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

251 篇 会议
30 册 图书
3 篇 期刊文献

馆藏范围

284 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

132 篇 工学
- 111 篇 计算机科学与技术...
- 62 篇 软件工程
- 27 篇 信息与通信工程
- 19 篇 电气工程
- 12 篇 生物工程
- 11 篇 生物医学工程（可授...
- 10 篇 控制科学与工程
- 9 篇 机械工程
- 9 篇 光学工程
- 9 篇 仪器科学与技术
- 7 篇 化学工程与技术
- 6 篇 交通运输工程
- 5 篇 材料科学与工程（可...
- 5 篇 石油与天然气工程
- 4 篇 电子科学与技术（可...
- 4 篇 建筑学
- 4 篇 安全科学与工程
- 4 篇 网络空间安全
55 篇 理学
- 27 篇 数学
- 14 篇 物理学
- 14 篇 生物学
- 9 篇 化学
- 9 篇 统计学（可授理学、...
33 篇 管理学
- 21 篇 图书情报与档案管...
- 15 篇 管理科学与工程(可...
- 6 篇 工商管理
9 篇 医学
- 6 篇 临床医学
- 4 篇 基础医学(可授医学...
- 4 篇 药学(可授医学、理...
5 篇 法学
3 篇 经济学
- 3 篇 应用经济学
3 篇 农学
2 篇 教育学
1 篇 艺术学

主题

56 篇 pattern recognit...
25 篇 artificial intel...
20 篇 computer vision
15 篇 computer imaging...
15 篇 shape
15 篇 layout
14 篇 image segmentati...
14 篇 optical computin...
12 篇 feature extracti...
11 篇 concurrent compu...
10 篇 data mining
10 篇 image motion ana...
10 篇 image analysis
9 篇 machine learning
9 篇 image processing...
8 篇 computer science
8 篇 cameras
8 篇 image processing
8 篇 user interfaces ...
8 篇 computer systems...

机构

12 篇 shenyang institu...
6 篇 tsinghua univers...
6 篇 shenyang institu...
5 篇 university of te...
5 篇 dalian universit...
5 篇 university of sy...
5 篇 school of comput...
5 篇 university of ch...
5 篇 institute of aut...
5 篇 shenzhen univers...
3 篇 pattern recognit...
3 篇 center for visua...
2 篇 department of co...
2 篇 college of compu...
2 篇 department of in...
2 篇 college of compu...
2 篇 faculty of engin...
2 篇 ramon llull univ...
2 篇 national researc...
2 篇 tecnológico de m...

作者

5 篇 hui huang
5 篇 jing dong
5 篇 jiwen lu
5 篇 risheng liu
5 篇 wanli ouyang
5 篇 min xu
5 篇 huchuan lu
3 篇 c. clausner
3 篇 shiguang shan
3 篇 r. chellappa
3 篇 s. pletschacher
3 篇 a. antonacopoulo...
2 篇 giuseppe nicosia
2 篇 g.w. cook
2 篇 v. a. narayana
2 篇 umapada pal
2 篇 sohn mye
2 篇 p. n. suganthan
2 篇 ryszard tadeusie...
2 篇 david hawkes

语言

281 篇 英文
2 篇 其他
1 篇 中文

检索条件"任意字段=12th International Conference on Computing and Pattern Recognition, ICCPR 2023"

共 284 条记录，以下是241-250 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：

Adaptive Fusion Attention Network for Facial Expression recognition 23

Adaptive Fusion Attention Network for Facial Expression Reco...

引用

Proceedings of the 2023 12th international conference on computing and pattern recognition

作者： Guodong Li Cheng Peng Kun Zou Bowen Zhang School of Computer Science and Engineering(School of Cybersecurity) University of Electronic Science and Technology of China China School of Computing University of Electronic Science and Technology of China Zhongshan Institute China College of Big Data and Internet Shenzhen Technology University China

ISBN: (纸本)9798400707988

In this paper, we propose a novel facial expression recognition network, called Adaptive Fusion Attention Network (AFAN). Facial expression recognition is different from traditional image classification tasks. there are potentially similar features between different categories, and the differences between them may be subtle and difficult to distinguish. To solve this problem, we propose AFAN, which not only can get multi-dimensional features, but also can generate an attention map with stronger representation ability. the comparative experiments on AffectNet-7 dataset verify the excellent performance of the proposed method on facial expression recognition tasks.

关键词： Adaptive convolutional blocks Facial expression recognition Fine-grained classification Multi-head attention networks

来源：评论

学校读者我要写书评

暂无评论

Modified distance measure between fuzzy sets

Modified distance measure between fuzzy sets

引用

international conference on Intelligent System and Knowledge Engineering, ISKE

作者： Ruirui Zhao Minxia Luo Department of information and Computing Science China Jiliang University Hangzhou PR China

Distance measure of fuzzy sets is an important tool to indicate the difference between fuzzy sets. Hatzimichailidis et al proposed a distance measure between fuzzy sets based on D - implication and a matrix norm. Although this distance measure considers the relationship between the elements, the measure is not satisfied the definition of distance measure between fuzzy sets. In this paper, we modify the distance measure between fuzzy sets. the modified distance measure is not only to meet the definition of a distance measure, but also to improve the efficiency of Hatzimichailidis's measure. A series of examples are used to demonstrate this phenomenon.

关键词： Fuzzy sets pattern recognition Measurement Tools Fuzzy set theory Entropy Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Deferring range/domain comparisons in fractal image compression

Deferring range/domain comparisons in fractal image compress...

引用

international conference on Image Analysis and Processing

作者： D. Riccio M. Nappi Dipartimento di Matematica e Informatica Università di Salerno Baronissi Italy

Fractals are a promising framework for several applications other than image coding and transmission, such as database indexing, texture mapping and pattern recognition problems such as writer authentication. However, fractal based algorithms are strongly asymmetric because, in spite of the linearity of the decoding phase, the coding process is very time consuming. Many different solutions have been proposed for this problem, but there is not yet a standard for fractal coding. In this paper we analyze the problem of complexity reduction of the image coding phase and providing a new classification technique based on an approximation error measure. We show formally that postponing range/domain comparisons with respect to a preset block, it is possible to reduce the amount of operations needed to encode each range and therefore whole the image. the proposed strategy allows a drastic complexity reduction of the coding phase. the proposed method has been compared with another fractal coding method, showing in which circumstances the proposed algorithm performs better in terms of both bit rate and/or computing time.

关键词： Fractals Image coding Image databases Indexing pattern recognition Authentication Linearity Decoding Image analysis Approximation error

来源：评论

学校读者我要写书评

暂无评论

Hybrid spintronic/straintronics: A super energy efficient computing scheme based on interacting multiferroic nanomagnets

Hybrid spintronic/straintronics: A super energy efficient co...

引用

IEEE conference on Nanotechnology

作者： Jayasimha Atulasimha Supriyo Bandyopadhyay Department of Mechanical and Nuclear Engineering Virginia Commonwealth University Richmond VA USA Department of Electrical and Computer Engineering Virginia Commonwealth University Richmond VA USA

We have theoretically shown that multiferroic nanomagnets (consisting of a piezoelectric and a magnetostrictive layer) could be used to perform computing while dissipating ~ few 100 kT/bit at clock rates of ~1GHz [1,2,3]. they can act as memory elements [2], binary logic gates [3, 4] and associative memory for four state logic [5, 6]. the latter enables signal processing functions such as ultrafast image reconstruction and pattern recognition [7]. this talk will provide an overview of our research in modeling stress induced nanoscale magnetization dynamics, its application to ultra low energy hybrid spintronic/straintronics memory and information processing, and discuss preliminary experimental work in fabrication and experimental demonstration of these devices.

关键词： Magnetic domains Magnetostriction Magnetic resonance imaging Magnetostrictive devices Nanoscale devices Switches

来源：评论

学校读者我要写书评

暂无评论

Research on Improved Faster R-CNN in Stacked Artifact recognition

Research on Improved Faster R-CNN in Stacked Artifact Recogn...

引用

Information and Communication Technology (ICTech), international conference of

作者： Weiguang Han Xuesong Han University of Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China

In order to improve the sorting efficiency of workpieces, improve the sorting quality, reduce the labor intensity of workers and improve the working environment, and at the same time meet the needs of small batch, multi-variety and mixed production, this paper studies the improvement of Faster R-CNN for the field of robotic sorting. Application in stacked workpiece recognition. this paper improves the Faster R-CNN and proposes the Bin-Soft-NMS algorithm based on the Soft-NMS algorithm. the dynamic threshold is used to improve the low recall rate of the model and the low score of the adjacent stacked workpiece bounding box caused by the inaccurate threshold. the problem of inhibition. A stacked workpiece dataset was made by using four kinds of workpieces, and the model was trained on the dataset to complete the experiment. the experimental results show that the average detection accuracy of the improved model in the stacked workpiece scene is 86.26%, and the improvement in mild, moderate and severe scenarios is improved respectively. increased by 1.0%, 3.2% and 4.825%, with an average increase of 3%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Power Voice Based on WaveNet+LSTM Improvement

Research on Power Voice Based on WaveNet+LSTM Improvement

引用

Information and Communication Technology (ICTech), international conference of

作者： HanJun Wang MingYun Zhu Qun Wang Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China

With the rapid development of speech recognition [1] in recent years, the WaveNet model has also been discovered by more people and applied to speech recognition. In the open source LJSpeech-1.0, AISHELL and thch-30 and other general speech datasets, the model has achieved relatively good recognition results, but in the face of a large number of power voice data, because of the uniqueness and complexity of industry speech, the model is generally performed, so in this paper we have made some improvements to the model, aiming to improve the recognition of power-related speech data. First of all, in view of the shortcomings of the WaveNet network model in power speech recognition, we have improved and optimized it. the output gate structure of the LSTM network model is used to increase the nonlinearity of the model, so as to optimize the structural composition of the new model. We then introduced the core structure of the Reduced Convolution in WaveNet. According to the length of speech in the electric speech dataset, the receptive field of this structure is adjusted, and the sensory field is theoretically analyzed in order to better analyze the speech data. Finally, we experimentally verify the feasibility of applying the improved WaveNet model on the thch-30 dataset and the power-related dataset, and evaluate the trained model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measurement of Imaging Indexes of Distal Radius based on deep Learning Key Point Detection 23

Measurement of Imaging Indexes of Distal Radius based on dee...

引用

9th international conference on computing and Artificial Intelligence, ICCAI 2023

作者： Jiachao, Niu Xin, Zhang Xufeng, Ling Yang, Jie Yin, Yong Shanghai Normal University Tianhua College AI School No. 1661 North Sheng Xin Road China Department of Orthopedics Jiading District Central Hospital Affiliated Shanghai University of Medicine &Health Sciences No.1 Chengbei Road China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 800 Dongchuan Road 200240 China

ISBN: (纸本)9781450399029

the measurement of imaging indexes of distal radius is the basic work of diagnosis and recovery evaluation. Due to the problems of large morphological differences and insufficient clarity in radial images, the accurate measurement of indexes relies heavily on the clinical experience of doctors, with defects such as low accuracy and poor consistency. In order to solve the above problems, this paper proposes an intelligent technology to achieve accurate measurement of imaging indicators of the distal radius. Firstly, 12 key points needed for distal imaging indexes were determined: radius left vertex, radius right vertex, radius left neck point, radius right neck point, radius left lower point, radius right lower point, ulna left vertex, ulna right vertex, ulna left neck point, right neck point, ulna left lower point, ulna right lower point. then, the deep convolutional neural network was used to estimate the geometric transformation features and regress the thermal map of the feature points, so as to achieve accurate positioning of the 12 feature points. Finally, each imaging index was calculated accurately by the preset computational method. the experimental results show that the proposed measurement method has advantages of high accuracy, good consistency and fast speed. the test accuracy is higher than the manual measurement results of inexperienced doctors, and the network model has good robustness and generalization ability. this method has practical value and can be applied in the field of medical imaging to help doctors improve the efficiency of diagnosis. © 2023 Copyright held by the owner/author(s).

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Supervised Neighborhood Topology Learning for Human Action recognition

Supervised Neighborhood Topology Learning for Human Action R...

引用

international conference on Computer Vision Workshops (ICCV Workshops)

作者： Jinhua Ma Pong C Yuen Weiwen Zou Jian-Huang Lai Sun Yat-Sen University Guangzhou China Hong Kong Baptist University Hong Kong China

Supervised manifold learning has been successfully applied to human action recognition. With the class label information, the recognition performance can be improved. However, the learned manifold may not be able to well preserve the local structure which reflects temporal information of an action. To overcome this limitation, this paper proposes a new supervised manifold learning algorithm namely supervised neighborhood topology learning (SNTL) for human action recognition. SNTL is based on the framework of locality preserving projection (LPP). Different from LPP, SNTL constructs the adjacency graph with a topology defined in a supervised manner, which not only separates data points from different actions but also preserves the local structure of data points from the same action. With the advantage of locality preserving property in the framework of LPP, SNTL provides good discriminant ability and preserves temporal information of each action contained in local structure. Weizmann human action database is used for evaluation. Experimental results show that the method achieves 95.56% recognition accuracy.

关键词： Topology Humans Computer vision Data mining Optical computing Linear discriminant analysis pattern recognition conferences Sun Shape

来源：评论

学校读者我要写书评

暂无评论

Parallel Problem Solving from Nature - PPSN XII 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Carlos A. Coello Coello Vincenzo Cutello Giuseppe Nicosia Mario Pavone Kalyanmoy Deb Stephanie Forrest

ISBN: (数字)9783642329647

ISBN: (纸本)9783642329630

the two volume set LNCS 7491 and 7492 constitutes the refereed proceedings of the 12th international conference on Parallel Problem Solving from Nature, PPSN 2012, held in Taormina, Sicily, Italy, in September 2012. the total of 105 revised full papers were carefully reviewed and selected from 226 submissions. the meeting began with 6 workshops which offered an ideal opportunity to explore specific topics in evolutionary computation, bio-inspired computing and metaheuristics. PPSN 2012 also included 8 tutorials. the papers are organized in topical sections on evolutionary computation; machine learning, classifier systems, image processing; experimental analysis, encoding, EDA, GP; multiobjective optimization; swarm intelligence, collective behavior, coevolution and robotics; memetic algorithms, hybridized techniques, meta and hyperheuristics; and applications.

关键词： Artificial Intelligence Computational Biology/Bioinformatics Computation by Abstract Devices pattern recognition Algorithm Analysis and Problem Complexity Discrete Mathematics in Computer Science

来源：评论

学校读者我要写书评

暂无评论

Parallel Problem Solving from Nature - PPSN XII 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Carlos A. Coello Coello Vincenzo Cutello Giuseppe Nicosia Mario Pavone Kalyanmoy Deb Stephanie Forrest

ISBN: (数字)9783642329371

ISBN: (纸本)9783642329364

the two volume set LNCS 7491 and 7492 constitutes the refereed proceedings of the 12th international conference on Parallel Problem Solving from Nature, PPSN 2012, held in Taormina, Sicily, Italy, in September 2012. the total of 105 revised full papers were carefully reviewed and selected from 226 submissions. the meeting began with 5 workshops which offered an ideal opportunity to explore specific topics in evolutionary computation, bio-inspired computing and metaheuristics. PPSN 2012 also included 8 tutorials. the papers are organized in topical sections on evolutionary computation; machine learning, classifier systems, image processing; experimental analysis, encoding, EDA, GP; multiobjective optimization; swarm intelligence, collective behavior, coevolution and robotics; memetic algorithms, hybridized techniques, meta and hyperheuristics; and applications.

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29页 << < 20 21 22 23 24 25 26 27 28 29 > >>

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：