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

1,778 篇 会议
14 册 图书
11 篇 期刊文献

馆藏范围

1,803 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,386 篇 工学
- 1,114 篇 计算机科学与技术...
- 818 篇 软件工程
- 457 篇 信息与通信工程
- 331 篇 光学工程
- 303 篇 控制科学与工程
- 199 篇 电气工程
- 181 篇 生物工程
- 152 篇 机械工程
- 126 篇 生物医学工程（可授...
- 97 篇 电子科学与技术（可...
- 85 篇 仪器科学与技术
- 65 篇 安全科学与工程
- 60 篇 化学工程与技术
- 42 篇 材料科学与工程（可...
- 40 篇 交通运输工程
- 25 篇 网络空间安全
615 篇 理学
- 373 篇 物理学
- 194 篇 数学
- 192 篇 生物学
- 61 篇 统计学（可授理学、...
- 58 篇 化学
- 25 篇 系统科学
222 篇 管理学
- 129 篇 管理科学与工程(可...
- 107 篇 图书情报与档案管...
- 46 篇 工商管理
136 篇 医学
- 125 篇 临床医学
- 58 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
37 篇 农学
- 33 篇 作物学
25 篇 艺术学
- 25 篇 设计学（可授艺术学...
20 篇 教育学
18 篇 法学
15 篇 经济学
4 篇 军事学
1 篇 文学

主题

289 篇 computer vision
164 篇 image processing
106 篇 feature extracti...
99 篇 deep learning
99 篇 image segmentati...
50 篇 object detection
47 篇 machine vision
47 篇 computational mo...
47 篇 convolutional ne...
45 篇 image enhancemen...
44 篇 image recognitio...
43 篇 cameras
37 篇 accuracy
36 篇 image edge detec...
36 篇 face recognition
34 篇 machine learning
33 篇 image color anal...
33 篇 training
31 篇 image reconstruc...
30 篇 visualization

机构

6 篇 shenyang institu...
6 篇 university of ch...
6 篇 shenyang ligong ...
5 篇 department of co...
4 篇 key laboratory o...
4 篇 school of softwa...
4 篇 school of inform...
4 篇 department of co...
4 篇 college of compu...
4 篇 beijing informat...
3 篇 school of comput...
3 篇 shanghaitech uni...
3 篇 chitkara univers...
3 篇 university of el...
3 篇 school of comput...
3 篇 institute for co...
3 篇 guangzhou civil ...
3 篇 institutes for r...
3 篇 babol noshirvani...
3 篇 computer vision ...

作者

5 篇 raman balasubram...
5 篇 lu zongqing
4 篇 zhang chao
4 篇 balasubramanian ...
4 篇 ramani sanjeev k...
4 篇 wang wei
4 篇 hossain syed akh...
4 篇 iyengar s.s.
4 篇 sanjeev kaushik ...
3 篇 liu bo
3 篇 kumar krishan
3 篇 zhang ji
3 篇 elizabeth rani g...
3 篇 neehal nafis
3 篇 rabby akm shahar...
3 篇 luc van gool
3 篇 farag aly a.
3 篇 zhao jiewen
3 篇 zou xiaobo
3 篇 zhang hualiang

语言

1,760 篇 英文
26 篇 其他
19 篇 中文
1 篇 土耳其文

检索条件"任意字段=2nd International Conference on Computer Vision and Image Processing, CVIP 2017"

共 1803 条记录，以下是341-350 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：

Multiscale Models for Real-Time Human Pose Estimation 2

Multiscale Models for Real-Time Human Pose Estimation

引用

2nd international conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2023

作者： Liu, Zongyou Li, Wenbai Wang, Hongtao Computer Scienc Shenyang Aerospace University Shenyang China

ISBN: (纸本)9798400707544

Although the lightweight OpenPose uses the depth-wise separable convolution to form the backbone to improve the computing efficiency of the model on the CPU, the lightweight OpenPose also has the following shortcomings. (1) The model has weak feature processing ability. (2) The model cannot identify multi-scale features well. In order to solve the above problems, a multi-scale model is proposed. We adjusted the network structure of the lightweight OpenPose model with reference to the network structure of RES2NET. The modified model not only recognizes multi-scale features but also has strong feature processing capabilities. The AP value of our model on the COCO2017 validation set is 0.412. The AP value of Multiscale Models is 0.037 higher than lightweight OpenPose on the COCO2017 validation set. Our future direction is to discover the influence of the model’s ability to extract multi-scale features on the model AP value. © 2023 Copyright held by the owner/author(s).

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Design of Machine vision image Target Recognition System Based on Improved ORB Algorithm 2

Design of Machine Vision Image Target Recognition System Bas...

引用

2nd IEEE international conference on Mobile Networks and Wireless Communications, ICMNWC 2022

作者： Liang, Beiyuan Guangxi Vocational&Technical Institute of Industry Guangxi Nanning China

ISBN: (纸本)9781665491112

With the rapid development of computer technology and the Internet era, machine vision is a new science and technology formed by the cross-integration of various disciplines such as image processing theory, advanced information science and digital signal processing methods based on computers. The application of computer in information processing has become an inevitable trend, it can better acquire and understand images, and it can quickly and effectively analyze, extract useful targets and provide decision makers with the required content. This can also improve work efficiency and accuracy to achieve a more precise and automated management level, and play a huge role in life. First of all, this paper uses the ORB algorithm for target recognition for the identification and positioning of static targets, but this algorithm still has the problem of low feature matching accuracy. Therefore, an improved ORB feature matching method based on multiple constraints is proposed;Secondly, it studies the design of the machine vision image target recognition system, including the overall function design of the system, the system process design and the system experimental verification. © 2022 IEEE.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Controllable One-shot Head Avatar Reconstruction 2

Controllable One-shot Head Avatar Reconstruction

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Liu, Weidong Zhang, Dingyun Guo, Yudong University of Science and Technology of China Hefei China Image Derivative Inc Hangzhou Hangzhou China

ISBN: (纸本)9798350331417

Recent advancements in the neural radiance field (NeRF) have allowed for the reconstruction of high-fidelity and expressive human head models. However, these methods often require lengthy videos and face challenges in effectively generalizing well to unseen expressions. To address this challenge, we propose a generic human head parametric model defined with a neural field. Additionally, the well-designed network architecture of this NeRF-based parametric model enables it to generalize to new identities with high fidelity. Specifically, we reconstruct a personalized canonical radiance field and a shared deformation field. The canonical radiance field models personalized facial details and hair information, while the shared deformation field models facial dynamics related to expressions such as smiling or frowning. To enhance the trained model's ability to generalize to unseen identities, we finetune the canonical radiance to reconstruct a highly realistic 3D head avatar, while freezing the deformation field to retain fine-grained control over facial dynamics. With a single image input, our method can reconstruct a personalized head avatar within a few minutes. We also utilize our method in various tasks, such as facial retargeting, expression transfer, and face relighting. Experimental results showcase the remarkable capacity of our method to accurately represent and control facial attributes. © 2023 IEEE.

关键词： component head avatar neural radiance field parametric head model

来源：评论

学校读者我要写书评

暂无评论

image inpainting algorithm based on image decomposition model and patch global structural information 2

Image inpainting algorithm based on image decomposition mode...

引用

2022 2nd conference on High Performance Computing and Communication Engineering, HPCCE 2022

作者： Liu, Lin Ye, Cuicui Wang, Kechao Liu, Zihan Mao, Yan Ma, Lihe School of Information Engineering Harbin University Harbin10086 China College of Computer Science and Technology Harbin Engineering University Harbin150001 China International School of Information Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9781510663374

With the improvement of image processing tools and the flexibility of digital image editing, automatic image inpainting has found important applications in computer vision and has also become an important and challenging topic of research in image processing. Through the analysis of the exemplar-based image inpainting method, we found the calculation of priority of image patches to fill is beneficial to the textures than the geometric structure, while the geometric structure is more important to the filling than the textures, resulting in the problem of texture extension or the discontinuity of the geometric structure in the image. The image decomposition model is applied to decompose the image to inpaint into two components: texture and cartoon, which are then filled respectively. We improve the calculation of the priority of the texture component and the cartoon component, which make it suitable to the image character. In order to solve the mismatch problem, we propose a measurement based on global structure information of the target patch and the candidate patch in this paper. The mean and variance of the pixels in the image patch representing the global structure of image patches added to the measurement formula can improve the accuracy of the best matching patch to fill the missing region. We compared our model with the Criminisi algorithm and its improved one, through applying the algorithm to the synthetic images and the natural image. We also compute the PNSF and SSIM values between the original images and the inpainted images to verify the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm can get more perceptually aware inpainted results than the Criminisi algorithm and its improved algorithm. © 2023 SPIE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain images Generation of Fundus Fluorescence Angiography Based on Generative Adversarial Networks with Self-Attention Mechanism 2

Cross-Domain Images Generation of Fundus Fluorescence Angiog...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Jiang, Lu Wang, Feng Zheng, Runan Li, Chaohong Southeast University School of Biological Science and Medical Engineering Nanjing China Suzhou MicroClear Medical Instruments Co. Ltd. Suzhou China

ISBN: (纸本)9798350331417

Fundus Fluorescein Angiography (FFA) is considered the gold standard technique for diagnosing retinal diseases. However, the invasive nature of the examination and the risk of adverse reactions to the contrast agent pose limitations and safety concerns. Therefore, it is important to explore a safe, efficient, and cost-effective alternative to acquire FFA images. Based on the rapid development of deep learning techniques in image synthesis, this paper proposes a supervised cross-domain generative adversarial network with self-attention mechanism to translate Infrared (IR) fundus images into angiography images, both acquired by confocal Scanning Laser Ophthalmoscope (cSLO). Moreover, a preprocessing method suitable for the paired fundus data of different modalities is also proposed. The experimental results prove that the performance of our method is demonstrated to be superior to state-of-the-art cross-domain image translation networks. © 2023 IEEE.

关键词： cross-domain image generation fundus fluorescein angiography image generative adversarial networks infrared fundus image self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 for Aerial images Object Detection with the Introduction of Attention Mechanism 2

Improved YOLOv5 for Aerial Images Object Detection with the ...

引用

2nd international conference on Data Analytics, Computing and Artificial Intelligence, ICDACAI 2023

作者： Xu, Linhao Zhengzhou University International College Zhengzhou450002 China

ISBN: (纸本)9798350339765

Due to the development of drone technology and researches on deep learning in computer vision, object detection of aerial images from UAVs has a wide range of applications in practical production. Aerial images have problems such as large scale variations, small and dense objects and background disturbance. Traditional object detection methods are difficult to apply in practical detection scenarios, while deep learning-based methods each has its pros and cons. In this paper, the YOLOv5 model, which is a good fit for UAVs, is chosen to deal with the challenges of aerial image object detection, and the CBAM attention module is introduced to improve the network of YOLOv5 to obtain better feature extraction capability. This paper uses dataset analysis to obtain insight into the characteristics of objects in different datasets, and uses DOTA dataset for training, combining image pre-processing and data augmentation techniques to improve the training process and enhance the robustness of the model. In addition, this paper uses Grad-CAM visualisation method in an attempt to analyse and interpret the detection results. Compared to the original YOLOv5, the improved model has an accuracy rate of 75.8%, gaining a 2.2% increase. This shows the model performs well and the attention mechanism can successfully assist in resolving the challenging issues with object detection in aerial photography scenarios. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

3D Human Motion Data Compression Based on computer vision 2

3D Human Motion Data Compression Based on Computer Vision

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Wang, Peng Jiang, Xiaolin Shandong Institute of Commerce and Technology Basic Course Teaching Department Shandong Jinan China Shandong Institute of Commerce and Technology Cloud Computing Technology and Application Industry School Shandong Jinan China

ISBN: (纸本)9798350331417

The motivation of this research is to address the issue of large storage and transmission space occupied by 3D human motion data, as well as the demand for large amounts of motion data in fields such as virtual reality and animation production. Our goal is to develop efficient 3D human motion data compression algorithms to reduce storage space and transmission bandwidth, while ensuring data quality and realism. The importance of 3D human motion data compression is mainly reflected in the fields of virtual reality and animation production. Virtual reality technology relies on accurate and realistic motion data, which often occupies a significant amount of space. Through effective compression algorithms, the storage space of motion data can be greatly reduced, thereby reducing hardware requirements and transmission costs, and improving the smoothness and real-time experience of virtual reality. In animation production, a large amount of motion data needs to be accurately captured and processed, and compression algorithms can optimize the storage and processing efficiency of the data, thereby improving the efficiency and quality of animation production. Through this research, we will delve into the technology and methods of 3D human motion data compression, and strive to provide a more efficient solution for compressing 3D human motion data with the help of advanced compression algorithms. This will bring many benefits to fields such as virtual reality and animation production, including cost reduction, performance improvement, and real-time capability, promoting innovation and development. In conclusion, this research will provide strong support and promotion for the compression of 3D human motion data and its application in virtual reality and animation production. © 2023 IEEE.

关键词： 3D human motion computer vision data compression

来源：评论

学校读者我要写书评

暂无评论

SLAM ground point extraction algorithm combining Depth image and Semantic Segmentation Network 2

SLAM ground point extraction algorithm combining Depth Image...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Zhang, Haocheng Wei, Shaungfeng Liu, Guangzu Pang, Fan Yu, Fan Beijing University of Civil Engineering and Architecture School of Geomatics and Urban Spatial Information Beijing China

ISBN: (纸本)9798350331417

With the outstanding performance of deep learning technology in semantic segmentation, object detection and other aspects, researchers have gradually tried to apply it to the field of three-dimensional scene semantic segmentation and extend it to LiDAR point cloud data, hoping to improve the automatic and real-time processing level of 3D scene semantic segmentation, and the combination of deep learning methods can effectively improve the system processing efficiency and improve the final SLAM construction *** semantic segmentation, which is one of the main directions of deep learning to improve the LiDAR SLAM *** present, the extraction of ground point cloud by traditional liDAR SLAM algorithm is still a simple geometric method, and the extraction accuracy of ground point cloud is *** solve the problem of low accuracy of ground point cloud extraction, this paper proposes a method of LiDAR SLAM point cloud segmentation extraction algorithm based on LEGO-LOAM algorithm and lightweight point cloud network RangeNet++,which implements the effective classification of LiDAR ground point clouds, and then improves the extraction quality of feature point clouds and the mapping accuracy of liDAR SLAM. © 2023 IEEE.

关键词： ground point cloud extraction LEGO-LOAM LiDAR SLAM RangeNet++

来源：评论

学校读者我要写书评

暂无评论

Dual Unsupervised Luminance-Space Pyramid-Constrained Network for image Deraining in Real-World Scenarios 2

Dual Unsupervised Luminance-Space Pyramid-Constrained Networ...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Ma, Liuzhong Wuhan University of Technology School of Computer Sciences and Artificial Intelligence Wuhan China

ISBN: (纸本)9798350331417

In the field of image processing, addressing the deleterious impact of rain streaks on images captured in real-world scenarios poses a formidable challenge. Previously developed deep learning-based deraining methods have demonstrated remarkable effectiveness when assessed using standardized benchmark datasets. Nonetheless, their applicability is often limited to pairwise training samples and domain-specific discrepancies. Moreover, these methods experience significant performance degradation when applied to genuine real-world rainy scenarios. Some researchers have observed the influence of luminance but have not proposed targeted solutions or have even disregarded it. In real rain-incorporated scenes, luminance exerts a noticeable influence on the visual characteristics of the images. The primary aim of this study is to alleviate the challenges related to dataset limitations and performance constraints inherent in real-world image deraining processes. To address this, we introduce a dual unsupervised Luminance-space Pyramid constrained Generative Adversarial Network (LP-GAN) designed to eliminate rain streak artifacts from real-world images. More specifically, the LP-GAN architecture comprises two interrelated loops: the first loop is responsible for mapping rainy input images to their corresponding rain-free counterparts, while the second loop operates in the reverse direction. In addition to the standard generative adversarial network (GAN) structure and the application of consistency constraints that align the initial rainy input with the predicted rainy image, we introduce an innovative luminance constraint. This constraint acts as a guiding mechanism to enhance the synthesis of rain-free images with improved naturalness and heightened contrast. Empirical evaluations conducted on diverse and challenging real-world datasets highlight the superior performance of our proposed model when compared to existing unsupervised deraining methodologies. © 2023 IEEE.

关键词： component Generative Adversarial Network Luminance constraint Unpaired image deraining

来源：评论

学校读者我要写书评

暂无评论

MiniDigPath: A New Standard for Pathology images Few-Shot Learning Classification 2

MiniDigPath: A New Standard for Pathology Images Few-Shot Le...

引用

2nd international conference on Cloud Computing, Big Data Application and Software Engineering, CBASE 2023

作者： Du, Yandong Liu, Xinlei Yue, Ling Feng, Lin Tao, Peng Jing, Qinlu Sichuan Normal University College of Computer Science Chengdu610101 China

ISBN: (纸本)9798350331448

Recently, few-shot learning(FSL) has received widespread attention. With the continuous development of machine learning and deep learning, the classification problem based on FSL has been deeply studied in fields such as computer vision and natural language processing. This greatly alleviates the problem of insufficient labeled data. So far, the publicly available datasets in FSL include Omniglot, miniimageNet, CUB-200, and CIFAR 100, etc. These datasets contain handwritten characters from different languages and natural images. No dataset in the medical field yet that can be applied to FSL despite massive of unlabeled data available. Therefore, the miniDigPath dataset is proposed by our work for FSL, which composed by 6 public pathology image datasets. It consists 67 different diseases and tissue types, and every type has 48-500 tissue image blocks. In total, there are 21165 histopathology images. Importantly, miniDigPath is available publicly for every researcher. It explores a new idea to solve pathological images annotation using FSL, which is the importance and originality of the dataset we proposed. Experimental evaluation on the classical FSL algorithm shows that the miniDigPath dataset can accomplish the task of FSL. Besides, FSL has good advantage for classification of digital pathology images. © 2023 IEEE.

关键词： Pathology

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181页 << < 31 32 33 34 35 36 37 38 39 40 > >>

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：