检索结果-内蒙古大学图书馆

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Ruizhi Zhou Lingfeng Niu Zhiquan Qi School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge management Chinese Academy of Sciences Beijing China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing China

The image restoration task is often modelled as an unconstrained minimization, which is composed of a quadratic data-fidelity term and a regularization term. Recently, nonsmooth regularization received significant attentions due to its excellent empirical performance on the presence of edges. To handle the nonsmoothness of the cost function, we propose a smoothing trust region algorithm in this paper. In order to make the new method more efficient and more suitable for big data situation, the Steihaug-CG algorithm is utilized to solve the trust region subproblem. New algorithm is compared with the Lucy-Richardson method. Numerical experiments on several images validate the effectiveness of the proposed method.

关键词： Image restoration Smoothing methods Approximation algorithms Image edge detection Cost function Symmetric matrices Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation via Improving Clustering Algorithms with Density and Distance

引用

Procedia Computer Science 2015年 55卷 1015-1022页

作者： Zhensong Chen Zhiquan Qi Fan Meng Limeng Cui Yong Shi School of Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management CAS Beijing 100190 China Sino-Danish Center for Education and Research Beijing 100190 China Research Center on Fictitious Economy and Data Science CAS Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100190 China

Image segmentation problem is a fundamental task and process in computer vision and image processing applications. It is well known that the performance of image segmentation is mainly influenced by two factors: the segmentation approaches and the feature presentation. As for image segmentation methods, clustering algorithm is one of the most popular approaches. However, most current clustering-based segmentation methods exist some problems, such as the number of regions of image have to be given prior, the different initial cluster centers will produce different segmentation results and so on. In this paper, we present a novel image segmentation approach based on DP clustering algorithm. Compared with the current methods, our method has several improved advantages as follows: 1) This algorithm could directly give the cluster number of the image based on the decision graph; 2) The cluster centers could be identified correctly; 3) We could simply achieve the hierarchical segmentation according to the applications requirement. A lot of experiments demonstrate the validity of this novel segmentation algorithm.

关键词： Image Segmentation Clustering Algorithm Feature Representation

来源：评论

学校读者我要写书评

暂无评论

Promoting Business Analytics and Quantitative management of Technology: Preface for ITQM 2016

引用

Procedia Computer Science 2016年 91卷 1-8页

作者： Lee, Heeseok Shi, Yong Lee, Jongwon Cordova, Felisa Dzitac, Ioan Kou, Gang Li, Jaiping College of Business Korea Advanced Institute Science and Technology Dongdaemum-gu Seoul130-722 Korea Republic of Research Center on Fictitiotus Economy and Data Science Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States School of Business Administration Hoseo University Asan-si Chungcheongnam-do336-795 Korea Republic of Faculty of Engineering and Business University Finis Terrae Pedro de Valdivia 1509. Providencia Santiago Chile Universitatea Agora Agora University Piata Tineretului 8 Oradea410526 Romania School of Business Administration Southwestern University of Finance and Economics Chengdu Sichuan61130 China Institute of Policy and Management Chinese Academy of Sciences Beijing100190 China

来源：评论

学校读者我要写书评

暂无评论

Can stock markets lead the macroeconomic variables? Dynamic analysis based on TOP method

引用

Procedia Computer Science 2019年 162卷 39-45页

作者： Zhenni Jin Yijing Wang Xiao Cui Kun Guo Sino-Danish College University of Chinese Academy of Science Beijing China Research Center on Fictitious Economy & Data Science Chinese Academy of Science Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Science Beijing China School of Economics and Management University of Chinese Academy of Science Beijing China CHINALCO Finance Company Limited Beijing China

Fictitious economy connects with real economy in many aspects. The interaction between stock markets and macro-economy is becoming more and more crucial for different parties in the whole economic society. On the basis of the Thermal Optimal Path (TOP) method, this paper used the quarterly and monthly data of seven pairs of time series to analyse the dynamic lead-lag connections between the macro-economic fluctuation and the stock market change. The results suggest that the data of stock market can be used to predict the macro-economic variables for most time periods. Investors as an important agent in the stock markets, their expectations can be reflected by stock prices. The irrationality of investors can affect the” barometer” function of stock markets.

关键词： Stock market Macro-economy Thermal optimal path Lead-lag analysis

来源：评论

学校读者我要写书评

暂无评论

Exploiting sample correlation for crowd counting with multi-expert network

Exploiting sample correlation for crowd counting with multi-...

引用

International Conference on Computer Vision (ICCV)

作者： Xinyan Liu Guorong Li Zhenjun Han Weigang Zhang Yifan Yang Qingming Huang Nicu Sebe University of Chinese Academy of Sciences Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Harbin Institute of Technology Weihai China Key Lab of Intelligent Information Processing ICT CAS Beijing China University of Trento Trento Italy

ISBN: (纸本)9781665428132

Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately, the performance of existing methods on large-scale data sets is not satisfactory. In order to handle various scenarios with less complex network, we explored how to efficiently use the multi-expert model for crowd counting tasks. We mainly focus on how to train more efficient expert networks and how to choose the most suitable expert. Specifically, we propose a task-driven similarity metric based on sample’s mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network. Similar samples are considered as a cluster which is used to obtain parameters of an expert. Besides, to make better use of the proposed method, we design a simple network called FPN with Deconvolution Counting Network, which is a more suitable base model for the multi-expert counting network. Experimental results show that multiple experts FDC (MFDC) achieves the best performance on four public data sets, including the large scale NWPU-Crowd data set. Furthermore, the MFDC trained on an extensive dense crowd data set can generalize well on the other data sets without extra training or fine-tuning. 1

关键词： Training Measurement Computer vision Deconvolution Correlation Design methodology Training data

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Reinforcement Learning – Concept, Approaches and Applications

引用

Procedia Computer Science 2023年 221卷 526-532页

作者： Linzi Zhang Zhiquan Qi Yong Shi School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China University of Birmingham Edgbaston Birmingham B15 2TT United Kingdom Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Real-world decision-making tasks are generally complicated and require trade-offs between multiple, even conflicting, objectives. As the advent and great development of advanced information technology, it has evolved into using reinforcement learning (RL) algorithms to tackle the multi-objective decision making (MODM) problems. In this paper, we will first identify the basic concepts and factors when modelling the MODM tasks with reinforcement learning, and then review the traditional RL, such as Sarsa, Q-Learning, Policy Gradients, Actor-Critic, Monte-Carlo learning, and modern deep RL algorithms applied in this process. Furthermore, the specific practical scenarios described in MODM problems will be summarized through analyzing some typical articles. Finally, the future trends of multi-objective reinforcement learning will be discussed.

关键词： Multi-objective decision making Reinforcement Learning Survey

来源：评论

学校读者我要写书评

暂无评论

Video saliency prediction with optimized optical flow and gravity center bias

Video saliency prediction with optimized optical flow and gr...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhe Wu Li Su Qingming Huang Bo Wu Jian Li Guorong Li Key Lab on Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China Capital Medical University Beijing China Beijing University of Posts and Telecommunications China Beijing

ISBN: (纸本)9781467372596

Dynamic videos are viewed fundamentally different from static images. Besides spatial features, motion feature also plays an important role as a temporal factor. Most existing video saliency models usually employ optical flow to represent the motion feature. However, optical flow often suffers from the discontinuity problem. And we also notice that human fixations in one single video frame are much sparser than that in an identical still picture. However, many spatial saliency models take each video frame as static image independently. In this paper, we predict the dynamic visual saliency by fusing spatial and temporal features. In order to construct the temporal relationships among a set of successive frames, we introduce a smoothness operator in optical flow field to obtain more accurate motion feature. Then, considering the sparse property of video saliency, we adapt the weights of the regions surrounding to the saliency gravity center in the final maps. The experiments show that our model is more consistent with humans eye-tracking benchmarks than the state-of-the-art models.

关键词： Optical imaging Gravity Computational modeling Visualization Biomedical optical imaging Adaptation models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Macroprudential policy in retail lending: Concept and results – a case study of the Bank of Russia

引用

Procedia Computer Science 2024年 242卷 1331-1338页

作者： Ekaterina Eremina Yong Shi School of Economics and Management University of Chinese Academy of Sciences No.19A Yuquan Road Beijing 100049 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences No.19A Yuquan Road Beijing 100049 China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences No.19A Yuquan Road Beijing 100049 China

Macroprudential regulation of the banking system is a significant instrument for ensuring the financial stability of the state. Unsecured consumer lending is growing at a steadily high rate (in August-October 2022, the average monthly debt growth was 0.9%), and it remains a priority segment for banks because of its high margins. The share of unsecured consumer loans provided to borrowers with debt burden indicator (DBI) of more than 80% amounted to more than 32% in the third quarter of 2022 (28% in the second quarter of 2022). The share of consumer loans for a term of more than 5 years remains at a high level (15% in July-September 2022). The share of MFO loans issued to borrowers with a DBI of more than 80% was 41% in the second quarter of 2022 (38% in the first quarter of 2022). A further increase in the citizens’ debt burden in the context of the economy restructuring may create additional macroeconomic risks. Problems of citizens with servicing loans and borrowings can lead to a reduction in demand in the economy, and losses of banks as a result of writing off “bad” loans can lead to a decrease in their ability to lend to the economy. To limit the risks associated with an increase in the citizens’ debt burden, since the first quarter of 2023, the Bank of Russia has established direct quantitative restrictions on the issuance of certain types of credits (loans) and the application of increased buffers to risk coefficients if creditors exceed established limits. This article discusses the main approaches to implementation of the macroprudential policy of the Central Bank of the Russian Federation, its goals and instruments, and peculiarities of application in the current conditions.

关键词： macroprudential policy banking system risks macroprudential instruments Bank of Russia

来源：评论

学校读者我要写书评

暂无评论

Threshold and Deadline Effect in Crowdfunding

引用

Procedia Computer Science 2019年 162卷 339-346页

作者： Yan Song Xin Tian Chunlin Luo Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190China School of Information Technology Jiangxi University of Finance and Economics Nanchang Jiangxi 330013China

The deadline effect and threshold effect are common in product development and group buying. We consider these two effects also exist in crowdfunding, affecting the crowdfunding performance in the future. We conduct an empirical study using a dataset from *** to examine these two effects and their interactive relationship on the following crowdfunding performance. We find the threshold effect exists in crowdfunding and has a positive influence on the following contribution behaviour. The deadline effect also can stimulate the crowdfunding behaviour via limited fundraising time. Furthermore, we find the threshold effect and deadline effect are complements that increase the amount pledged.

关键词： crowdfunding performance threshold effect deadline effect interactive effect

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Relation between Artificial Intelligence and the Internet from the Perspective of Brain Science

引用

Procedia Computer Science 2017年 122卷 377-383页

作者： Feng Liu Yong Shi Peijia Li Research Center on Fictitious Economy and Data Science the Chinese Academy of Sciences Beijing 100190 China The Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China

Artificial intelligence (AI) like deep learning, cloud AI computation has been advancing at a rapid pace since 2014. There is no doubt that the prosperity of AI is inseparable with the development of the Internet. However, there has been little attention to the link between AI and the internet. This paper explores them with brain insights mainly from four views:1) How is the general relation between artificial intelligence and Internet of Things, cloud computing, big data and Industrial Internet from the perspective of brain science. 2) Construction of a new AI system model with the Internet and brain science.

关键词： Internet’s virtual brain big SNS AI model of the Internet-like brain

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：