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

11,003 篇 会议
794 册 图书
289 篇 期刊文献
4 件 标准

馆藏范围

12,090 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,007 篇 工学
- 4,589 篇 计算机科学与技术...
- 3,918 篇 软件工程
- 1,068 篇 光学工程
- 776 篇 电气工程
- 759 篇 生物医学工程（可授...
- 543 篇 信息与通信工程
- 506 篇 电子科学与技术（可...
- 488 篇 机械工程
- 433 篇 控制科学与工程
- 423 篇 生物工程
- 270 篇 土木工程
- 263 篇 建筑学
- 213 篇 仪器科学与技术
- 158 篇 化学工程与技术
- 142 篇 力学（可授工学、理...
- 141 篇 测绘科学与技术
- 104 篇 材料科学与工程（可...
2,503 篇 理学
- 1,384 篇 物理学
- 1,134 篇 数学
- 450 篇 生物学
- 213 篇 统计学（可授理学、...
- 180 篇 化学
- 101 篇 系统科学
993 篇 医学
- 883 篇 临床医学
- 321 篇 基础医学(可授医学...
- 260 篇 药学(可授医学、理...
809 篇 管理学
- 431 篇 管理科学与工程(可...
- 416 篇 图书情报与档案管...
- 158 篇 工商管理
107 篇 教育学
- 103 篇 教育学
89 篇 法学
88 篇 农学
37 篇 经济学
28 篇 文学
25 篇 艺术学
16 篇 军事学
1 篇 哲学

主题

3,365 篇 visualization
1,606 篇 rendering (compu...
1,252 篇 computer graphic...
1,121 篇 data visualizati...
693 篇 biomedical imagi...
691 篇 three-dimensiona...
528 篇 image segmentati...
500 篇 computer imaging...
489 篇 cameras
487 篇 computational mo...
424 篇 magnetic resonan...
401 篇 artificial intel...
380 篇 solid modeling
333 篇 three dimensiona...
327 篇 graphics
319 篇 computer science
313 篇 feature extracti...
310 篇 computer vision
306 篇 shape
298 篇 application soft...

机构

31 篇 school of comput...
25 篇 univ utah sci co...
24 篇 tsinghua univers...
23 篇 shanghai jiao to...
22 篇 institute for co...
17 篇 department of co...
16 篇 indian statistic...
15 篇 eindhoven univer...
15 篇 department of ma...
14 篇 department of co...
14 篇 faculty of infor...
14 篇 nanyang technolo...
14 篇 fraunhofer insti...
14 篇 peking universit...
13 篇 agh university o...
12 篇 school of comput...
12 篇 imaging and visu...
12 篇 university of ca...
12 篇 department of co...
12 篇 zhejiang univ st...

作者

20 篇 nassir navab
19 篇 osvaldo gervasi
18 篇 horst bischof
15 篇 huang mao lin
14 篇 ryszard tadeusie...
14 篇 scheuermann geri...
14 篇 linsen lars
13 篇 g.j. clapworthy
13 篇 mateu sbert
13 篇 marcin korytkows...
13 篇 jacek m. zurada
13 篇 m. sarfraz
12 篇 ertl thomas
12 篇 leonidas deligia...
12 篇 lotfi a. zadeh
12 篇 george bebis
12 篇 zhang jian j.
11 篇 bernady o. apduh...
11 篇 bahram parvin
11 篇 darko koracin

语言

11,774 篇 英文
201 篇 其他
90 篇 俄文
35 篇 中文
1 篇 西班牙文
1 篇 法文

检索条件"任意字段=International Conference on Computer Graphics, Imaging and Visualization"

共 12090 条记录，以下是801-810 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：

Video Action Classification through Graph Convolutional Networks 16

Video Action Classification through Graph Convolutional Netw...

引用

16th international Joint conference on computer Vision, imaging and computer graphics Theory and Applications (VISIGRAPP) / 16th international conference on computer Vision Theory and Applications (VISAPP)

作者： Costa, Felipe F. Saito, Priscila T. M. Bugatti, Pedro H. Univ Tecnol Fed Parana Dept Comp 1640 Alberto Carazzai Ave Cornelio Procopio Brazil

ISBN: (纸本)9789897584886

Video classification methods have been evolving through proposals based on end-to-end deep learning architectures. Several works have testified that end-to-end models are effective for the learning of intrinsic video features, especially when compared to the handcrafted ones. In general, convolutional neural networks are used for deep learning in videos. Usually, when applied to such contexts, these vanilla deep learning networks cannot identify variations based on temporal information. To do so, memory-based cells (e.g. long-short term memory), or even optical flow techniques are used in conjunction with the convolutional process. However, despite their effectiveness, those methods neglect global analysis, processing only a small quantity of frames in each batch during the learning and inference process. Moreover, they also completely ignore the semantic relationship between different videos that belong to the same context. Thus, the present work aims to fill these gaps by using information grouping concepts and contextual detection through graph-based convolutional neural networks. The experiments show that our method achieves up to 87% of accuracy in a well-known public video dataset.

关键词： Deep Learning Graph Convolutional Network computer Vision Action Classification

来源：评论

学校读者我要写书评

暂无评论

Comparative Assessment of Modern Approaches for 3D Reconstruction

Comparative Assessment of Modern Approaches for 3D Reconstru...

引用

international conference on Radioelektronika

作者： Oleh Kryvoshei Patrik Kamencay Roberta Hlavata Adam Stech Miroslav Benco Department of Multimedia and Information-Communication Technologies University of Zilina Zilina Slovakia

ISBN: (数字)9798331544478

ISBN: (纸本)9798331544485

This paper explores and evaluates the strengths and weaknesses of neural and Gaussian-based approaches in 3D reconstruction. While neural radiance fields (NRFs) methods are increasingly favored for their adaptability and excellent outcomes, Gaussian techniques stand out for their analytical efficiency and robustness. This study systematically evaluates these both paradigms by comparing their performance in terms of accuracy, computational complexity, scalability, and real-world feasibility. In this paper, we analyze their effectiveness in reconstructing diverse 3D environments, considering factors such as noise resilience, data requirements, and rendering quality. Through experimental comparisons and benchmarking against standard datasets, our aim is to identify the strengths and limitations of each method and determine their suitability for specific applications in computer vision and graphics. By offering insights into the trade-offs between neural and Gaussian-based approaches, this paper contributes to the ongoing development of efficient and high-fidelity 3D reconstruction techniques. The findings will aid researchers and practitioners in selecting appropriate methods for different use cases, ultimately advancing the state of the art in 3D vision and computational graphics. Furthermore, the paper highlights the potential integration of NeRF in medical imaging, where it offers significant promise for generating 3D reconstructions from standard 2D medical scans. These reconstructions could revolutionize diagnostic accuracy, enhance surgical planning, and improve medical education.

关键词： Three-dimensional displays Accuracy Neural networks Surgery Neural radiance field Rendering (computer graphics) Real-time systems Planning Image reconstruction Standards

来源：评论

学校读者我要写书评

暂无评论

Assisting MoCap-Based Teleoperation of Robot Arm Using Augmented Reality Visualisations 25

Assisting MoCap-Based Teleoperation of Robot Arm Using Augme...

引用

ACM/IEEE international conference on Human-Robot Interaction (HRI)

作者： Qiushi Zhou Antony Chacon Jiahe Pan Wafa Johal Aarhus University The University of Melbourne ETH Zurich

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Teleoperating a robot arm involves the human operator positioning the robot's end-effector or programming each joint. Whereas humans can control their own arms easily by integrating visual and proprioceptive feedback, it is challenging to control an external robot arm in the same way, due to its inconsistent orientation and appearance. We explore teleoperating a robot arm through motion-capture (MoCap) of the human operator's arm with the assistance of augmented reality (AR) visualisations. We investigate how AR helps teleoperation by visualising a virtual reference of the human arm alongside the robot arm to help users understand the movement mapping. We found that the AR overlay of a humanoid arm on the robot in the same orientation helped users learn the control. We discuss findings and future work on MoCap-based robot teleoperation.

关键词： visualization Human-robot interaction Propioception Humanoid robots Arms Manipulators Rendering (computer graphics) End effectors Robots Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Pinhole Occlusion: Enhancing Soft-Edge Occlusion Using a Dynamic Pinhole Array

Pinhole Occlusion: Enhancing Soft-Edge Occlusion Using a Dyn...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE conference on

作者： Xiaodan Hu Yan Zhang Monica Perusquía-Hernández Yutaro Hirao Hideaki Uchiyama Kiyoshi Kiyokawa NAIST Shanghai Jiao Tong University

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

Systems with occlusion capabilities have gained interest in augmented reality, vision augmentation, and image processing. To address the challenge of creating a precise yet lightweight occlusion system, we introduce a novel architecture to tackle occlusion blurriness due to defocusing. Our approach, utilizing a dynamic pinhole array on a transmissive spatial light modulator (SLM) positioned between the eye and the occlusion layer, offers adaptive pinhole patterns, gaze-contingent functionality, and the potential to reduce visual artifacts. Our preliminary result demonstrates that, with the focal plane at 1.8 m, an occlusion placed at 4cm can be observed sharply through a 4.3 mm aperture.

关键词： visualization Three-dimensional displays Image processing Modulation User interfaces Rendering (computer graphics) Optical imaging

来源：评论

学校读者我要写书评

暂无评论

A Normalized Mutual Information-based Multi-Modal Medical Image Fusion Technique using Non Sub-sampled Shearlet Transform and Method Noise

A Normalized Mutual Information-based Multi-Modal Medical Im...

引用

international conference on Parallel Distributed and Grid Computing (PDGC)

作者： Shailesh Bhosekar Prabhishek Singh Deepak Garg School of Computer Science and Artificial Intelligence SR University Warangal Telangana India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

In image processing, image fusion is the process of merging characteristics and information from multiple images to build a single, more complete representation. This approach includes multi-modal medical image fusion, which involves fusing medical images from several imaging modalities such as computed tomography (CT) scans, Positron Emission Tomography (PET) and magnetic resonance imaging (MRI). This integration improves diagnostic accuracy by using each modality's own strengths, resulting in clearer visualization of anatomical structures and clinical situations. This work utilizes CT, PET, and MRI images as modalities for the experimentation purpose. This study (M3IF-NSST-MI) aims to construct a multi modal medical image approach that combines Non Sub-sampled Shearlet Transform (NSST) and method noise to the information content in the fused image, where high pass subbands are fused using Normalized Mutual Information (NMI) based fusion strategy. NSST domain is used for its Multi-Scale Representation and shift invariance. The concept of method noise as post-processing operation that extracts the information which was missed in the initial phase. The wavelet coefficients are fused using NMI-based fusion method. This combination of NSST with NMI-based fusion and method noise provides superior results than many conventional methods. This improves overall visual and parametric quality of fusion results than many compared methods.

关键词： visualization Accuracy Magnetic resonance imaging Computed tomography Noise Positron emission tomography Medical diagnostic imaging Image fusion Mutual information Wavelet coefficients

来源：评论

学校读者我要写书评

暂无评论

The use of modern computer technologies in the study of the Geometric Modeling course 22

The use of modern computer technologies in the study of the ...

引用

22nd international conference on Computational Mechanics and Modern Applied Software Systems, CMMASS 2021

作者： Zakharov, A.A. Zakharova, Yu.V. Computational Mathematics and Mathematical Physics Department Bauman Moscow State Technical University 5/1 2nd Baumanskaya st. Moscow105005 Russia

The paper describes the educational discipline "Geometric modeling", which is suitable for students of applied mathematics. The course covers spline representations and transfinite interpolation methods for modeling the shape of geometric objects, the methods for performing Boolean operations between objects and methods for visualizing the objects. Screenshots of some graphic windows of the developed visualization programs for supporting the implementation of individual assignments in the course are shown. The programs have web interfaces that use the WebGL graphics API in a browser, independent of an operating system, and are also available for smartphones and tablets. They provide graphical output for curves and surfaces in three-dimensional space, user interfaces for entering the initial data and interaction with geometric objects. Students only need to write their own calculation code for the programs in the JavaScript programming language. The interactive tools enable students to get practical skills in working with splines and visually analyze the impact of the input data on the final geometry. The individual assignments and programs are specially focused to stimulate students' interests. The paper is addressed to teachers of the geometric modeling for mathematicians and computer scientists. It seems to be interesting to those who develop software interfaces for geometric modeling algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Future of Fashion: AI-Powered Virtual Dressing for E-Commerce Applications

Future of Fashion: AI-Powered Virtual Dressing for E-Commerc...

引用

Emerging Innovations and Advanced Computing (INNOCOMP), international conference on

作者： Er. Nitasha Sneha Kumari Aditya Kumar Rizul Bhardwaj Vinita Maddheshiya Altamas Khan Department of Computer Science and Engineering Chandigarh University Mohali Punjab India

ISBN: (数字)9798350376470

ISBN: (纸本)9798350376487

This paper introduces an innovative AI-powered Virtual Dressing technology designed to revolutionize the way consumers shop for clothing online. Utilizing advanced computer vision techniques and machine learning models, our system offers a seamless virtual dressing experience. The process begins with high-resolution image capture, followed by dynamic resizing for optimal processing. A sophisticated cloth segmentation method is employed to accurately identify and separate the clothing item from the background. Utilizing the models for cloth segmentation and semantic segmentation, combined with posing coordinates, our system ensures precise body posture and garment alignment. The removal of background elements is achieved through semantic segmentation masks, enhancing the realism of the virtual experience. The final virtual dressing visualization supports both scenarios of retaining or omitting the background, based on user preference. To assess consumer interest in such technology, we conducted a survey which revealed that a vast majority of online shoppers would consider buying clothing if they could see a virtual picture of themselves in the attire beforehand. This finding underscores the potential of our AI -powered Virtual Dressing technology to not only enhance the online shopping experience by providing a realistic visualization of clothing fit but also significantly reduce return rates due to size or fit dissatisfaction. Our experiments demonstrate the system's efficacy in creating realistic and customizable virtual dressing experiences, showcasing its potential to become an integral part of future e-commerce platforms.

关键词： Surveys Technological innovation Computational modeling Semantic segmentation Scalability Clothing Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

8th international conference on Augmented Reality, Virtual Reality and computer graphics, AVR 2021

8th International Conference on Augmented Reality, Virtual R...

引用

8th international conference on Augmented Reality, Virtual Reality and computer graphics, AVR 2021

ISBN: (纸本)9783030875947

The proceedings contain 52 papers. The special focus in this conference is on Augmented Reality, Virtual Reality and computer graphics. The topics include: Immersive Insights: Virtual Tour Analytics System for Understanding Visitor Behavior;Immersive VR as a Promising Technology for computer-Supported Mindfulness;AR Scribble: Evaluating Design Patterns for Augmented Reality User Interfaces;interdisciplinary Collaboration in Augmented Reality Development - A Process Model;interoperable Dynamic Procedure Interactions on Semantic Augmented Reality Browsers;Creating Immersive Play Anywhere Location-Based Storytelling Using Mobile AR;efficient Augmented Reality on Low-Power Embedded Systems;visualizing Building Energy Measurement Data in Mixed Reality Applying B.I.M.;VIAProMa: An Agile Project Management Framework for Mixed Reality;developing a Gesture Library for Working in a Virtual Environment;the Experience "Mondrian from Inside". An Immersive and Interactive Virtual Reality Experience in Art;Initial Evaluation of an Intelligent Virtual Museum Prototype Powered by AI, XR and Robots;virtual Reality in Italian Museums: A Brief Discussion;uncovering the Potential of Digital Technologies to Promote Railways Landscape: Rail to Land Project;mobile Extended Reality for the Enhancement of an Underground Oil Mill: A Preliminary Discussion;design of a Serious Game for Enhancing Money Use in Teens with Autism Spectrum Disorder;proposed System for Orofacial Physiotherapy Based on a Computational Interpretation of Face Gestures to Interact with a 3D Virtual Interface;A Virtual Reality Based Application for Children with ADHD: Design and Usability Evaluation;a New Technique of the Virtual Reality visualization of Complex Volume Images from the computer Tomography and Magnetic Resonance imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Brain Tumor Diagnosis with MedMamba: A Novel Application in Neural imaging Analysis

Enhancing Brain Tumor Diagnosis with MedMamba: A Novel Appli...

引用

Intelligent Computing and Human-computer Interaction (ICHCI), international conference on

作者： Xinrui Chen School of Computer Science and Technology Beijing Jiaotong University Beijing China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Brain tumors pose a great threat to human health and need to be diagnosed at an early stage. MRI plays an important role in assisting diagnosis due to its clear soft tissue visualization. Currently, the application of deep learning techniques in medical imaging shows the possibility of outperforming humans in terms of diagnostic accuracy and speed. This study explores the application of transfer learning and MedMamba models for brain tumor diagnosis, with a particular focus on their role in performing MRI brain tumor image classification. The MedMamba model is introduced and evaluated, which is a new adaptation of the Mamba framework optimized for the medical imaging field. This study not only compares the performance of MedMamba models with traditional deep learning models such as Convolutional Neural Network and Vision Transformer, but also highlights the effectiveness of transfer learning in improving these models for specialized tasks in medical diagnosis. The main purpose is to describe the performance optimization capabilities provided by transfer learning and to demonstrate the inherent advantages of the MedMamba model. The model combines an innovative design with a streamlined architecture for efficient image processing. The positive role of transfer learning in the task of brain tumor image classification and the potential of MedMamba to set a new benchmark in this area are highlighted through comprehensive testing and evaluation of results on a brain MRI image dataset.

关键词： Deep learning Adaptation models Analytical models Accuracy Magnetic resonance imaging Transfer learning Brain tumors Brain modeling Medical diagnostic imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

A Physical Device to Help the Visually Impaired Read Money Using AI/Machine Learning in Third World Countries 30

A Physical Device to Help the Visually Impaired Read Money U...

引用

30th international conference in Central Europe on computer graphics, visualization and computer Vision, WSCG 2022

作者： Mathihalli, Nidhi Saratoga High School 20300 Herriman Ave SaratogaCA95070 United States

ISBN: (纸本)9788086943336

There are over 285 million blind people in the world, with approximately 87% of them living in developing countries. However, in the third world countries, there is currently very little technology to help the visually impaired, especially with financial independence. In this article we present the machine learning algorithms used to develop the device to help visually impaired distinguish between different forms of currency. Using the various currency images, we form a data set that is used to train the transfer learning model. Experimental results show over 94% accuracy with transfer learning model. The device is designed to be portable and hand-held. The device can distinguish between 1, 5, 10, and 20 dollar currency bills. Additionally, the model can work offline. Overall, the device is cost effective, portable, and can be used in the absence of internet connectivity. © 2022 University of West Bohemia. All rights reserved.

关键词： computer vision

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500页 << < 77 78 79 80 81 82 83 84 85 86 > >>

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：