professionals to assess several complex characteristics, including visual acuity tests, pupil dilation, and optical consistency tomography. The process is challenging, time-consuming, and prone to errors. This paper proposes a deep learning (DL) technique, DRDnet22, to detect and categorize DR into five distinct stages. The APTOS 2019 dataset is utilized in this study, which contains 3662 images. The study employs dense block and transition layer with global average pooling (GAP) techniques, and the combination of distinct Convolutional Networks (ConvNets) results in an enhanced representation beyond the utilization of features from a single ConvNet alone. To conduct an ablation analysis, the conventional pre-trained model’s performance was compared. The performance evaluation points out that the proposed model achieved 81.6% accuracy, which is an advantage over other DCNN models. Despite facing a few inaccuracies, the model’s competence in spotting vital features underscores its diagnostic potential.

关键词： Performance evaluation Optical losses Diabetic retinopathy visualization Accuracy Tomography Retina Pupils optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Vision Vanguard: A CNN-Based Solution for Visually Impaired

Vision Vanguard: A CNN-Based Solution for Visually Impaired

引用

International conference on Advances in Information Technology (ICAIT)

作者： Amith Shekhar C Kavya B Bashetti Bhoomika P Department of CSE BNM Institute of Technology Bengaluru India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The Vision Vanguard project offers a cutting-edge CNN (Convolutional Neural Network) driven solution designed to strengthen the ranks of the visually disabled population. Using state-of-the-art image recognition techniques and instantaneous feedback, Vision Vanguard seeks to transform the everyday lives of those who are visually disabled, by giving them access to a dependable and user-friendly navigation and object recognition tool. The project intends to use artificial intelligence to help those with disabilities such as the blind or visually disabled perceive their environment. The CNN model is built with cutting-edge computer vision techniques and trained on a wide range of datasets with different environmental circumstances. Through the processing of input from a live video stream, the model produces written descriptions or aural feedback about its environment through an interface which maybe utilised by those with vision impairments. The study describes the CNN model's architecture and training process and goes over its performance measures, which include accuracy, precision, and recall. It also emphasizes the model's usefulness in various environmental settings and its capacity for real-time inference. The model is built using deep learning techniques and trained on a large and diverse dataset that encompasses both outdoor and indoor scenarios. Strict optimization and validation were used in the training process to achieve the ideal balance between accuracy and efficiency. The model's dependability and efficiency in identifying and categorizing objects, barriers, and contextual data are extensively tested and illustrated using performance measures including accuracy and precision. The research also explores the CNN model's real-time inference capabilities, showing how quickly it can digest visual input and provide textual explanations or aural feedback through an intuitive interface. Tests of robustness under several lighting and weather situations were carrie

关键词： Training Deep learning Computer vision visualization Accuracy Navigation Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Deformation Correction in Laparoscopic Liver Surgical Navigation Using Point Cloud Completion and Biomechanical Model

Deformation Correction in Laparoscopic Liver Surgical Naviga...

引用

IEEE International conference on Bioinformatics and Biomedicine (BIBM)

作者： Qian Zhang Deqiang Xiao Danni Ai Jingfan Fan Tianyu Fu Shuo Yang Hong Song Jian Yang School of Optics and Photonics Beijing Institute of Technology Beijing China School of Medical Technology Beijing Institute of Technology Beijing China School of Computer Science Beijing Institute of Technology Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In the minimally invasive liver resection surgery, deformation estimation of liver is required to correct the preoperative virtual model to match the intraoperative scenarios, in which the liver deforms due to respiration and surgical operations. Existing methods on liver deformation estimation often struggle to achieve high accuracy when the intraoperative liver surface is limited in size. To overcome the challenge of sparse intraoperative point cloud data and improve the accuracy of liver deformation predictions, this paper introduces an innovative method for estimating liver deformation. This method comprises two main components: intraoperative point cloud completion and liver deformation estimation. Intraoperative point cloud completion uses registration techniques to integrate preoperative topological structures into the intraoperative phase. Liver deformation estimation combines optimization control with biomechanical modeling to accurately align the preoperative liver model with its intraoperative counterpart. Comparative and ablation experiments, as well as investigations into the impact of different completion ratios, were conducted. The results demonstrate that this method effectively utilizes preoperative liver geometric features to enhance intraoperative visualization, even with limited intraoperative data. Additionally, the opti-mization control method provides reliable deformation estimates with acceptable accuracy. This study offers new insights and methodologies for the development of augmented reality surgical navigation systems, contributing to the computer assisted liver surgey.

关键词： Deformable models Point cloud compression Biomechanics Accuracy Deformation Biological system modeling Liver Estimation Reliability optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Integrated Shading Device and Light Shelf for Daylight Performance and Visual Comfort in Architecture Studio

Optimizing Integrated Shading Device and Light Shelf for Day...

引用

International conference on Environment and Electrical Engineering (EEEIC)

作者： Pelin Avcı Berk Ekici Zehra Tuğçe Kazanasmaz Department of Architecture Izmir Institute of Technology Izmir Turkey

ISBN: (数字)9798350355185

ISBN: (纸本)9798350355192

To provide a sustainable interior, it is essential to consider visual comfort and energy efficiency for the occupants' well-being. Daylight is crucial in providing visual comfort while proposing energy-efficient design alternatives. Using daylight as a primary source is one of the most crucial strategies. However, controlling daylight for unwanted situations such as discomfort glare is important. There have been several research studies on daylighting, visual comfort, and shading techniques. Shading devices are façade configurations to control daylight, while light shelves distribute daylight evenly through the space. There are two types of classifications for shading devices: adaptive ones and non-adaptive ones. Numerous research studies have been conducted on daylighting, energy consumption, occupancy performance, and shading systems. Shading technologies, whether adaptive or not, provide benefits and drawbacks. Even though optimizing them is one way to design non-adaptive shading devices, they require minimal maintenance. This study aims to integrate adaptive shading devices and light shelves for university campus buildings to provide lighting design strategies. The aim is to create a study environment that promotes well-being and academic achievement. To pursue this study, three optimization algorithms were run to find the nearly optimal solution. The goal was to both maximize Daylight Autonomy and uniformity values. Results showed that HypE and SPEA2 results discovered near-optimal DA above 75% and uniformity between 0.6 and 0.7.

关键词： Performance evaluation visualization Energy consumption Daylighting Architecture Buildings Europe Energy efficiency Maintenance optimization

来源：评论

学校读者我要写书评

暂无评论

SALIENCY-COGNIZANT ROBUST VIEW SYNTHESIS IN FREE VIEWPOINT VIDEO STREAMING

SALIENCY-COGNIZANT ROBUST VIEW SYNTHESIS IN FREE VIEWPOINT V...

引用

IEEE International conference on Image Processing

作者： Bruno Macchiavello Camilo Dorea Edson M. Hung Gene Cheung Wai-tian Tan Universidade de Brasilia Brazil National Institute of Informatics Japan Hewlett-Packard Laboratories USA.

ISBN: (纸本)9781479923427

In free viewpoint video, texture and depth maps from two camera-captured viewpoints are transmitted, so that at receiver, a novel virtual view chosen by the client can be synthesized via depth-image-based rendering (DIBR). When irrecoverable packet losses occur during transmission--typically affecting less important spatial regions in the video given unequal error protection (UEP) is deployed--appropriate error concealment strategies must be used at decoder to minimize resulting visual degradation in the synthesized view. Towards this goal, we propose a new optimization framework based on visual saliency to combine two different concealment techniques. First, given a pixel in the virtual view is typically constructed as a convex combination of corresponding pixels in the left and right captured views, weighted pixel blending (WPB) readjusts the weights in the linear sum to reflect the expected error in code blocks that contain the corresponding pixels. Second, exemplar-based patch matching (EPM) finds the most similar patches in the known spatial region to complete missing pixels in the unknown region. To choose between candidates constructed using the two techniques when filling a given pixel patch in the synthesized view, we first compute a weighted sum of expected error and visual saliency for each candidate patch. The candidate with the smaller sum (one with small expected error and visual saliency, so that even if errors do occur, they do not stand out visually) is selected for pixel completion. Experimental results show that our scheme can outperform the use of co-located blocks from a previous frame by up to 0.7dB in PSNR and improve subjective visual quality.

关键词： free viewpoint video visual saliency error concealment pixel Videotapes visualization View Data Security Packet loss indium Peak signal-to-noise ratio

来源：评论

学校读者我要写书评

暂无评论

Parallel Medical Imaging: An ACP-Based Approach for Intelligent Medical Image Recognition with Small Samples

Parallel Medical Imaging: An ACP-Based Approach for Intellig...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International conference on

作者： Tianyu Shen Chao Gou Jiangong Wang Jun Huang Yonglan He Huadan Xue Zhengyu Jin Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Guangzhou China Peking Union Medical College Hospital Chinese Academy of Medical Sciences Peking Union Medical College Beijing China

The deep learning methods trained with large-scale manually annotated datasets have led to significant breakthroughs in medical image community. However, obtaining such datasets remains a challenging work in medical domain. In this paper, we propose an ACP-based approach named parallel medical imaging (PMI) for analyzing and addressing the small sample problem of medical image recognition. Firstly, we present the basic framework and key techniques of PMI, in which the Artificial imaging systems are constructed to effectively augment the “medical small sample”, the Computational experiments are carried out for designing and evaluating the visual models trained with small samples, and the Parallel execution is conducted to achieve closed-loop interaction and optimization in the domain-knowledge guidance. Furthermore, we illustrate a preliminary implementation and application of PMI approach through the case study of mammogram analysis.

关键词： Deep learning visualization Image recognition Annotations Digital twin conferences Computational modeling

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110页 << < 97 98 99 100 101 102 103 104 105 106 > >>

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：