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

283 篇 会议
41 册 图书
3 篇 期刊文献

馆藏范围

327 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

171 篇 工学
- 152 篇 计算机科学与技术...
- 93 篇 软件工程
- 47 篇 光学工程
- 35 篇 信息与通信工程
- 28 篇 生物工程
- 22 篇 电气工程
- 16 篇 控制科学与工程
- 9 篇 电子科学与技术（可...
- 8 篇 化学工程与技术
- 8 篇 生物医学工程（可授...
- 6 篇 网络空间安全
- 5 篇 机械工程
- 5 篇 安全科学与工程
- 3 篇 仪器科学与技术
- 3 篇 材料科学与工程（可...
- 3 篇 建筑学
- 3 篇 农业工程
78 篇 理学
- 48 篇 物理学
- 30 篇 生物学
- 25 篇 数学
- 11 篇 统计学（可授理学、...
- 8 篇 化学
21 篇 医学
- 16 篇 临床医学
- 4 篇 公共卫生与预防医...
- 3 篇 基础医学(可授医学...
- 3 篇 特种医学
18 篇 管理学
- 10 篇 管理科学与工程(可...
- 9 篇 图书情报与档案管...
- 5 篇 工商管理
4 篇 农学
- 4 篇 作物学
2 篇 法学
2 篇 教育学

主题

37 篇 computer vision
25 篇 image processing...
21 篇 artificial intel...
20 篇 pattern recognit...
20 篇 computer imaging...
17 篇 machine learning
14 篇 computer applica...
13 篇 computer systems...
12 篇 signal, image an...
11 篇 deep learning
8 篇 image processing
6 篇 computers and ed...
5 篇 vision transform...
5 篇 low-level vision
4 篇 image enhancemen...
4 篇 object detection
4 篇 cell microscopy
4 篇 image segmentati...
4 篇 graphics process...
4 篇 stereo image pro...

机构

17 篇 microsoft resear...
17 篇 microsoft res as...
12 篇 tsinghua univers...
7 篇 university of sc...
7 篇 univ sci & techn...
6 篇 national key lab...
6 篇 shanghai collabo...
6 篇 shanghai key lab...
5 篇 university of te...
5 篇 dalian universit...
5 篇 university of sy...
5 篇 institute of aut...
5 篇 shenzhen univers...
4 篇 key laboratory o...
4 篇 national enginee...
4 篇 university of ud...
4 篇 tsinghua univ pe...
4 篇 microsoft cloud ...
4 篇 university of yo...
4 篇 vision and image...

作者

8 篇 han hu
7 篇 hu han
6 篇 zuxuan wu
6 篇 min xu
5 篇 hui huang
5 篇 jing dong
5 篇 yu-gang jiang
5 篇 jiwen lu
5 篇 risheng liu
5 篇 wanli ouyang
5 篇 huchuan lu
4 篇 gian luca forest...
4 篇 qi dai
4 篇 zhiguo cao
4 篇 dongdong chen
4 篇 edwin hancock
4 篇 boxin shi
4 篇 jean-jacques rou...
4 篇 zheng zhang
4 篇 andrea fusiello

语言

322 篇 英文
5 篇 其他
3 篇 中文

检索条件"任意字段=2023 Asia Conference on Computer Vision, Image Processing and Pattern Recognition, CVIPPR 2023"

共 327 条记录，以下是121-130 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：

26th Iberoamerican Congress on pattern recognition, CIARP 2023

26th Iberoamerican Congress on Pattern Recognition, CIARP 20...

引用

26th Iberoamerican Congress on pattern recognition, CIARP 2023

ISBN: (纸本)9783031492488

The proceedings contain 61 papers. The special focus in this conference is on pattern recognition. The topics include: Time Distributed Multiview Representation for Speech Emotion recognition;detection of Covid-19 in Chest X-Ray images Using Percolation Features and Hermite Polynomial Classification;abandoned Object Detection Using Persistent Homology;interactive Segmentation with Incremental Watershed Cuts;supervised Learning of Hierarchical image Segmentation;unveiling the Influence of image Super-Resolution on Aerial Scene Classification;Weeds Classification with Deep Learning: An Investigation Using CNN, vision Transformers, Pyramid vision Transformers, and Ensemble Strategy;leveraging Question Answering for Domain-Agnostic Information Extraction;towards a Robust Solution for the Supermarket Shelf Audit Problem: Obsolete Price Tags in Shelves;graph Embedding of Almost Constant Large Graphs;a Self-Organizing Map Clustering Approach to Support Territorial Zoning;spatial-Temporal Graph Transformer for Surgical Skill Assessment in Simulation Sessions;deep Learning in the Identification of Psoriatic Skin Lesions;wildFruiP: Estimating Fruit Physicochemical Parameters from images Captured in the Wild;depression Detection Using Deep Learning and Natural Language processing Techniques: A Comparative Study;impact of Synthetic images on Morphing Attack Detection Using a Siamese Network;face image Quality Estimation on Presentation Attack Detection;knowledge Distillation of vision Transformers and Convolutional Networks to Predict Inflammatory Bowel Disease;analysis and Impact of Training Set Size in Cross-Subject Human Activity recognition;efficient Brazilian Sign Language recognition: A Study on Mobile Devices;feature Importance for Clustering;presumably Correct Undersampling;leveraging Longitudinal Data for Cardiomegaly and Change Detection in Chest Radiography;self-supervised Monocular Depth Estimation on Unseen Synthetic Cameras;novelty Detection in Human-Machine Inter

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object detection algorithm based on mixed dilated convolution pyramid 3

Object detection algorithm based on mixed dilated convolutio...

引用

3rd International conference on computer vision and pattern Analysis, ICCPA 2023

作者： Yu, Tingjian Yuan, Zemin Huang, Tao Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510667563

To address the problem that FPN in the one-stage object detection algorithm loses a large amount of semantic information after upsampling and downsampling fusion, leading to difficulties in detecting small objects in dense scenes. This paper proposes a new FPN structure, Residual dilated FPN(RdFPN), compared to the traditional FPN, which uses multiple Dilated Block instead of the standard convolution in the FPN horizontal structure to mix the receptive fields of different layers in the feature map and expand the object size range of the feature map, while improving the network's ability to extract features at different scales. Experimental results show that RdFPN improves the mAP of the one-stage object detection algorithms RetinaNet, FCOS, and GFL by 0.9%, 0.7%, and 0.8% on the MS COCO dataset, enough to improve the overall performance of the detector. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

EGF: An Improved Edge Detection Model for Low-Resolution images 2

EGF: An Improved Edge Detection Model for Low-Resolution Ima...

引用

2nd IEEE International conference on Futuristic Technologies, INCOFT 2023

作者： Deepak Raj, D.M. Shanmuganathan, Harinee Geetha, A. Keerthika, V. Alliance University Department of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350308846

Edge detection can benefit many different industries and domains, including computer vision, machine learning, image analysis, remote sensing, thermal imaging, pattern recognition, and medical imaging. The technique of determining the borders between several objects or regions in an image is known as edge detection. The edges of an object in a picture serve as the object's limits and can reveal crucial details about the object's size, shape, and position. Since low-resolution images have low pixel densities or pixel values, which muddy the images, detecting edges in them is demanding work. This paper proposes a novel edge-detection approach called EGF (Extended Gaussian Filter) for low-resolution images. EGF utilizes the basic concept of Gaussian filter to find the edges of images. The objective function of EGF is developed to reduce the noise and pixel differentiation in images. The outcomes show that the suggested strategy outperforms the conventional edge detection technique. © 2023 IEEE.

关键词： edge detection gaussian filter image processing machine learning pre-processing

来源：评论

学校读者我要写书评

暂无评论

Diversified and Multi-Class Controllable Industrial Defect Synthesis for Data Augmentation and Transfer

Diversified and Multi-Class Controllable Industrial Defect S...

引用

2023 IEEE/CVF conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Wei, Jing Shen, Fei Lv, Chengkan Zhang, Zhengtao Zhang, Feng Yang, Huabin Institute of Automation Chinese Academy of Sciences China The School of Artificial Intelligence University of Chinese Academy of Sciences China Casi Vision Technology CO. China

ISBN: (纸本)9798350302493

Data augmentation is crucial to solve few-sample issues in industrial inspection based on deep learning. However, current industrial data augmentation methods have not yet demonstrated on-par ability in the synthesis of complex defects with pixel-level annotations. This paper proposes a new defect synthesis framework to fill the gap. Firstly, DCDGANc (Diversified and multi-class Controllable Defect Generation Adversarial Networks based on constant source images) is proposed to employ class labels to construct source inputs to control the category and random codes to generate diversified styles of defects. DCDGANc can generate defect content images with pure backgrounds, which avoids the influence of non-defect information and makes it easy to obtain binary masks by segmentation. Secondly, the Poisson blending is improved to avoid content loss when blending generated defect contents to the normal backgrounds. Finally, the complete defect samples and accurate pixel-level annotations are obtained by fine image processing. Experiments are conducted to verify the effectiveness of our work in wood, fabric, metal, and marble. The results show that our methods yield significant improvement in the segmentation performance of industrial products. Moreover, our work enables zero-shot inspection by facilitating defect transfer between datasets with different backgrounds but similar defects, which can greatly reduce the cost of data collection in industrial inspection. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-computer Interaction: Hand Detection for Air Writing Utilizing NumPy and OpenCV 3

Enhancing Human-Computer Interaction: Hand Detection for Air...

引用

3rd International conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Shukla, Pranjal Das, Prasenjit Chandigarh University Department of Cse Punjab Mohali India

ISBN: (纸本)9798350342338

In recent years, there has been a remarkable increase in interest and challenges in image processing and pattern recognition, specifically in the context of air writing. This exciting research area has significant potential to advance automation processes and improve human-machine interfaces in various applications. The emergence of faster computers, affordable high-performance video cameras, and the need for automated analysis of videos has led to an increase in the popularity of object tracking, a critical task in computer vision. The process of video analysis typically encompasses object detection, tracking, and behavior analysis. Object tracking involves four main aspects choosing the suitable object representation, selecting features for tracking, detecting the object, and tracking the object. Object tracking algorithms find applications in different domains, including vehicle navigation, video indexing, and surveillance that are automated. The objective of the paper is to create a software application for smart wearable devices that utilizes computer vision to track finger gestures in the air, functioning as a motion-to-text converter for air-writing. The technology will facilitate communication for people by enabling them to generate text for multiple purposes, like sending emails and messages, through intermittent gestures. This is a productive means of communication that curbs the usage of laptops and mobiles, making it particularly beneficial for individuals who are deaf. © 2023 IEEE.

关键词： Air Writing computer vision Digital sketching Gesture recognition Hand Detection Hand Tracking Interactive whiteboard

来源：评论

学校读者我要写书评

暂无评论

Spatial-Angular Multi-Scale Mechanism for Light Field Spatial Super-Resolution

Spatial-Angular Multi-Scale Mechanism for Light Field Spatia...

引用

2023 IEEE/CVF conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Gao, Chen Lin, Youfang Chang, Song Zhang, Shuo School of Computer and Information Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining China

ISBN: (纸本)9798350302493

Light Field (LF) cameras are promising due to their ability to capture both spatial and angular information of scenes. However, the trade-off between spatial and angular resolution significantly limits the real-world applications. In this paper, we propose a spatial-angular multi-scale decoupling network to reconstruct high-resolution LF images. Considering the epipolar geometry, we propose a spatial-angular multi-scale processing approach to explore the correspondence of sub-pixel information with different disparity ranges between sub-aperture images in LFs. We extract sub-pixel information from various dimensions and fuse it to generate global high-frequency details. Finally, we combine upsampled low-frequency and high-frequency details to generate high resolution results. To further filter the correct interpolation information, we use the shear operation to change the disparity range of the LF images and fine-tune the results. Experimental results on synthetic and real-world datasets demonstrate that our method outperforms other state-of-the-art methods in visual and numerical evaluations, especially on datasets with small disparity ranges. Furthermore, our approach fully considers the epipolar geometry of the LF image, enabling us to recover information that better maintains the imaging consistency of the LF. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Dense Pedestrian Detection Based on Multiple Link Feature Pyramid Networks 3

Dense Pedestrian Detection Based on Multiple Link Feature Py...

引用

3rd International conference on computer vision and pattern Analysis, ICCPA 2023

作者： Huang, Tao Yang, Siyu Yu, Tingjian Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510667563

Pedestrian detection is widely employed in a variety of industries, including security, autonomous driving, and pedestrian flow statistics. However, because most pedestrians in real-world scenes are densely distributed with occlusion issues, scale variation and pose variability, majority pedestrian detection algorithms have low detection accuracy and a high miss detection rate. In this paper, we propose a new FPN neck module, Multiple Link Feature Pyramid Networks (MLFPN) for dense pedestrian detection, which innovative information transfer pathways and incorporation of Poly-Scale Convolution (PSconv) capable of long-range interaction into feature extraction tasks to reduce feature information loss and enhanced representation of effective pedestrian features, achieving 0.6MR-2, 0.35AP, and 0.21JI improvements on CrowdHuman dataset, improving detection accuracy and reducing missed detection rates. © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Pseudo-label based and transformation-consistent self-ensembling model for underwater life images

Pseudo-label based and transformation-consistent self-ensemb...

引用

2023 International conference on image, Signal processing, and pattern recognition, ISPP 2023

作者： Huang, Shan Luo, Xiaonan Lu, Jiahao Huang, Chao Xu, Chengpei Yuan, Tianran School of Computer Science and Information Security Guilin University of Electronics Technology No. 1 Jinji Road Guilin541004 China

ISBN: (纸本)9781510666351

With the continuous development of underwater vision technology, high-precision object segmentation has received more attention from scholars. Due to the complexity of the underwater environment, the segmentation of underwater objects has become a new challenge. In order to alleviate such problems, this paper proposes a semi-supervised segmentation model based on pseudo-labels and transformation-consistent(PSTM). Due to the complexity of underwater images, PSTM preprocesses underwater biological images through an image enhancement module. A semi-supervised segmentation network with pseudo-labels and transformation-consistent is then used to obtain a more robust segmentation result. The method in this paper achieves better performance on the public underwater biological dataset DUT-USEG. © 2023 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Rethinking Implicit Neural Representations For vision Learners 48

Rethinking Implicit Neural Representations For Vision Learne...

引用

48th IEEE International conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Song, Yiran Zhou, Qianyu Ma, Lizhuang Shanghai Jiao Tong University China

ISBN: (纸本)9781728163277

Implicit Neural Representations (INRs) are powerful to parameterize continous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image generation. The questions on how to explore INRs to high-level tasks and deep networks are still under-explored. Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks;2) lack of representation capabilities to deep networks. Motivated by above facts, we reformulate the definitions of INRs from a novel perspective, and propose an innovative Implicit Neural Representation Network (INRN), which is the first study of INRs to tackle both low-level and high-level tasks. Specifically, we present three key designs for basic blocks in INRN along with two different stacking ways and corresponding loss functions. Extensive experiments with analysis on both low-level task (image fitting) and high-level vision tasks (image classification, object detection, instance segmentation) demonstrate the effectiveness of the proposed method. © 2023 IEEE.

关键词： computer vision Implicit Neural Representations pattern recognition Representation Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Women Hairstyle Classification Through Inception Resnet-101

Deep Learning-Based Women Hairstyle Classification Through I...

引用

2023 International conference on Energy, Materials and Communication Engineering, ICEMCE 2023

作者： Farook, Faazelah Mohamed Mohamed Mansoor Roomi, S. Sasithra Devi, A. Jayanthi Rajee, R.B. Thiagarajar College of Engineering Department of Electronics and Communication Engineering Tamil-Nadu Madurai India

ISBN: (纸本)9798350393378

Artificial intelligence and computer science's computer vision field is revolutionizing a number of industries, including healthcare, automotive, agriculture, security, and entertainment, by enabling robots to assess visual input. For tasks like object detection, classification, and 3D reconstruction, it makes use of methods from the fields of image processing, machine learning, deep learning, and pattern recognition. One promising application of this technology is the classification of hairstyles using pre-trained networks, which can be used for the detection of criminals who may be using certain hairstyles as a form of disguise or it can be used to identify a person through CCTV surveillance for further investigations. In this paper, a study using the performance of Inception Resnet 101, a popular learning architecture has been used for the classification of several common hairstyles. These hairstyles include 'Bald', 'Braids', 'Free Hair', 'Pony Tail' and 'Short Hair'. Validation accuracy of about 89.7% and testing accuracy of 95.6% has been achieved. This approach demonstrates that the model can attain high accuracy even in the face of difficult real-world circumstances, such as changes in illumination, angles, and distances. A few of the industries that need to take this into account are marketing, trend analysis, and customized haircuts. Approaches utilizing computer vision and artificial intelligence facilitate innovation, enhance decision-making, and enhance the user experience. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共33页 << < 9 10 11 12 13 14 15 16 17 18 > >>

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：