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

3,206 篇 会议
41 篇 期刊文献
33 册 图书

馆藏范围

3,280 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,710 篇 工学
- 1,193 篇 计算机科学与技术...
- 868 篇 软件工程
- 652 篇 信息与通信工程
- 277 篇 电气工程
- 196 篇 光学工程
- 191 篇 控制科学与工程
- 181 篇 生物工程
- 137 篇 电子科学与技术（可...
- 130 篇 机械工程
- 115 篇 仪器科学与技术
- 114 篇 生物医学工程（可授...
- 70 篇 化学工程与技术
- 66 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...
- 44 篇 安全科学与工程
813 篇 理学
- 434 篇 物理学
- 255 篇 数学
- 194 篇 生物学
- 76 篇 化学
- 75 篇 统计学（可授理学、...
- 61 篇 系统科学
343 篇 管理学
- 196 篇 图书情报与档案管...
- 166 篇 管理科学与工程(可...
- 55 篇 工商管理
181 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

502 篇 visualization
287 篇 visual communica...
201 篇 image processing
198 篇 feature extracti...
154 篇 image coding
117 篇 training
96 篇 accuracy
91 篇 semantics
89 篇 multimedia commu...
87 篇 deep learning
84 篇 computer vision
83 篇 cameras
81 篇 computational mo...
78 篇 signal processin...
78 篇 humans
78 篇 streaming media
75 篇 image segmentati...
65 篇 real-time system...
64 篇 wireless communi...
64 篇 image reconstruc...

机构

24 篇 school of commun...
21 篇 institute of ima...
20 篇 school of inform...
20 篇 communication un...
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

3,173 篇 英文
84 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 3280 条记录，以下是301-310 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：

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

Ensemble Model Classifier in Hybrid CNN to Predict Diabetic Foot Ulcers 15

Ensemble Model Classifier in Hybrid CNN to Predict Diabetic ...

引用

15th International conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Athira, Anil Jyothi Varshepally, Anjana Manogna, Akula Sridhar, Alakunta Vivek, D. B V Raju Institute of Technology Dept.of Computer Science Engineering Medak Telangana Narsapur India

ISBN: (纸本)9798350370249

Diabetes arises due to decrease in the level of sufficient insulin produced in the human body. The prevalent issue faced by the individuals suffering from diabetes is Diabetic foot ulcer (DFU). Diabetic Feet affected around 1-4% individuals within 6.1% of diabetic population in 2023 globally. In this developing world, computer vision technologies are playing a vital role even in the field of medicine, particularly it can be beneficial in detecting and monitoring diabetes, along with its difficulties such as foot ulcers. Various models in computer vision are used for detecting the foot ulcers by image processing. Here the proposed novel hybrid model detects and monitors the diabetic foot ulcer in a proficient way. The proposed model is a combination of multiple neural network frameworks including EfficientNet as a Convolutional neural network architecture along with InceptionNet, Stacked Sparse Autoencoder (SSAE) and Sparrow Search Optimization (SSO). Every framework helps in performing different tasks in contribution for an efficient and accurate output. By analyzing diabetic foot images, EfficientNet brings out the information related to visual features and Inception-ResNet-v2 is able to capture the specific features as well as patterns from the images. Stacked Sparse Autoencoder (SSAE) can learn about the features in detail. Sparrow Search Optimization (SSO) is an optimization algorithm which can make the models work together optimally moreover, can eliminate unnecessary parameters which results in less memory requirement and makes the model smaller. The proposed model can improve the detection and management of Diabetic Foot ulcers and is expected to be 2 percentage higher than any existing models. © 2024 IEEE.

关键词： Convolutional Neural Network (CNN) Diabetic Foot Ulcer (DFU) Digital image processing Frameworks Telemedicine application

来源：评论

学校读者我要写书评

暂无评论

visual Question Answering: Convolutional Vision Transformers with Image-Guided Knowledge and Stacked Attention

Visual Question Answering: Convolutional Vision Transformers...

引用

Multimedia processing, communication & information Technology (MPCIT), International conference on

作者： Miranda Surya Prakash Madhavi Mallam Department of Electronics and Communication PES Institute of Technology and Management Visvesvaraya Technological University Belagavi Karnataka India

ISBN: (数字)9798350375466

ISBN: (纸本)9798350375473

visual Question Answering (VQA) have shown promise in understanding and answering questions about images, but they struggle with better image representation techniques and complex reasoning tasks that require external knowledge. This work addresses the mentioned limitations by incorporating an image-guided knowledge attention mechanism for improved reasoning capabilities. The objective is to enhance VQA models by integrating external knowledge and to develop a robust approach that takes advantage of hybrid transformers for image representation. To achieve these goals, a VQA model CvT-KB is proposed, utilizing a Convolutional visual Transformer (CvT) for rich visual feature extraction, a stacked attention network for effective multi-modal fusion of image and text information, and an image-guided knowledge attention mechanism to incorporate relevant knowledge from ConceptNet based on entities identified in the given question. The model demonstrates improved accuracy of 52.2% and WUPS score of 52.81% on the OK-VQA dataset compared to baseline models, and highlight the ability to utilize knowledge and achieve a deeper understanding of visual scenes.

关键词： Knowledge engineering visualization Computer vision Attention mechanisms Accuracy Image representation Transformers Feature extraction Cognition Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Improving Wart Treatment Efficacy Prediction with Immunotherapy and Cryotherapy Using SVM, RF, CVM, k-NN, MLP, and BLR Algorithms in Machine Learning

Improving Wart Treatment Efficacy Prediction with Immunother...

引用

2024 International conference on Signal processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Sanmugasundaram, R. Ramadass, Parthasarathy Devi, M.Kiruthiga Unnamalai, K. Sannasi Rajan, M.V. Rajalakshmi Institute of Technology Electronics and Communication Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India Dr. M.G.R. Educational and Research Institute Department of Information and Technology Chennai India Anna Adarsh College for Women Department of Computer Science India Sidani Innovative Management Services Dubai United Arab Emirates

ISBN: (纸本)9798331540685

Warts, characterized by small, rough, benign tumors induced by human papillomavirus (HPV), pose a challenge in treatment prediction due to variations in patient response and disease characteristics. While a machine learning-based expert prediction system and associated rules have been proposed, their success remains unsatisfactory and lacks interpretability for medical professionals. In this study, we employ a decision tree-based approach to delineate rules for predicting wart treatment success. Our findings reveal success rates ranging from 90% to 95% across different treatment methods, surpassing previous reports. Additionally, the decision tree rules generated can be converted into visual representations, enabling intuitive interpretation of treatment success rates in relation to patient age and disease duration. This method offers a straightforward and more precise interpretation of rules for medical experts, facilitating the prediction of treatment success as a percentage. © 2024 IEEE.

关键词： Cryotherapy

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Intelligent Disease Detection using Advanced Machine Learning-Based Image processing Technology 2

A Novel Framework for Intelligent Disease Detection using Ad...

引用

2nd IEEE International conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Naheeda Tharannum, B. Venkateshappa Khan, Noor A Nabi Reva University School of Electronics and Communication Bangaluru India Camellia Institute of Engineering and Technology Makaut West Bengal India

ISBN: (纸本)9798350383287

Agriculture plays a pivotal role in sustaining global food and textile production, with over 70% of the Indian population directly or indirectly reliant on this sector for their livelihood. In the Indian agricultural landscape, cotton stands out as a vital commercial crop contributing significantly to farmers' income. Despite its economic importance, cotton cultivation faces a persistent challenge - susceptibility to various diseases caused by insects, viruses, and other factors. Detecting these diseases at an early stage is crucial for preventing widespread crop damage. Traditional methods of visual inspection often fall short, necessitating the implementation of an intelligent system for accurate cotton-plant disease *** paper proposes a comprehensive framework designed to identify diseases in cotton plants, offering a solution to empower farmers with timely and precise information. By leveraging advanced image processing technology and machine learning algorithms, the proposed system enhances disease identification beyond the capabilities of the naked eye. The goal is to enable farmers to proactively identify and address specific diseases affecting their cotton crops, thereby optimizing resource allocation and ultimately increasing overall agricultural productivity. This framework represents a significant step towards sustainable and efficient cotton farming practices in India. © 2024 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Diversified Characteristics and Performance of Network visual communication Design Based on Internet Technology 9th

Diversified Characteristics and Performance of Network Visua...

引用

9th International conference on Signal and information processing, Network and Computers, ICSINC 2021

作者： Sun, Hongbo Mattek, Andrew Changchun Humanities and Sciences College Jilin Changchun China Loyola University New Orleans New OrleansLA United States

ISBN: (纸本)9789811947742

With the development of Internet technology and cultural integration, visual communication is developing towards a variety of possible directions. In modern design, the core of design work is visual communication. The development of science and technology and Internet technology also has a strong impact on visual communication. Just as the industrial revolution has changed the way of human life and promoted the great development of human social civilization, visual communication is also being affected. New technologies and theories such as virtual and reality technology and Internet technology are having a profound impact on visual communication. This paper mainly studies the diversified characteristics and performance of network visual communication design (NVCD) based on Internet technology. This paper studies the network visual communication technology, understands the thinking methods of visual information communication design, rich and diverse ways of expression and communication methods, and puts forward the problems exposed in the development of NVCD. In the we media era, the design works are intermingled, and the excessive pursuit of the sense of form falls into the void of unilateral pursuit of formal beauty. The algorithm of graphic language automatic arrangement in network visual communication is also studied to find the best size and position in NVCD for graphic arrangement. This paper also uses chart analysis method to analyze and study the use satisfaction of NVCD and its forms of expression. The experimental results show that in the form of NVCD, graphic design accounts for 27.29%, followed by film and television design accounts for 21.52%, advertising design accounts for 19.58%, font design accounts for 14.64%, logo design accounts for 9.36%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： visual communication

来源：评论

学校读者我要写书评

暂无评论

visual Aircraft Recognition via Mobile Virtual Reality 11

Visual Aircraft Recognition via Mobile Virtual Reality

引用

11th IEEE Global conference on Consumer Electronics, GCCE 2022

作者： Plupattanakit, Kantinan Choensawat, Worawat Sookhanaphibarn, Kingkarn BU-Multimedia Intelligent Technology Laboratory School of Information Technology and Innovation Bangkok University Thailand

ISBN: (纸本)9781665492324

This paper presents a mobile application for visual aircraft recognition (VACR) training. Traditional VACR training uses images, aircraft recognition cards, and video clips as training media. However, the mentioned media only provides basic information about aircraft with minimal viewing angles. Therefore the aircraft viewer mobile application is the solution for overcoming these pain points in the traditional visual aircraft recognition training. Moreover, the proposed application is easy to access and is more visualizable. The application's three significant features, aircraft information, 3D aircraft models, and mobile visual reality, give a promising result in training. © 2022 IEEE.

关键词： Three dimensional computer graphics

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328页 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：