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

103 篇 会议
7 册 图书
3 篇 期刊文献

馆藏范围

113 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

82 篇 工学
- 76 篇 计算机科学与技术...
- 54 篇 软件工程
- 23 篇 信息与通信工程
- 12 篇 生物工程
- 11 篇 电气工程
- 8 篇 生物医学工程（可授...
- 6 篇 光学工程
- 5 篇 机械工程
- 4 篇 控制科学与工程
- 2 篇 电子科学与技术（可...
- 2 篇 农业工程
51 篇 理学
- 35 篇 数学
- 13 篇 生物学
- 12 篇 物理学
- 3 篇 系统科学
- 3 篇 统计学（可授理学、...
- 1 篇 化学
- 1 篇 大气科学
- 1 篇 地球物理学
13 篇 管理学
- 9 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
- 2 篇 工商管理
5 篇 医学
- 5 篇 基础医学(可授医学...
- 5 篇 临床医学
- 3 篇 药学(可授医学、理...
- 2 篇 公共卫生与预防医...
3 篇 教育学
- 3 篇 教育学
2 篇 农学
- 2 篇 作物学
1 篇 经济学
- 1 篇 理论经济学
1 篇 法学
- 1 篇 社会学

主题

8 篇 artificial intel...
5 篇 natural language...
4 篇 computational in...
3 篇 computer science
3 篇 physics computin...
3 篇 convolution
3 篇 computational mo...
3 篇 soft computing
3 篇 cloud computing
2 篇 knowledge based ...
2 篇 quantum computin...
2 篇 concurrent compu...
2 篇 task analysis
2 篇 three-dimensiona...
2 篇 algorithms
2 篇 neural networks
2 篇 iterative method...
2 篇 dna computing
2 篇 diagnosis
2 篇 sequences

机构

4 篇 department of ma...
4 篇 department of ma...
4 篇 research center ...
3 篇 university of ca...
2 篇 computer science...
2 篇 graduate school ...
2 篇 department of co...
2 篇 institute of sof...
2 篇 school of mathem...
2 篇 school of comput...
2 篇 academic center ...
2 篇 bio-computing re...
2 篇 school of comput...
2 篇 school of comput...
2 篇 dr. b. r. ambedk...
2 篇 harbin institute...
1 篇 school of electr...
1 篇 department of co...
1 篇 informatics engi...
1 篇 department of co...

作者

5 篇 liu ting
4 篇 jagdish chand ba...
3 篇 tran dat
3 篇 che wanxiang
3 篇 wagner michael
3 篇 atulya k. nagar
3 篇 kusum deep
2 篇 aruna tiwari
2 篇 kapil ahuja
2 篇 narayan kumar k.
2 篇 kondrak grzegorz
2 篇 sonogashira moto...
2 篇 iiyama masaaki
2 篇 hwang chong-sun
2 篇 z. ibrahim
2 篇 o. ono
2 篇 y. tsuboi
2 篇 anupam yadav
1 篇 seuret mathias
1 篇 hsu shun-fa

语言

112 篇 英文
1 篇 其他

检索条件"任意字段=5th Asian Computing Science Conference on Advances in Computing Science, ASIAN 1999"

共 113 条记录，以下是21-30 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：

Octahedron-shaped Convolution for Refining Aorta Semantic Segmentation

Octahedron-shaped Convolution for Refining Aorta Semantic Se...

引用

Artificial Intelligence Technology (ACAIT), asian conference on

作者： Xi Xiang Gongning Luo Pengfei Zhao Wei Wang Kuanquan Wang Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9781665426312

Refining 3D aorta segmentation is essential for clinical aorta analysis. the small tubular diameter of the aorta branches and the discontinuity of neighboring information make it difficult to get a continuous semantic segmentation map. In this paper, we propose a novel octahedron-shaped convolution (OSC) based on VNet and signed distance map (SDM). OSC aimes to aggregate more contextual information for each sample point in the aortic branches with small tubular diameters. SDM is introduced as auxiliary information to measure the similarity of neighboring points, and it provides weights for feature fusion. Furthermore, we embed the learned 3D offset field into OSC to avoid inaccurate segmentation on the region around the narrow tubular structures. the OSC module prolongs the predicted length of small aorta branches and then improves the tubular continuity of the aorta segmentation map. We evaluate the OSC module on our-collected dataset and MICCAI ASOCA2020 coronary artery dataset. Our method has achieved the state-of-the-art results in terms of Dice and Jaccard metrics.

关键词： Weight measurement Image segmentation three-dimensional displays Convolution Shape Shape measurement Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Multifactorial Bare Bones Sine Cosine algorithm with Chaotic-based elite learning for Multi-tasking Optimization

Multifactorial Bare Bones Sine Cosine algorithm with Chaotic...

引用

Artificial Intelligence Technology (ACAIT), asian conference on

作者： Ning Li Lei Wang Qiaoyong Jiang Xiaoyu Li Bin Wang Guangnan Zhang Computer Science and Engineering Xi’an University of Technology Xi’an China School of Computer Science Baoji University of Arts and Sciences Baoji China The Key Laboratory of Industrial Automation of Shaanxi Provice Shaanxi University of Technolog Hanzhong China

ISBN: (纸本)9781665426312

the problem of multi-task optimization is a new research topic in the field of evolutionary computing in recent years, and it has attracted more and more attention from the academic community. Compared with single-objective optimization and multi-objective optimization, multi-task optimization can use the similarity and complementarity between tasks to solve different optimization tasks at the same time. However, as the population evolves to the later stage, the ability of the two tasks to learn from each other gradually declines. In order to solve this problem and enhance the effectiveness of knowledge transfer between different tasks, this paper combines the bare bone sine cosine algorithm (BBSCA) and the elite learning strategy based on chaos mapping (ELM) into MFEA, and proposes the MFBBSCA-ELM algorithm. Since BBSCA and ELM have different search neighborhoods and are highly complementary to the analog binary crossover used in the classic MFEA algorithm, this article combines BBSCA and ELM, which is also the motivation of this article. In addition, the integration of BBSCA and ELM can reduce the probability of MFEA falling into a local optimum. Finally, this article verifies the effectiveness of integrating BBSCA and ELM into MFEA on the classic MTO benchmark problem. the experimental results show that compared with the classic MFEA, the performance of the MFBBSCA-ELM proposed in this paper has been significantly improved.

关键词： Learning systems Sociology Benchmark testing Multitasking Bones Task analysis Statistics

来源：评论

学校读者我要写书评

暂无评论

Twitter scrapping for profiling education staff 5

Twitter scrapping for profiling education staff

引用

5th International conference on Informatics and computing, ICIC 2020

作者： Herlawati, Herlawati Trias Handayanto, Rahmadya Ekawati, Inna Meutia, Kardinah Indrianna asian, Jelita Aditiawarman, Umar Informatics Engineering Universitas Bhayangkara Jakarta Raya Bekasi17121 Indonesia Computer Engineering Universitas Islam 45 Bekasi17113 Indonesia Management Universitas Bhayangkara Jakarta Raya Bekasi17121 Indonesia School of Computer Science Nusa Putra University Sukabumi43152 Indonesia

ISBN: (纸本)9781728180472

Social media (Facebook, Instagram, Twitter, etc.) have been widely used. they have many advantages, especially for business. However, such media sometimes invite negative effects, e.g. decreasing employee performance, conflict in a relationship, crime, etc. therefore, this study proposes a method to scrap one of the social media, i.e. Twitter for profiling. Gephi application is used for network analysis after scrapping the network using Twecoll, a Python-based scrapping application. A web-based application is also created including the Apache-based server and Python-based script. the result shows that the scrapped account has several groups/communities including the weight of each connection. In addition, the result can be used for group profiling and additional analysis to complete the sentiment analysis based on tweets. © 2020 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Temporal-Aware Self-Supervised Learning for Unsupervised Video Anomaly Detection

Temporal-Aware Self-Supervised Learning for Unsupervised Vid...

引用

Artificial Intelligence Technology (ACAIT), asian conference on

作者： Guoqian Shang Chao Huang Jingyong Su Yong Xu Bio-Computing Research Center Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9781665426312

Video anomaly detection (VAD) is commonly formulated as the discrimination of events that do not confirm to the regular patterns in videos. Recently, deep neural network-based VAD approaches have gained remarkable progresses. Existing unsupervised approaches usually achieve VAD by frame reconstruction or prediction, and then identifying anomalies according to the reconstruction or prediction errors. However, these approaches suffer from two limitations: (1) they cannot obtain the semantic features of normal training samples. (2) It is suboptimal because of the non-alignment between the proxy and actual tasks. To address the above issues, we present a novel temporal-aware self-supervised learning framework to obtain the high-level semantic features and to perform VAD by solving multiple pretext tasks. In particular, we utilize temporal transformations to form multiple pretext tasks (transformations prediction) for VAD. A 3D encoder is trained to obtain semantic features by jointly solving these pretext tasks. then, multi task heads utilize these features to solve different pretext tasks. In the inference phase, multiple task losses are used for calculating the final anomaly score. Extensive experiments are conducted on two benchmarks, which shows that the proposed method outperforms state-of-the-arts.

关键词： Training Representation learning three-dimensional displays Semantics Neural networks Benchmark testing Task analysis

来源：评论

学校读者我要写书评

暂无评论

Outstanding People and Works in the Area of Computer science Enhancing Quality of Life. the Evidence from Prestigious American, European and asian Computer science Awards 40th

Outstanding People and Works in the Area of Computer Science...

引用

40th Anniversary International conference on Information Systems Architecture and Technology (ISAT)

作者： Wiechetek, Lukasz Marie Curie Sklodowska Univ Fac Econ Lublin Poland

ISBN: (纸本)9783030304430;9783030304423

Information technology is one of the fastest developing business sector and research area. People use IT solutions based on computer science both for entertainment, education and work. Modern organizations cannot operate effectively without application of IT tools for data acquisition, storage, communication, visualization, but also for linking digital world with the real life or the real business processes. Works in the field of computer science are the foundation of fast and balanced development of IT sector. they are the accelerators of transformation from traditional, real economy into digital business and digital society. the main aim of the article is to explore what nations, people and works played the most significant role in development of information technology during the previous decades. Also what works are crucial today to ensure stability of present digital natives. the author analyzes the five prestigious awards in computer science to find out what works were honored for the past hundred years. In the first part of the article the characteristics of the explored awards is presented. the second part of the paper contains quantitative analysis of award recipients (n = 224) and prizes comparison. the performed literature review and the analysis of the awarded works allow to conclude that during the last decades the main drivers for IT development, noticed by awards committees were related both to the theory, hardware, software development and application areas. the vast majority of laureates came from (was born in) United States (62%), United Kingdom (8,5%) and Japan (4,9%). At the beginning of twenty first century huge amounts of data are generated not only by people but also autonomous objects, so the most crucial in computer science was to prepare systems and networks for secure processing (transferring) huge amounts of data in real time and find methods to assess the accuracy and quality of the information. therefore, new awards like IEEE Internet Aw

关键词： Computer science IT Award Turing Award Millennium Prize Kyoto Prize IEEE Medal of Honor IEEE Internet Award IT evolution Computer science evolution Important works in IT

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Fully Convolutional Networks for Stroke Recovery of Handwritten Chinese Character 5th

Two-Stage Fully Convolutional Networks for Stroke Recovery o...

引用

5th asian conference on Pattern Recognition, ACPR 2019

作者： Wang, Yujung Sonogashira, Motoharu Hashimoto, Atsushi Iiyama, Masaaki Graduate School of Informatics Kyoto University Kyoto Japan Academic Center for Computing and Media Studies Kyoto University Kyoto Japan Graduate School of Education Kyoto University Kyoto Japan

ISBN: (纸本)9783030412982

In this paper, we propose a method to recover strokes from offline handwritten Chinese characters. the proposed method employs a fully convolutional network (FCN) to estimate the writing order of connected components in offline Chinese character images and a multi-task FCN to estimate the writing order and directions of strokes in each connected component. Online dataset CASIA-OLHWDB1.0 from the CASIA database is hired as the training set. Because the network produces discontinuous strokes, we refine the estimated writing orders using a graph cut (GC), in which the estimated directions are used for calculation of smoothness term. Experimental results with test dataset of CASIA-OLHWDB1.0tst demonstrate the effectiveness of our method. © 2020, Springer Nature Switzerland AG.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Group Activity Recognition via computing Human Pose Motion History and Collective Map from Video 5th

Group Activity Recognition via Computing Human Pose Motion H...

引用

5th asian conference on Pattern Recognition, ACPR 2019

作者： Chen, Hsing-Yu Lai, Shang-Hong Department of Computer Science National Tsing Hua University Hsinchu Taiwan

ISBN: (纸本)9783030412982

In this paper, we propose a deep learning based approach that exploits multi-person pose estimation from an image sequence to predict individual actions as well as the collective activity for a group scene. We first apply multi-person pose estimation to extract pose information from the image sequence. then we propose a novel representation called pose motion history (PMH), that aggregates spatio-temporal dynamics of multi-person human joints in the whole scene into a single stack of feature maps. then, individual pose motion history stacks (Indi-PMH) are cropped from the whole scene stack and sent into a CNN model to obtain individual action predictions. Based on these individual predictions, we construct a collective map that encodes both the positions and actions of all individuals in the group scene into a feature map stack. the final group activity prediction is determined by fusing results of two classification CNNs. One takes the whole scene pose motion history stack as input, and the other takes the collective map stack as input. We evaluate the proposed approach on a challenging Volleyball dataset, and it provides very competitive performance compared to the state-of-the-art methods. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Denoising and Inpainting of Sea Surface Temperature Image with Adversarial Physical Model Loss 5th

Denoising and Inpainting of Sea Surface Temperature Image wi...

引用

5th asian conference on Pattern Recognition, ACPR 2019

作者： Hirahara, Nobuyuki Sonogashira, Motoharu Kasahara, Hidekazu Iiyama, Masaaki Graduate School of Informatics Kyoto University Kyoto Japan Academic Center for Computing and Media Studies Kyoto University Kyoto Japan

ISBN: (纸本)9783030414030

this paper proposes a new approach for meteorology;estimating sea surface temperatures (SSTs) by using deep learning. SSTs are essential information for ocean-related industries but are hard to measure. Although multi-spectral imaging sensors on meteorological satellites are used for measuring SSTs over a wide area, they cannot measure sea temperature in regions covered by clouds, so most of the temperature data will be partially occluded. In meteorology, data assimilation with physics-based simulation is used for interpolating occluded SSTs, and can generate physically-correct SSTs that match observations by satellites, but it requires huge computational cost. We propose a low-cost learning-based method using pre-computed data-assimilation SSTs. Our restoration model employs adversarial physical model loss that evaluates physical correctness of generated SST images, and restores SST images in real time. Experimental results with satellite images show that the proposed method can reconstruct physically-correct SST images without occlusions. © Springer Nature Switzerland AG 2020.

关键词： Surface temperature

来源：评论

学校读者我要写书评

暂无评论

5th asian Supercomputing conference, SCFA 2019

5th Asian Supercomputing Conference, SCFA 2019

引用

5th asian Supercomputing conference, SCFA 2019

ISBN: (纸本)9783030186449

the proceedings contain 6 papers. the special focus in this conference is on asian Supercomputing. the topics include: A crystal/clear pipeline for applied image processing;a cache-based data movement infrastructure for on-demand scientific cloud computing;PHINEAS: An embedded heterogeneous parallel platform;MH-QEMU: Memory-state-aware fault injection platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selecting Discriminative Features for Fine-Grained Visual Classification 5th

Selecting Discriminative Features for Fine-Grained Visual Cl...

引用

5th asian conference on Pattern Recognition, ACPR 2019

作者： Xu, Qin Li, Linyang Chen, Qian Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9783030414030

Fine-grained visual classification is a challenging task because of intra-class variation and inter-class similarity. Most fine-grained models predominantly focus on discriminative region localization which can effectively solve the intra-class variation, but ignore global information and the problem of inter-class similarity which easily leads to overfitting on specific samples. To address these issues, we develop an end-to-end model based on selecting discriminative features for fine-grained visual classification without the help of part or bounding box annotations. In order to accurately select discriminative features, we integrate effective information from different receptive fields to enhance the quality of features, then the features of discriminative regions detected by anchors and the whole image’s feature are jointly processed for classification. Besides, we propose a new loss function to optimize the model to find discriminative regions and prevent overfitting in the particular sample, which can simultaneously solve the problems of intra-class variation and inter-class similarity. Comprehensive experiments show that the proposed approach is superior to the state-of-the-art methods on CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets. © Springer Nature Switzerland AG 2020.

关键词： Classification (of information)

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12页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：