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

78 篇 会议
8 册 图书
3 篇 期刊文献

馆藏范围

89 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

57 篇 工学
- 50 篇 计算机科学与技术...
- 26 篇 软件工程
- 10 篇 生物工程
- 8 篇 信息与通信工程
- 7 篇 电气工程
- 7 篇 控制科学与工程
- 4 篇 仪器科学与技术
- 4 篇 生物医学工程（可授...
- 3 篇 光学工程
- 3 篇 电子科学与技术（可...
- 3 篇 石油与天然气工程
- 3 篇 交通运输工程
- 2 篇 建筑学
- 2 篇 土木工程
- 2 篇 安全科学与工程
- 1 篇 材料科学与工程（可...
- 1 篇 动力工程及工程热...
- 1 篇 水利工程
- 1 篇 化学工程与技术
22 篇 理学
- 12 篇 生物学
- 6 篇 数学
- 4 篇 物理学
- 3 篇 化学
- 1 篇 地质学
- 1 篇 统计学（可授理学、...
11 篇 管理学
- 7 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
- 2 篇 工商管理
3 篇 医学
- 3 篇 临床医学
1 篇 教育学
- 1 篇 教育学
1 篇 军事学

主题

18 篇 pattern recognit...
4 篇 neural networks
4 篇 artificial intel...
3 篇 support vector m...
3 篇 face recognition
3 篇 data mining and ...
3 篇 computer applica...
3 篇 feature extracti...
3 篇 machine learning
3 篇 information retr...
3 篇 computer vision
3 篇 shape
2 篇 iris recognition
2 篇 active vision
2 篇 decision support...
2 篇 pattern classifi...
2 篇 statistics
2 篇 image segmentati...
2 篇 local binary pat...
2 篇 computer communi...

机构

2 篇 department of co...
2 篇 national laborat...
2 篇 college of compu...
2 篇 department of el...
2 篇 democritus unive...
2 篇 department of co...
2 篇 department of el...
2 篇 university of pi...
1 篇 college of compu...
1 篇 laboratoire ura ...
1 篇 cybersecurity ma...
1 篇 vietnam national...
1 篇 trinity coll dub...
1 篇 katholieke univ ...
1 篇 icme university ...
1 篇 lee kong chian f...
1 篇 computer enginee...
1 篇 hasso plattner i...
1 篇 centre for patte...
1 篇 univ texas san a...

作者

2 篇 sandeep kumar
2 篇 ignacio rojas
2 篇 munish kumar
2 篇 phung dinh
2 篇 monali gulhane
2 篇 tran truyen
2 篇 venkatesh svetha
2 篇 nazri a. zamani
2 篇 gonzalo joya
2 篇 ilias maglogiann...
2 篇 lazaros iliadis
1 篇 pereira luis fel...
1 篇 jiang xiaoyi
1 篇 nitin
1 篇 turki turki
1 篇 wang lei
1 篇 alizadeh aylar z...
1 篇 akter nasrin
1 篇 meysam alavi
1 篇 pan shuai

语言

88 篇 英文
1 篇 中文

检索条件"任意字段=12th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2023"

共 89 条记录，以下是71-80 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：

VLNet: A Multi-task Network for Joint Vehicle and Lane Detection 12th

VLNet: A Multi-task Network for Joint Vehicle and Lane Det...

引用

12th international conference on Image and Graphics, ICIG 2023

作者： Feng, Aiqi Liu, Haodong Xu, Tianyang Zhang, Donglin Wu, Xiao-Jun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Jiangsu Wuxi214122 China

ISBN: (纸本)9783031463075

Visual perception is a crucial component of autonomous driving. Fully understanding the road environment is conducive to the safe driving of vehicles. However, most existing methods are usually unable to simultaneously accomplish multiple visual perception tasks, limiting the promotion and utilization. To this end, we propose VLNet: a novel and effective multi-task road environment perception network, which can perform vehicle and lane detection simultaneously. Specifically, VLNet consists of a shared feature extraction network and two detection branches for specific tasks. the vehicle detection branch uses a multi-scale method to detect vehicles, and the lane detection branch outputs instance-level segmentation map of lanes. Considering the correlation between vehicles and lanes, we leverage the semantic clues of the lane branch to assist vehicle detection. Compared with single-task networks, the proposed method reduces memory and computing costs effectively. Finally, experiments on the challenging Boxy vehicle detection dataset and the LLAMAS lane detection dataset demonstrate the efficacy of the developed model. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An empirical comparison of in-learning and post-learning optimization schemes for tuning the support vector machines in cost-sensitive applications

An empirical comparison of in-learning and post-learning opt...

引用

international conference on Image Analysis and Processing

作者： F. Tortorella DAEIMI Università degli Studi di Cassino Italy

Support vector machines (SVM) are currently one of the classification systems most used in pattern recognition and data mining because of their accuracy and generalization capability. However, when dealing with very complex classification tasks where different errors bring different penalties, one should take into account the overall classification cost produced by the classifier more than its accuracy. It is thus necessary to provide some methods for tuning the SVM on the costs of the particular application. Depending on the characteristics of the cost matrix, this can be done during or after the learning phase of the classifier. In this paper we introduce two optimization schemes based on the two possible approaches and compare their performance on various data sets and kernels. the first experimental results show that both the proposed schemes are suitable for tuning SVM in cost-sensitive applications.

关键词： Support vector machines Costs Support vector machine classification pattern recognition Data mining Cancer Error correction Kernel Risk management Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

DistilDoc: Knowledge Distillation for Visually-Rich Document applications 18th

DistilDoc: Knowledge Distillation for Visually-Rich Document...

引用

18th international conference on Document Analysis and recognition (ICDAR)

作者： Van Landeghem, Jordy Maity, Subhajit Banerjee, Ayan Blaschko, Matthew Moens, Marie-Francine Llados, Josep Biswas, Sanket Katholieke Univ Leuven Leuven Belgium Contractfit Brussels Belgium Univ Autonoma Barcelona Comp Vis Ctr Barcelona Spain

ISBN: (纸本)9783031705458;9783031705465

this work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and cumbersome models, the field has neglected to study efficiency via model compression. Here, we design a KD experimentation methodology(dagger) for more lean, performant models on document understanding (DU) tasks that are integral within larger task pipelines. We carefully selected KD strategies (response-based, feature-based) for distilling knowledge to and from backbones with different architectures (ResNet, ViT, DiT) and capacities (base-small-tiny). We study what affects the teacher-student knowledge gap and find that some methods (tuned vanilla KD, MSE, SimKD with an apt projector) can consistently outperform supervised student training. Furthermore, we design downstream task setups to evaluate covariate shift and the robustness of distilled DLA models on zero-shot layout-aware document visual question answering (DocVQA). DLA-KD experiments result in a large mAP knowledge gap, which unpredictably translates to downstream robustness, accentuating the need to further explore how to efficiently obtain more semantic document layout awareness.(dagger Code available at: https://***/Jordy-VL/DistilDoc_ICDAR24)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Outlier detection on mixed-type data: An energy-based approach 12th

Outlier detection on mixed-type data: An energy-based approa...

引用

12th international conference on Advanced Data Mining and applications, ADMA 2016

作者： Do, Kien Tran, Truyen Phung, Dinh Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

ISBN: (纸本)9783319495859

Outlier detection amounts to finding data points that differ significantly from the norm. Classic outlier detection methods are largely designed for single data type such as continuous or discrete. However, real world data is increasingly heterogeneous, where a data point can have both discrete and continuous attributes. Handling mixed-type data in a disciplined way remains a great challenge. In this paper, we propose a new unsupervised outlier detection method for mixed-type data based on Mixed-variate Restricted Boltzmann Machine (***). the *** is a principled probabilistic method that models data density. We propose to use free-energy derived from *** as outlier score to detect outliers as those data points lying in low density regions. the method is fast to learn and compute, is scalable to massive datasets. At the same time, the outlier score is identical to data negative log-density up-to an additive constant. We evaluate the proposed method on synthetic and real-world datasets and demonstrate that (a) a proper handling mixed-types is necessary in outlier detection, and (b) free-energy of *** is a powerful and efficient outlier scoring method, which is highly competitive against state-of-the-arts. © Springer international Publishing AG 2016.

关键词： Free energy

来源：评论

学校读者我要写书评

暂无评论

Structural, Syntactic, and Statistical pattern recognition 2008

引用

丛书名： Lecture Notes in Computer Science

2008年

作者： Niels da Vitoria Lobo Takis Kasparis Michael Georgiopoulos Fabio Roli James Kwok Georgios C. Anagnostopoulos Marco Loog

ISBN: (数字)9783540896890

ISBN: (纸本)9783540896883

this book constitutes the refereed proceedings of the 12th international Workshop on Structural and Syntactic pattern recognition, SSPR 2008 and the 7th international Workshop on Statistical Techniques in pattern recognition, SPR 2008, held jointly in Orlando, FL, USA, in December 2008 as a satellite event of the 19th international conference of pattern recognition, ICPR 2008. the 56 revised full papers and 42 revised poster papers presented together with the abstracts of 4 invited papers were carefully reviewed and selected from 175 submissions. the papers are organized in topical sections on graph-based methods, probabilistic and stochastic structural models for PR, image and video analysis, shape analysis, kernel methods, recognition and classification, applications, ensemble methods, feature selection, density estimation and clustering, computer vision and biometrics, pattern recognition and applications, pattern recognition, as well as feature selection and clustering.

关键词： pattern recognition systems Congresses.

来源：评论

学校读者我要写书评

暂无评论

A deterministic algorithm for edge-preserving computed imaging using Legendre transform

A deterministic algorithm for edge-preserving computed imagi...

引用

international conference on pattern recognition

作者： G. Aubert M. Barlaud L. Blanc-Feraud P. Charbonnier Laboratoire J.A. Dieudonnb URA du Cnrs University de Nice Nice France Laboratoire URA du Cnrs Gdr Traitement du Signal et Images University of Nice-Sophia Antipolis La Valbonne France Laboratoire URA du Cnrs Gdr Traitement du Signal Images University of Nice-Sophia Antipolis La Valbonne France

Many image processing problems are ill-posed and must be regularized. Usually, a roughness penalty is imposed on the solution. the difficulty is to avoid the smoothing of edges, which are very important attributes of the image. We first propose sufficient conditions for the design of such an edge-preserving regularization. Using the Legendre transform, it is then possible to introduce an auxiliary variable which role is twofold. Firstly, it marks the discontinuities and ensures their preservation from smoothing. Secondly, it makes the criterion half-quadratic. the optimization is then easier. We propose a deterministic algorithm, based on alternate minimizations over the image and the auxiliary variable. We apply this algorithm to the problem of SPECT reconstruction.

关键词： Smoothing methods Image reconstruction Image processing Sufficient conditions Minimization methods Computer applications Gaussian noise Image restoration Single photon emission computed tomography Vectors

来源：评论

学校读者我要写书评

暂无评论

Volumetric Image Reconstruction by 3D Hahn Moments

Volumetric Image Reconstruction by 3D Hahn Moments

引用

IEEE/ACS international conference on Computer Systems and applications

作者： Mostafa El Mallahi Abderrahim Mesbah Hassan Qjidaa Aissam Berrahou Khalid Zenkouar Hakim El Fadili CED-ST Center of Doctoral Studies in Sciences and Technologies LESSI laboratory Faculty of Sciences Dhar el Mehraz Sidi Mohamed Ben Abdellah University Fez Morocco Mohammadia School of Engineers Mohamed V University Rabat LSIA laboratory Faculty of Science Technique Sidi Mohamed Ben Abdellah University Fez ENSA National school of engineering Sidi Mohamed Ben Abdellah University Fez

ISBN: (纸本)9781509004799

three-Dimensional Hahn moments are performant tool in the domain of image processing applications and pattern classification. In this work, we propose a new method for computing the three-Dimensional Hahn moments. this method is based on matrix multiplication and symmetry property to decrease the complexity and computational time for volumetric image reconstruction. Experimental results showed that the proposed method is very efficient in terms of computation time, but also in terms of volumetric image reconstruction capability.

关键词： three-Dimensional Hahn moments Volumetric Image symmetry property matrix multiplication Matrix multiplication image reconstruction computational time Moment of force pattern recognition new methods

来源：评论

学校读者我要写书评

暂无评论

Facial family similarity recognition using Local Gabor Binary pattern Histogram Sequence

Facial family similarity recognition using Local Gabor Binar...

引用

international conference on Hybrid Intelligent Systems (HIS)

作者： Mohammad Mahdi Dehshibi Jamshid Shanbezadeh Meysam Alavi Department of Computer Engineering Science and Research Branch I.A.U. Tehran Iran Computer Engineering Department Kharazmi University Karaj Iran Computer Engineering Department University of Science and Culture Hamedan Iran

Facial image analysis is one of the areas that have been received considerable attention in recent decades. In addition to areas such as face recognition, gender classification, emotion recognition, and age estimation, there are new applications that have not been studied yet. Family similarity recognition is a new trend that has been studied in this paper for the first time. Local Gabor Binary pattern Histogram Sequence (LGBPHS) has led to many important advances in face recognition, including over looking generalizability and training issues. Given the current status of this study, two approaches were considered: (1) holistic approach and (2) component-based approach, which embodies the practical principles of theory. In order to model facial family manifold, LGBP is used both for the holistic view and components of the face. For recognition, histogram intersection is used to measure the similarity of different LGBPHSes and the nearest neighborhood is exploited for final clustering. In order to prove the efficiency of the proposed method three set of experiments are conducted in which both subjective and algorithmic issues are considered. It is observed in the course of experiments that the proposed method outperforms the subjective test up to 15%, and outperforms the observed state of the art face recognition methods up to 25.06%.

关键词： Decision support systems Hybrid intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Towards Better Ocular recognition for Secure Real-World applications

Towards Better Ocular Recognition for Secure Real-World Appl...

引用

IEEE international conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Reza M. Parizi Ali Dehghantanha Kim-Kwang Raymond Choo Kennesaw State University Kennesaw GA US The University of Sheffield Sheffield Sheffield GB University of Texas at San Antonio San Antonio TX US

In the last decade, biometric has become one of the most common uses for verification and authentication of someone's personal identity. Biometrics are defined as the measurement and analysis of unique physical or behavioral characteristics. Fingerprint is undoubtedly the most well-known biometric, but in the recent years ocular recognition has taken a huge jump forward. Ocular recognition (OR) is one of the most reliable personal identification methods in biometrics that can have flexible applications as opposed to the iris recognition. the basic breakdown of the eye is the iris, cornea, retina, pupil, sclera, and conjunctiva. the iris is where eye is actually colored; this is determined by the amount and type of pigment in one's iris. Iris recognition is an accurate form of ocular recognition. It works by using biometric systems to apply pattern recognition to a person's eye since no two people have the same patterns in their eye. Ocular recognition has been used as an identification method on both Apple and Android devices without much popularity. the reason for this is mainly related to the issues with the underlying algorithm used that affects the accuracy and security measures. Many different algorithms have been proposed and tested; some are more accurate than others. Our goal is to investigate different technologies currently used to help combine the best parts of both (Iris and Retina) in order to propose a better system for future implementation. With the proper design, ocular recognition could be a great tool for user authentication in emerging Internet of things (IoT) and mobile markets.

关键词： Iris recognition Retina Authentication Fingerprint recognition Hardware Software

来源：评论

学校读者我要写书评

暂无评论

Super resolution combination methods for CCTV forensic interpretation

Super resolution combination methods for CCTV forensic inter...

引用

international conference on Intelligent Systems Design and applications (ISDA)

作者： Nik Nur Aisyah Nik Ghazali Nazri A. Zamani Siti Norul Huda Sheikh Abdullah Jinjuli Jameson Faculty of Defence Science and Technology Universiti Pertahanan National Malaysia Kuala Lumpur Malaysia Digital Forensics Department CyberSecurity Malaysia Selangor Darul Ehsan Malaysia Pattern Recognition Research Group Center for Artificial Intelligence Technology Faculty of Technology and Information Science Universiti Kebangsaan Malaysia Selangor Darul Ehsan Malaysia

Generating a quality high resolution image has become an essential for variety purposes especially in forensic field. Compressed and at low resolution video frames of common security surveillance videos are found to be very low in clarity and degraded with many noises, distortions, blurs, bad illumination and video compression artifact. this could interfere during image interpretation and analysis process. this paper proposed a combination of super resolution methods for image processing. Using super resolution methods, high resolution image is obtained from a set of low resolution images, after it had undergone two main processes; image registration process based on Keren algorithm and image reconstruction process based on Projection onto Convex Set (POCS) on frequency domain. the validation process of output is done by calculating the Peak Signal to Noise Ratio (PSNR) value to show the comparison of image quality. the experimental results have shown that our proposed combinatorial method based super resolution and nearest neighbor methods outperformed other state-of-the-art methods.

关键词： Decision support systems Intelligent systems PSNR

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9页 << < 1 2 3 4 5 6 7 8 9 > >>

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：