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

3,180 篇 会议
40 篇 期刊文献
33 册 图书

馆藏范围

3,253 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,694 篇 工学
- 1,180 篇 计算机科学与技术...
- 863 篇 软件工程
- 644 篇 信息与通信工程
- 275 篇 电气工程
- 194 篇 光学工程
- 188 篇 控制科学与工程
- 181 篇 生物工程
- 136 篇 电子科学与技术（可...
- 129 篇 机械工程
- 114 篇 生物医学工程（可授...
- 109 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
804 篇 理学
- 431 篇 物理学
- 254 篇 数学
- 194 篇 生物学
- 74 篇 统计学（可授理学、...
- 70 篇 化学
- 61 篇 系统科学
335 篇 管理学
- 196 篇 图书情报与档案管...
- 158 篇 管理科学与工程(可...
- 54 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
15 篇 经济学
14 篇 军事学
2 篇 艺术学
1 篇 历史学

主题

498 篇 visualization
287 篇 visual communica...
201 篇 image processing
196 篇 feature extracti...
154 篇 image coding
117 篇 training
95 篇 accuracy
91 篇 semantics
88 篇 multimedia commu...
85 篇 deep learning
83 篇 cameras
83 篇 computer vision
79 篇 computational mo...
78 篇 signal processin...
78 篇 humans
78 篇 streaming media
75 篇 image segmentati...
64 篇 wireless communi...
64 篇 image reconstruc...
63 篇 data mining

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 state key labora...
7 篇 institute of ima...
6 篇 institute of inf...
6 篇 institute for in...
6 篇 peng cheng labor...

作者

25 篇 guangtao zhai
15 篇 sumei li
14 篇 xiongkuo min
12 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

3,183 篇 英文
47 篇 其他
23 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 3253 条记录，以下是291-300 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

A Joint Multi-Gradient Algorithm for Demosaicing Bayer Images 8

A Joint Multi-Gradient Algorithm for Demosaicing Bayer Image...

引用

8th International conference on communication, Image and Signal processing, CCISP 2023

作者： Wu, Di Xin, Zhihui Zhang, Chao School of Physics and Electronic Information Yunnan Normal University Kunming China

ISBN: (纸本)9798350305838

In image sensors such as CMOS and CCD, de-mosaicing is usually required to replace Bayer-format images with RGB-format images. Poor de-mosaicing algorithms can produce zipper effects and pseudo-colors, etc. In view of this situation and the hardware requirements of image devices, the original de-mosaicing technology gradually fails to meet the practical needs. On the other hand, although the deep learning-based de-mosaicing technology is more effective, the computational volume is too large, occupies too much hardware resources, and is difficult to be realized on the hardware platform. Therefore, this paper proposes a de-mosaicing algorithm based on multi-gradient union, which improves the traditional gradient-based first-order differentiation method, designs a new gradient operator, and ultimately judges the image edges by means of four gradient direction decisions to interpolate along the image edges. Experiments show that the algorithm in this paper has better recovery in image edges as well as texture complex regions with higher PSNR and SSIM values and better subjective visual perception compared to the traditional gradient algorithms such as BI, Cok, Hibbard, Laroche, Hamiton, while the algorithm involves only the add-subtract and shift operations, which is suitable to be implemented on the hardware platform. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Content Based Image Retrieval Techniques

A Review on Content Based Image Retrieval Techniques

引用

2023 International conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Suresh Kumar, J.S. Maria Celestin Vigila, S. Noorul Islam Centre for Higher Education Kumaracoil Department of Computer Science and Engineering Tamilnadu Kanyakumari India Noorul Islam Centre for Higher Education Kumaracoil Department of Information Technology Tamilnadu Kanyakumari India

ISBN: (纸本)9798350333244

Significant interest in Content-Based Image Retrieval (CBIR) has been identified over the last two decades, which utilizes image and video perception to find adequate images. The availability of graphical and multimedia data, as well as the expansion of the Internet, demands field matching. Because of the lack of visual content as a ranking clue, methodologies for visual retrieval that use text search methods may suffer from lack of consistency between full texts and visual content. Many programmers and tools have been developed to help users develop, implement, and conduct research on visual or audio content, as well as to browse large multimedia repositories. A benchmark for transmission model has been established DICOM, and patient data can be ended up saving along with the images, although there are still a few issues with standardization. Several papers have proposed content-based access to medical images to aid clinical decision-making and simplify medical evidence, and instances for integrating based on their content access methods into images and communication systems have been developed. This work provides a thorough evaluation of current advancements in the fields of CBIR. This investigation utilizes key characteristics of numerous retrieval methods for images and frameworks, ranging from basic identification of features from images to current deep-learning approaches. © 2023 IEEE.

关键词： Hospital data processing

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks for Image-Based Indian Sign Language Recognition: A Comprehensive Review and Practical Analysis 1

引用

2nd International conference on Advances in Data-driven Computing and Intelligent Systems, ADCIS 2023

作者： Kaur, Harleen Bedi, Sanjam Kaur Rao K, Mallikharjuna Lekhana, M.A. Data Science and Artificial Intelligence International Institute of Information Technology Naya Raipur Chhattisgarh Naya Raipur India Electronics and Communication Engineering International Institute of Information Technology Naya Raipur Chhattisgarh Naya Raipur India

ISBN: (数字)9789819995318

ISBN: (纸本)9789819995301

Addressing the communication barriers faced by individuals with vocal and hearing disabilities, sign language serves as a visual means of expression. However, the limited understanding of sign language among the general population creates significant challenges in various settings, such as banks, airports, and supermarkets. To overcome this, a sign language recognition (SLR) system is essential. This study focuses on developing a real-time word-level sign language recognition system that translates sign language into text, with a specific emphasis on Indian sign language (ISL) to cater to the needs of the deaf and hard-of-hearing community in India. Our research presents an ISL-based sign language recognition system, enabling users to capture hand movement images through a web camera, with the system accurately predicting and displaying the corresponding sign name. The captured images undergo several processing stages, incorporating computer vision techniques like grayscale conversion, dilatation, and masking. To achieve robust recognition, a convolutional neural network (CNN) is trained on the collected dataset, demonstrating exceptional performance with a 99% accuracy rate. This research contributes to the advancement of assistive technologies by providing an effective solution for real-time ISL recognition, promoting inclusive communication and accessibility for individuals with hearing and vocal impairments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Extensive Survey on Image Compression using Deep Learning 14

Extensive Survey on Image Compression using Deep Learning

引用

14th International conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Nagarsenker, Anish U. Khandekar, Prasad D. Deshmukh, Minal School of Electronics and Communication Engineering Dr.Vishwanath Karad MIT World Peace University Pune India Vishwakarma Institute of Information and Technology Pune India

Nowadays, Data Compression is adopted because it leads to pruning transmission bandwidth, storage hardware and data communication time. Deep Neural Networks (DNN) have confirmed exquisite achievements in several tasks such as Image Classification, Image processing etc. Excellent performances with speech, audio or image input signals differentiates Convolutional Neural Networks (CNN) from other neural networks. Enhancing the video and lossy image compression visual quality is treated as a serious problem, but the modern advances in computing power along with the accessibility of sizeable training datasets has led to the usage of deep learning networks like CNNs to deal with image processing and image recognition tasks. Some of the image and video compression techniques (lossy as well as lossless techniques) include JPEG, JPEG2000, BPG, GIF, PNG, MPEG etc. Data Compression along with DNN ensures that there is not much loss in data, size is reduced and the accuracy also is preserved. In the following section, a comparison of various papers related to data compression and image compression using Deep Learning Techniques like CNN is provided along with suggestions for topics that can be taken up in the near future. © Grenze Scientific Society, 2023.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Accurate and Efficient Segmentation of Malignant Pulmonary Adenocarcinoma Nodules Using the Deformable Transformer Based on U-Net 6

Accurate and Efficient Segmentation of Malignant Pulmonary A...

引用

6th International conference on information communication and Signal processing, ICICSP 2023

作者： Zhang, Zheng Lin, Yuan Gu, Zhongze Southeast University School of Biological Science and Medical Engineering Nanjing China Shanghai Jiao Tong University School of Mechanical Engineering Shanghai China

ISBN: (纸本)9798350339994

Pulmonary adenocarcinoma tumors exhibit heterogeneity, and a single factor is often insufficient to fully describe the overall condition of tumor lesions. Therefore, the acurrate segmentation of critical targets in medical images of lung cancer is crucial for accurate diagnosis by clinical physicians. However, at present, radiologists need to manually or semi-automatically perform tasks such as measuring tumor size, location, and surrounding tissues, which consumes valuable time and resources and may lead to inter- and intra-observer variability, thereby affecting segmentation accuracy. In response to the above challenges, this study achieves accurate and efficient segmentation of malignant pulmonary adenocarcinoma nodules, which are with more randomness and variable region and size, using the deformable transformer based on U-Net with bridge connections (DeTrans U-Net). This approach achieves low computational costs and high accuracy in segmenting malignant pulmonary adenocarcinoma nodules. Compared to U-Net, the transformer exhibits higher naturalness and effectiveness in handling higher-level visual semantic information. The method reduces computational overhead by utilizing this advantage and integrating deformable self-attention mechanism and multi-scale features while outperforming 2D/3D-UNet in segmentation accuracy. In the public test set, the method achieves an average DICE coefficient of 0.871, representing an improvement of 4.80% and 1.24% compared to the 2D/3D-UNet models. Furthermore, it has been validated on an internal hospital test set for the first time, demonstrating its ability to meet clinical requirements. The accurate and efficient segmentation of pulmonary adenocarcinoma achieved in this study holds significant importance for automated measurement of nodule diameter, morphological assessment, and prognosis prediction. © 2023 IEEE.

关键词： accurate biomedical image processing DeTrans U-net efficient pulmonary adenocarcinoma nodules

来源：评论

学校读者我要写书评

暂无评论

Multimodal Knowledge Graph for Database Alarm based on Enhanced Fusion Strategy 6

Multimodal Knowledge Graph for Database Alarm based on Enhan...

引用

6th International conference on Next Generation Data-Driven Networks, NGDN 2024

作者： Gao, Dequan Li, Jiwei Feng, Bao Wang, Zhifan Ding, Xuewei Zhang, Linfeng State Grid Information & Telecommunication Brach Beijing China Nanjing Nari Information & Communication Technology Co. Nanjing China

ISBN: (纸本)9798350388374

Database alarms are a pivotal monitoring mechanism, designed to notify system administrators of potential database performance issues, security risks, or failures in a real-time context. Traditional database alarm systems typically depend on pre-established rules and thresholds, which curtails their efficacy when confronted with unknown or intricate anomalies. Moreover, these systems often neglect the multimodal characteristics of alarm data, such as textual logs and visual charts, further impairing the precision and promptness of the alarm. We put forward an innovative database alarm management model, ImageKnowledgeRetriever and the Advanced Textual Knowledge Retriever module are designed to extract the image and text information and design a fusion strategy to merge multiple modal characteristics. Our model is adept at comprehending and processing textual logs, as well as analyzing and interpreting image data, including performance charts and architectural diagrams. This method enables our model to conduct a more exhaustive analysis of alarms, thereby pinpointing and diagnosing database issues with heightened accuracy. Our model demonstrates superiority over existing database alarm systems regarding accuracy and F1 score. Specifically, our model achieves an average accuracy enhancement of 8.1% and surpasses the current leading model by 0.5% in the F1 score metric. These findings affirm the advanced capabilities and effectiveness of our model in managing database alarms. © 2024 IEEE.

关键词： Alarm systems

来源：评论

学校读者我要写书评

暂无评论

Location-Aware visual Question Generation with Lightweight Models

Location-Aware Visual Question Generation with Lightweight M...

引用

2023 conference on Empirical Methods in Natural Language processing, EMNLP 2023

作者： Suwono, Nicholas Collin Chen, Chih Yao Hung, Tun Min Huang, Ting-Hao Liao, I-Bin Li, Yung-Hui Ku, Lun-Wei Sun, Shao-Hua Institute of Information Science Academia Sinica National Taiwan University Taiwan Pennsylvania State University United States Hon Hai Research Institute

ISBN: (纸本)9798891760608

This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location. Specifically, we represent such location-aware information with surrounding images and a GPS coordinate. To tackle this task, we present a dataset generation pipeline that leverages GPT-4 to produce diverse and sophisticated questions. Then, we aim to learn a lightweight model that can address the LocaVQG task and fit on an edge device, such as a mobile phone. To this end, we propose a method which can reliably generate engaging questions from location-aware information. Our proposed method outperforms baselines regarding human evaluation (e.g., engagement, grounding, coherence) and automatic evaluation metrics (e.g., BERTScore, ROUGE-2). Moreover, we conduct extensive ablation studies to justify our proposed techniques for generating the dataset and solving the task. ©2023 Association for Computational Linguistics.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Flower Classification using Deep Networks 2

A Novel Approach for Flower Classification using Deep Networ...

引用

2nd International conference on Data Science and information System, ICDSIS 2024

作者： Jeevan Reddy, A. Natarajan, B. Abinaya, A. Tamilselvi, M. Murali, P. Geetha, K. Chennai India Vit University School Of Computer Science And Engineering Tamilnadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute Of Science And Technology Department Of Electroncis And Communication Engineering Chennai Avadi India Roever Engineering College Department Of Computer Science And Engineering Tamil nadu Perambalur India Saveetha Institute Of Medical And Technical Sciences Saveetha School Of Engineering Department Of Cse Tamilnadu Chennai India Chennai India

ISBN: (纸本)9798350381665

The introduction of transformer models, which utilize a self-attention mechanism within deep neural networks, represents a notable breakthrough in natural language processing. This advancement has spurred researchers to investigate its applicability in computer vision tasks. Transformer-based models have showcased remarkable performance compared to traditional convolutional and recurrent neural networks across a spectrum of visual tasks, highlighting their prowess in representation learning. This study aims to classify vision transformer models according to their task-specific functionalities and conducts an extensive evaluation to discern their advantages and limitations. Moreover, it proposes effective strategies for integrating transformers into real-world device-based applications. Investigating the use of vision transformers, inspired by the transformer model, on diverse benchmark datasets, this research focuses on their ability to identify broad-based visual characteristics and distant dependencies through self-attentional mechanisms. Through meticulous examination on the Oxford Flowers dataset, this research delves into various pre-training methods, model topologies, and hyperparameters to enhance recognition accuracy. The findings reveal that vision transformers not only surpass previous state-of-the-art techniques but also exhibit the capacity to discern subtle differences among flower species with remarkable 98.5% accuracy. Furthermore, this research work explores the interpretability of the vision transformer model, elucidating how it recognizes and integrates crucial visual characteristics during classification. By analyzing the model' s attention maps, insights into its decision-making process are provided. In essence, this research underscores the potential of vision transformers for fine-grained image classification and contributes to the burgeoning field of research on their efficacy in computer vision tasks. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Learning to use of the structure of base 3d structures and point cloud structures from ancient artifact constructions in visual arts experience via virtual reality tool 8

Learning to use of the structure of base 3d structures and p...

引用

Joint 8th International conference on Digital Arts, Media and Technology and 6th ECTI Northern Section conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2023

作者： Sookkaew, Jirawat Puntatong, Apiwat Kaenmueang, Wisoot School of Information and Communication Technology University of Phayao Department of Computer Graphic and Multimedia Phayao Thailand

ISBN: (纸本)9798350396546

It is well known that art and ancient artifacts play a part in creating inspiration and ideas to create inspiration and to continue to develop knowledge of art, including concepts in the perspective of the visual arts. This is mainly due to the visual structure that people can generally see from the image displayed or appearance, whether it's structures, statues, sculptures, workpieces, or various other forms. The uses and benefits of technology in relation to the study of ancient artifacts, art, or buildings are many. There are many tools and technologies that come to help with the study, recording, research, or extension of the concept and origin of past art objects. In a variety of steps and processes, a variety of technologies have helped to create benefits in a variety of steps and processes through the techniques of computer programs or processing from a variety of tools. There are steps that give rise to the appearance that is based on the original structure, like the process of creating 3D structures using the process of photogrammetry. It is a technological process that brings a variety of images into the processing of shapes, colors, light, and position and creates a structure according to real objects. Its unique feature is the appearance of millions of point-colored specks that form its structure. It is a feature derived from the digital process and from real historical works that creates works that will inspire the viewer in another way derived from ancient art that is conveyed through the style of digital art. In addition, the application of broadcasting and presenting with a new form of technology, especially the use of virtual reality (V.R.) media tools for the transmission of work, creates a dimension in how to present work to people in a spectacular way with the characteristics and strengths of V.R.. is the creation of a link between users and media to experience the same virtual world. Therefore, bringing such point cloud work to the audience is a

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

On the Role of Perceptual information in Image Classification 1

引用

2nd International conference on Signal and Data processing, ICSDP 2022

作者： Kashyap, Manish Department of Electronics and Communication Engineering National Institute of Technology Bhopal India

ISBN: (数字)9789819914104

ISBN: (纸本)9789819914098

In this paper, the following hypothesis is validated—"Alternate image representations, of the same image, that preserve visual perception do not degrade the classification accuracy". The underlying phenomenon that is exploited is the property of the human visual system to see an area in a digital image as a continuous region even though it is discrete. This is because the human eye senses energy per unit area rather than closely spaced individual pixels. In our current work, we use ‘Linear discriminant analysis’ (LDA) and ‘Convolutional neural networks’ (CNN) for classifying images and their alternate representations. The results suggest that the representation of data is immaterial and perceptual information actually classifies the images. The primary contribution of this paper is suggesting ‘feature space reduction while preserving perception’ as an alternative to ‘dimensionality reduction’. By using traditional methods of dimensionality reduction, perception-based information is lost. In the process, we develop the following: (1) An algorithm to convert 256 Gy level grayscale image to gray level grayscale image where such that the visual perception is preserved. The case of, i.e., binary image is particularly of interest to us because of its appealing applications. (2) An algorithm to define clustering efficiency based on density. The applications of reduced data size and search space include compression, transmission efficiency, big data handling, efficient storage, etc. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

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326页 << < 26 27 28 29 30 31 32 33 34 35 > >>

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：