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

1,851 篇 会议
40 篇 期刊文献
7 册 图书

馆藏范围

1,898 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,517 篇 工学
- 1,317 篇 计算机科学与技术...
- 750 篇 软件工程
- 430 篇 电气工程
- 252 篇 信息与通信工程
- 251 篇 光学工程
- 195 篇 生物工程
- 118 篇 生物医学工程（可授...
- 117 篇 控制科学与工程
- 95 篇 电子科学与技术（可...
- 87 篇 机械工程
- 68 篇 化学工程与技术
- 59 篇 安全科学与工程
- 37 篇 仪器科学与技术
- 37 篇 交通运输工程
- 34 篇 材料科学与工程（可...
- 22 篇 建筑学
- 18 篇 农业工程
620 篇 理学
- 324 篇 物理学
- 232 篇 数学
- 209 篇 生物学
- 71 篇 化学
- 62 篇 统计学（可授理学、...
- 28 篇 系统科学
345 篇 医学
- 333 篇 临床医学
- 61 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
174 篇 管理学
- 121 篇 图书情报与档案管...
- 66 篇 管理科学与工程(可...
24 篇 农学
- 22 篇 作物学
23 篇 法学
- 21 篇 社会学
12 篇 教育学
8 篇 经济学
5 篇 军事学
2 篇 文学

主题

232 篇 computer vision
101 篇 image processing
92 篇 deep learning
73 篇 image segmentati...
68 篇 feature extracti...
41 篇 object detection
41 篇 convolutional ne...
37 篇 computational mo...
36 篇 image enhancemen...
34 篇 image reconstruc...
33 篇 machine learning
32 篇 graphics process...
32 篇 image classifica...
31 篇 face recognition
30 篇 visualization
29 篇 cameras
26 篇 image edge detec...
23 篇 training
22 篇 pixel
21 篇 generative adver...

机构

15 篇 indian institute...
12 篇 indian inst tech...
9 篇 indian statistic...
9 篇 indian institute...
9 篇 indian inst tech...
8 篇 indian institute...
8 篇 indian inst tech...
7 篇 indian stat inst...
7 篇 indian inst tech...
7 篇 indian institute...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian inst tech...
7 篇 indian inst sci ...
6 篇 indian inst tech...
6 篇 department of co...
6 篇 indian inst tech...
6 篇 indian inst sci ...
6 篇 indian institute...
6 篇 indian inst tech...

作者

31 篇 chaudhury santan...
25 篇 mukherjee jayant...
25 篇 chaudhuri subhas...
21 篇 das sukhendu
16 篇 lall brejesh
15 篇 babu r. venkates...
15 篇 raman shanmugana...
13 篇 das partha prati...
13 篇 mukherjee dipti ...
13 篇 harit gaurav
13 篇 mishra deepak
11 篇 chanda bhabatosh
11 篇 mukherjee snehas...
10 篇 biswas soma
10 篇 raman balasubram...
10 篇 jawahar c.v.
10 篇 biswas prabir ku...
10 篇 sur arijit
9 篇 banerjee biplab
9 篇 bhavsar arnav

语言

1,857 篇 英文
37 篇 其他
6 篇 中文
2 篇 俄文

检索条件"任意字段=6th Indian Conference on Computer Vision, Graphics and Image Processing"

共 1898 条记录，以下是511-520 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 Fast image Encryption Scheme Based on Simultaneous Permutation-Diffusion 22

A Fast Image Encryption Scheme Based on Simultaneous Permuta...

引用

6th International conference on graphics and Signal processing, ICGSP 2022

作者： Du, Kangming Lyu, Xin Zhang, Chao Li, Xin Zeng, Tao Zhao, Liancheng College of Computer and Information Hohai University Nanjing211100 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing211100 China Information Center Ministry of Water Resources Beijing100053 China

ISBN: (纸本)9781450396370

In the traditional image encryption algorithm where permutation and diffusion are performed independently, multiple image scans are required, which reduces the encryption efficiency. In this paper, a fast image encryption scheme based on simultaneous permutation-diffusion is proposed, which performs simultaneous permutation-diffusion row by row and column by column. Firstly, the sorting and cyclic-shift are combined for the permutation. the permutation index sequence of the first row/column is obtained by sorting, and the rest is updated by the cyclic-shift operation related to the plain image, which can resist the chosen-plaintext attack. Secondly, cross-diffusion is performed with dynamic index sequences, which enhances the randomness of the diffusion behavior. Finally, the permutation and diffusion are performed at the same time. therefore, a round of permutation and diffusion only needs to scan the image once, which improves the encryption efficiency. Note that our scheme only needs to generate and sort chaotic sequences with row/column level length, which reduces the iteration times of the chaotic system and sorting length. In addition, all index sequences are updated at row/column level, which is faster than pixel-level. the simulation results and security analysis show that our scheme has higher encryption efficiency than existing similar methods, and has sufficient security to resist common attacks. © 2022 ACM.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Fusion with GCN and SE-ResNeXt Network for Aspect Based Multimodal Sentiment Analysis

Fusion with GCN and SE-ResNeXt Network for Aspect Based Mult...

引用

IEEE Information Technology, Networking, Electronic and Automation Control conference

作者： Jun Zhao Fuping Yang College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

Aspect Based Multimodal Sentiment Analysis to determine the sentiment polarity of each aspect mentioned in multimodal posts or comments. However, many models fail to explain the related syntactic constraints and long-term word dependencies, as well as lack image feature extraction. In view of the above problems, we propose a Fusion with GCN and SE-ResNeXt Network(FGSN), which constructs a graph convolution network on the dependency tree of sentences to obtain the context representation and aspects words representation by using syntactic information and word dependency. Also, we use the pretrained network SE-ResNeXt101 to extract image features and generate visual representations. Moreover, the position attention and channel attention mechanism are used to obtain the image features. Finally, we fuse image features and text features to classify sentiment polarity. the experimental results show that our model performs well on the two datasets of TWITTER-2015 and TWITTER-2017.

关键词： Visualization Sentiment analysis Convolution Mood Fuses Computational modeling graphics processing units

来源：评论

学校读者我要写书评

暂无评论

EREH-Net: A CNN and Transformer Hybrid Model for Industrial Robot Grasping vision Localization

EREH-Net: A CNN and Transformer Hybrid Model for Industrial ...

引用

International conference on Communications, Information System and computer Engineering (CISCE)

作者： Haixia Pan Mojie Ma Leping Wang Sinan Lin Beihang university Beijing China Jomoo Xiamen China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

Industrial robot vision localization system, aims to enable the vision system to identify the grasping center and rotation angle of target components, thereby assisting in the localization of industrial robot. However, there are limitations in identifying boundaries with weak contrast, and it is difficult to cover different products by the same algorithm. To address these challenges, this study proposes a hybrid network based on CNN and Transformer Salient Object Detection (SOD), as well as related grasping localization algorithm: First, our proposed hybrid network effectively utilizes both global and local features to segment targets. then, the localization post-processing algorithm calculates the grasping center and rotation angle based on the contours of the segmentation image. Next, we introduce an Edge Reverse Enhance Module (EREM) to enhance the features of the segmentation boundary. Finally, Loss function is employed to measure the deviation between the segmentation boundary and ground truth, the center distance between prediction and ground truth. At the grasping center x, grasping center y, and rotation angle A, the Mean Absolute Error (MAE) reached 2.78 pixels, 5.75 pixels, and 2.43°, respectively, which were reduced by 45%, 38.2%, and 70.3% compared to the second place. the mIoU reaches 0.987, which is a 0.003 improvement over the second place. Furthermore, our model has been validated on other industrial datasets T-LESS.

关键词： Location awareness image segmentation Visualization Robot vision systems Grasping Object segmentation Production

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability of Domain Adaptation Networks through Domain Alignment Layers 34

Improving Transferability of Domain Adaptation Networks Thro...

引用

34th SIBGRAPI conference on graphics, Patterns and images (SIBGRAPI)

作者： Silva, Lucas F. A. Pedronette, Daniel C. G. Faria, Fabio A. Papa, Joao P. Almeida, Jurandy Univ Fed Sao Paulo UNIFESP Inst Ciencia & Tecnol Sao Jose Dos Campos SP Brazil Sao Paulo State Univ UNESP Dept Stat Appl Math & Comp Rio Claro SP Brazil Sao Paulo State Univ UNESP Dept Comp Bauru SP Brazil

ISBN: (纸本)9781665423540

Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. these layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. the experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.

关键词： graphics Deep learning computer vision Adaptation models Predictive models Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation and Recognition of Complex images Based on Convolutional Neural Networks

Automatic Segmentation and Recognition of Complex Images Bas...

引用

IEEE International conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Yuliang Dong Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

With the progress of computer vision and artificial intelligence, deep learning has become a key tool to effectively improve the accuracy and robustness of fuzzy image processing. In this paper, based on the YOLO algorithm, a systematic analysis of the complex image recognition problem is carried out by training the convolutional neural network model, which is intended to solve the problem of single word segmentation, text recognition, and matching in complex images. First of all, the original image preprocessing, first gray-scale processing of the image after the resultant image binarization, and then edge detection, and feature extraction. the resultant image is used to build a segmentation model through the YOLO algorithm, which transforms the complex image target detection task into a single regression problem, using a convolutional neural network to predict the bounding box and category probabilities directly from the input image, thus training a model that can perform automatic single-word segmentation and recognition. Experimental results show that the accuracy of this model is 65.48%. the method in this paper can accurately segment and recognize complex images, extract and recognize the text in the image, and provide a method support for dealing with fuzzy images.

关键词： YOLO Training image segmentation Systematics Text recognition Target recognition image edge detection Computational modeling Predictive models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multimodal Transformers for Medical image Captioning: Enhancing Automated Descriptions via AI Systems

Optimizing Multimodal Transformers for Medical Image Caption...

引用

International image processing, Applications and Systems conference (IPAS)

作者： Mithila Arman Md. Khurshid Jahan Ahmed Faizul Haque Dhrubo Md. Mahfuzur Rhaman Sumaya Binte Zilani Choya Din Mohammad Dohan Md. Ashiq Ul Islam Sajid Md. Golam Rabiul Alam Dept. of CSE BRAC University Dhaka Bangladesh Dept. of ECE North South University Dhaka Bangladesh Dept. of Computational Data Science George Mason University Fairfax Virginia USA Dept. of CSE American International University-Bangladesh Dhaka Bangladesh

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

In contemporary diagnostic workflows, medical image captioning has emerged as a pivotal advancement, combining deep learning methodologies and transformer architectures to enhance accuracy and efficiency in medical interpretations. this paper proposes the optimization of multimodal transformers for automated medical image captioning, focusing on integrating vision Transformers (ViT) and Bidirectional Auto-Regressive Transformers (BART) with novel variations such as Swin Transformers and GPT-2. We use a robust multimodal AI framework to explore how these architectures synergize to generate coherent and diagnostically relevant captions for radiological images. We assess the performance of multiple transformer models by employing the ROCO dataset, containing paired X-ray images and expert-generated reports. Our findings demonstrate that the ViT + BART combination yields the most stable and accurate captions, minimizing training and validation loss. In contrast, DEiT + MBART displayed instability, highlighting the need for further hyperparameter tuning. through this comparative analysis, we underscore the critical role of transformer-based models in reducing the cognitive load on medical professionals, enhancing diagnostic accuracy, and promoting real-time, automated medical image interpretation.

关键词： Deep learning Training computer vision Accuracy Transformers Real-time systems Artificial intelligence Medical diagnostic imaging X-ray imaging Tuning

来源：评论

学校读者我要写书评

暂无评论

third vision for Safeguarding Women with A Live Surrounding Update using Deep-Learning for computer vision 6

Third Vision for Safeguarding Women with A Live Surrounding ...

引用

6th IEEE International conference on Signal processing, Computing and Control, ISPCC 2021

作者： Anju, A Abilash, M R Balaji, V Sayee Darshan, J K KCG College Of Technology Department Of Information Technology Chennai India

ISBN: (纸本)9781665425520

the Large deployment of deep learning is safeguarding women all over the world. the main motive is to discover a few specific design necessities for women's safety. Women's safety is the most crucial issue in every country. Women are harassed and distressed, and on occasion, whilst pressing assistance is needed, there may be no required place for women so that people can help. It's vital that everyone is privy to the significance of women's safety;all need to examine that they ought to be properly protected. the formerly existing methodology enables tracking down the victim's place after the crime has been committed. Whenever she comes in touch with any individual out of doors, the person's activities and the phrases they talk about can be monitored constantly. If the person's feelings vary, ensuing in any dangerous motion, and their speech results are abusive and vulgar, then the system will encounter it and process the captured image. It will forward it to the own circle of relatives that the user has given with GPS place tracked from the IP address in the form of SMS to their phone number and email. thus the undertaking enables in saving womankind and safeguarding her in the current state of affairs. © 2021 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A yolo-based approach for Aedes aegypti larvae classification and detection 6

A yolo-based approach for Aedes aegypti larvae classificatio...

引用

6th International conference on image, vision and Computing, ICIVC 2021

作者： Hubalde, Angelo M. Padilla, Dionis A. Santos, Denzel Antoinette C. School of Electrical Electronics and Computer Engineering Mapúa University Manila Philippines

ISBN: (纸本)9781665443685

Mosquitoes are small, flying insects that can be found almost anywhere in the world. Although most of these creatures are just considered a nuisance, a few of its species can be vectors of some of the deadliest viruses and diseases that can greatly affect living organisms—animals and people alike. Aedes aegypti species, for instance, are deemed as the primary vector of the infamous dengue virus that has been around for a long time. With this, there have been many studies, mostly only with limited success, in different fields of learning on how to control and suppress both the mosquitoes and the diseases they carry. While some of these studies and research experiments are geared towards the use of modern technology such as machine learning, deep learning, and image processing, there are still a lot of strategies and methods that are yet to be discovered to improve present-day approaches and attain better results that are more sustainable and efficient. And so, the main goal of this study is to aid in the early suppression and prevention of the primary vector of dengue by creating a system implemented with the You Only Look Once (YOLO) algorithm that can detect and classify whether a mosquito larva is an Aedes aegypti species or not. Results showed that the system was able to correctly recognize most of the larval samples subjected to testing, with a root mean square error of 0.45 and 0.77 for Aedes and Non-Aedes larvae respectively. © 2021 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Customized YOLOv3 model for face detection in crowded images 6

Customized YOLOv3 model for face detection in crowded images

引用

6th International conference on Computing, Communication, Control and Automation, ICCUBEA 2022

作者： Al Othmani, Yasmin Kanungo, Priyadarshi Ghanem, Safwan Alnaeb, Abd Alaziz C. V. Raman Global University Dept. of Electronics and Telecommunication Engineering Odisha Bhubaneswar India C. V. Raman Global University Dept. of Computer Science and Engineering Odisha Bhubaneswar India Damascus University Dept. of Electronics and Telecommunication Engineering Damascus Syria

ISBN: (纸本)9781665484510

Face detection (FD) is an essential stage in many applications like face recognition, object detection, and class attendance systems. the accuracy of the FD system affects the further processing stages in those applications. therefore, the reliable FD system should give all faces that exist in the input image, and the corresponding bounding boxes as well. the standard methods for the FD system work well for frontal faces. However, those methods have a low accuracy where faces are blocked, blurred, or different in scales. In this work, hyper-parameters of the you-only-look-once version 3 (YOLOv3) algorithm are customized and used for FD in crowded images. Firstly, the dimensions of the anchor boxes is fine-tuned to be more appropriate to detect different face scales in crowded images. this customization gives better performance for YOLOv3 comparing with the predefined anchor boxes in this algorithm. Secondly, the dimensions of features on the last detection layers are reduced to enhance the detection speed. Finally, the proposed model is compared with other vision-based and deep learning-based FD algorithms using real-life crowded images. the conducted experiments on the Google open images v4 dataset show that accuracy of the customized YOLOv3 is 94.2% which outperforms the other models. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

the Nonlinear Hyperplane CNN for Hyperspectral image Classification 6

The Nonlinear Hyperplane CNN for Hyperspectral Image Classif...

引用

6th International conference on Signal and image processing, ICSIP 2021

作者： Zhang, Xinsheng Wang, Zhaohui Li, Ningyang Hainan University School of Computer Science and Technology Haikou China

ISBN: (纸本)9780738133737

With the development of hyperspectral technology, effective classification of hyperspectral images (HSI) has been one of the research hotspots. Convolutional neural network (CNN) has shown better performance in the HSI classification due to its ability of feature extraction and the special structure of weight sharing. However, the accuracy of CNN-based models is influenced by the overfitting problem. A Nonlinear Hyperplane CNN model is proposed in this paper, which improves the classification accuracy by constructing a classification hyperplane. the model is composed of two parts: feature extraction and nonlinear hyperplane construction. the Lagrange multiplier method and Karush-Kuhn-Tucker conditions are employed to construct the hyperplane. the proposal was tested on two widely used hyperspectral data sets: indian Pines and Salinas. Comparing with some well discussed models, the experimental results shown that the proposal could achieve better classification performance. © 2021 IEEE.

关键词： Feature extraction

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190页 << < 48 49 50 51 52 53 54 55 56 57 > >>

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：