检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Dong, Jianfeng Li, Xirong Xu, Chaoxi Yang, Xun Yang, Gang Wang, Xun Wang, Meng College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AI and Media Computing Lab School of Information Renmin University of China Beijing100872 China School of Computing National University of Singapore Singapore37580 Singapore School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method. Code is available at https://***/danieljf24/hybrid_space. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

DeepKAF: A Heterogeneous CBR & Deep Learning Approach for NLP Prototyping

DeepKAF: A Heterogeneous CBR & Deep Learning Approach for NL...

引用

IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA)

作者： Kareem Amin Stelios Kapetanakis Nikolaos Polatidis Klaus-Dieter Althoff Andreas Dengel Smart Data and Knowledge Services German Research Center for Artificial Intelligence Technische Universität Kaiserslautern Kaiserslautern Germany School of Computing Engineering and Mathematics University of Brighton Brighton United Kingdom Intelligent Information Systems Lab Institute of Computer Science University of Hildesheim Hildesheim Germany

ISBN: (数字)9781728167992

ISBN: (纸本)9781728168005

With widespread modernization, digitization and transformations of most of industries, Artificial Intelligence (AI) has become the key enabler in that modernization journey. AI offers substantial capabilities to solve new problems and optimise existing solutions specialising on specific problems and learning from different domains. AI solutions can be either explainable or black box ones with the latter being urged to improve since they cannot trust. Case-based Reasoning (CBR) is an explainable AI approach where solutions are provided along with relevant explanations in terms of why a solution was selected. However, CBR, like most other explainable approaches, has several limitations in terms of scalability, large data volumes, domain complexity, that reduce its ability to scale any CBR system in industrial applications. In this paper, we provide a heterogeneous CBR framework - DeepKAF where we combine CBR paradigm with Deep Learning architectures to solve complicated Natural Language Processing (NLP) problems (eg. mixed language and grammatically incorrect text).DeepKAF is built based on continuous research in the area of Deep Learning and CBR. DeepKAF has been implemented and used across different domains, test use cases and research models as an ensemble deep learning and CBR Architecture.

关键词： Machine learning Training Neural networks Natural language processing Cognition Buildings Task analysis

来源：评论

学校读者我要写书评

暂无评论

Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation

arXiv

引用

arXiv 2020年

作者： Hao, Shijie Zhou, Yuan Guo, Yanrong Hong, Richang Cheng, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Chinese University of Hong Kong Hong Kong

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing systems that are resource-constrained but require fast response speed. Therefore, it is valuable to develop accurate and real-time vision processing models that only require limited computational resources. To this end, we propose the Spatial-detail Guided Context Propagation Network (SGCPNet) for achieving real-time semantic segmentation. In SGCPNet, we propose the strategy of spatial-detail guided context propagation. It uses the spatial details of shallow layers to guide the propagation of the low-resolution global contexts, in which the lost spatial information can be effectively reconstructed. In this way, the need for maintaining high-resolution features along the network is freed, therefore largely improving the model efficiency. On the other hand, due to the effective reconstruction of spatial details, the segmentation accuracy can be still preserved. In the experiments, we validate the effectiveness and efficiency of the proposed SGCPNet model. On the Citysacpes dataset, for example, our SGCPNet achieves 69.5% mIoU segmentation accuracy, while its speed reaches 178.5 FPS on 768×1536 images on a GeForce GTX 1080 Ti GPU card. In addition, SGCPNet is very lightweight and only contains 0.61 M parameters. The code will be released at https://***/zhouyuan888888/SGCPNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

On multi-objective minimum spanning tree under the framework of uncertainty theory

引用

AIP Conference Proceedings 2023年第1期2851卷

作者： Swapna Halder Saibal Majumder Arindam Biswas Bijoy Kumar Mandal Sheng-Lung Peng Department of Computer Science and Engineering St. Thomas College of Engineering & Technology Kolkata West Bengal India Centre for IOT and AI Integration with Education -Industry-Agriculture Kazi Nazrul University Asansol West Bengal India Department of Computer Science and Engineering (Data Science) Dr. B. C. Roy Engineering College Durgapur West Bengal India School of Mines and Metallurgy Kazi Nazrul University Asansol West Bengal India Department of Computer Science and Engineering NSHM Knowledge Campus Durgapur West Bengal India Department of Creative Technologies and Product Design National Taipei University of Business Taoyuan Taiwan

Aminimum spanning tree with multiple objectives is one type of NP hard problem, and it has a wide application area in ourdaily life. Modelling real world problems, requires many associated parameters which are not well-defined and are indeterminate in nature. Thus, it is rational to consider these indeterminate parameters while modelling real life problems. This article, investigates onthe study of minimum spanning tree with multiple objectives which are uncertain in nature. The proposed multiple objectives minimum spanning tree has two uncertain parameters associated with it, they are time and cost. Both of these parameters are indeterminate in nature and characterizedas uncertain variables. The expected value model (EVM) of multiple objectives minimum spanning tree is formulatedin this study and convex combination method is used to solve this problem. Finally to achieve the nondominated solutions of this problem, we have solved the EVM by varying the related weights of its objectives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collective fast delivery by energy-efficient agents 43

Collective fast delivery by energy-efficient agents

引用

43rd International Symposium on Mathematical Foundations of Computer Science, MFCS 2018

作者： Bärtschi, Andreas Graf, Daniel Mihalák, Matúš Department of Computer Science ETH Zürich Switzerland Department of Data Science and Knowledge Engineering Maastricht University Netherlands

ISBN: (纸本)9783959770866

We consider k mobile agents initially located at distinct nodes of an undirected graph (on n nodes, with edge lengths). The agents have to deliver a single item from a given source node s to a given target node t. The agents can move along the edges of the graph, starting at time 0, with respect to the following: Each agent i has a weight ωi that defines the rate of energy consumption while travelling a distance in the graph, and a velocity υi with which it can move. We are interested in schedules (operating the k agents) that result in a small delivery time T (time when the item arrives at t), and small total energy consumption E. Concretely, we ask for a schedule that: either (i) Minimizes T , (ii) Minimizes lexicographically (T, E) (prioritizing fast delivery), or (iii) Minimizes · T + (1 − ) · E, for a given ∈ (0, 1). We show that (i) is solvable in polynomial time, and show that (ii) is polynomial-time solvable for uniform velocities and solvable in time O(n + k log k) for arbitrary velocities on paths, but in general is NP-hard even on planar graphs. As a corollary of our hardness result, (iii) is NP-hard, too. We show that there is a 2-approximation algorithm for (iii) using a single agent. © Andreas Bärtschi, Daniel Graf, and Matúš Mihalák.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Research on Government Information Sharing Model Using Blockchain Technology

Research on Government Information Sharing Model Using Block...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Yiwei Zhang Sanhong Deng Yue Zhang Jia Kong School of Information Management Nanjing University Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing China Nanjing University Nanjing China

Research Purpose: The distributed, traceable and security of blockchain technology are applicable to the construction of new government information resource models, which could eliminate the barn effect and trust in government information sharing, as well as promoting the transformation of government affairs from management to service, it is also of great significance to the sharing of government information and construction of service-oriented e-government. Propose Methods: By analyzing the current problems of government information sharing, combined with literature research, this paper proposes the theoretical framework and advantages of blockchain technology applied to government information management and sharing, expounds the blockchain-based solution, it also constructs a government information sharing model based on blockchain, and gives implementation strategies at the technical and management levels. Results and Conclusion: The government information sharing model based on the blockchain solution and the transparency of government information can be used as a research framework for information interaction analysis between the government and users. It can also promote the construction and development of information sharing for Chinese government, as well as providing unified information sharing solution at the departmental and regional levels for e-government.

关键词： Blockchain Information management Security Electronic government Information services data engineering

来源：评论

学校读者我要写书评

暂无评论

Self-concordant analysis of frank-wolfe algorithms

arXiv

引用

arXiv 2020年

作者： Dvurechensky, Pavel Shtern, Shimrit Staudigl, Mathias Ostroukhov, Petr Safin, Kamil Weierstrass Institute for Applied Analysis and Stochastics Mohrenstr. 39 Berlin10117 Germany Faculty of Industrial Engineering and Management Technion - Israel Institute of Technology Haifa Israel Department of Data Science and Knowledge Engineering Maastricht University P.O. Box 616 MaastrichtNL-6200 MD Netherlands Moscow Institute of Physics and Technology Dolgoprudny Russia

Projection-free optimization via different variants of the Frank-Wolfe (FW) method has become one of the cornerstones in optimization for machine learning since in many cases the linear minimization oracle is much cheaper to implement than projections and some sparsity needs to be preserved. In a number of applications, e.g. Poisson inverse problems or quantum state tomography, the loss is given by a self-concordant (SC) function having unbounded curvature, implying absence of theoretical guarantees for the existing FW methods. We use the theory of SC functions to provide a new adaptive step size for FW methods and prove global convergence rate O(1/k), k being the iteration counter. If the problem can be represented by a local linear minimization oracle, we are the first to propose a FW method with linear convergence rate without assuming neither strong convexity nor a Lipschitz continuous *** Codes 65K05, 90C25, Copyright © 2020, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

"Did You Hear That?" Learning to Play Video Games from Audio Cues

arXiv

引用

arXiv 2019年

作者： Gaina, Raluca D. Stephenson, Matthew Game AI Research Group Queen Mary University of London United Kingdom Department of Data Science Knowledge Engineering Maasricht University Netherlands

Game-playing AI research has focused for a long time on learning to play video games from visual input or symbolic information. However, humans benefit from a wider array of sensors which we utilise in order to navigate the world around us. In particular, sounds and music are key to how many of us perceive the world and influence the decisions we make. In this paper, we present initial experiments on game-playing agents learning to play video games solely from audio cues. We expand the Video Game Description Language to allow for audio specification, and the General Video Game AI framework to provide new audio games and an API for learning agents to make use of audio observations. We analyse the games and the audio game design process, include initial results with simple Q-Learning agents, and encourage further research in this area. Copyright © 2019, The Authors. All rights reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Privacy preservation for recommendation databases

Privacy preservation for recommendation databases

引用

作者： Riyana, Surapon Natwichai, Juggapong Data Engineering and Network Technology Laboratory Faculty of Engineering Chiang Mai University Chiang Mai Thailand Center of Data Analytics and Knowledge Synthesis for Healthcare Chiang Mai University Chiang Mai Thailand

Since recommendation systems play an important role in the current situations where such digital transformation is highly demanded, the privacy of the individuals’ collected data in the systems must be secured effectively. In this paper, the vulnerability of the existing query framework for the recommendation systems is identified. Thus, we propose to apply the well-known k-anonymity model to generalize the given recommendation databases to satisfy the privacy preservation constraint. We show that such data generalization problem which minimizes the impact on data utility is NP-hard. To tackle with such problem, an algorithm to preserve the privacy of the individuals in the recommendation databases is proposed. The idea is to avoid excessive generalizing on the databases by forming a group of similar tuples in the databases. Thus, the impact on the data utility of the generalizing such group can be minimized. Our work is evaluated by extensive experiments. From the results, it is found that our work is highly effective, i.e., the impact quantified by the data utility metrics and the errors of the query results are less than the compared algorithms, and also it is highly efficient, i.e., the execution time is less than the result of its effectiveness-comparable algorithm by more than three times. © 2018, Springer-Verlag London Ltd., part of Springer Nature.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Finding optimal Stackelberg production strategies: How to produce in times of war?

arXiv

引用

arXiv 2020年

作者： Schlicher, Loe Musegaas, Marieke Blok, Herman School of Industrial Engineering Eindhoven University of Technology P.O. Box 513 Eindhoven5600 MB Netherlands Department of Data Science and Knowledge Engineering Maastricht University P.O. Box 616 Maastricht6200 MD Netherlands Department of Mathematics Vrije Universiteit Amsterdam De Boelelaan 1081a Amsterdam1081 HV Netherlands

Inspired by a military context, we study a Stackelberg production game where a country’s government, the leader, wants to maximize the production of military assets. The leader does so by allocating his resources among a set of production facilities. His opponent, the follower, observes this allocation and tries to destroy the associated production as much as possible by allocating his destructive resources, for example bombs, among these facilities. In this paper, we identify a follower’s optimal strategy. For the leader, we show that an optimal production strategy can be found in the class of so-called seried-balanced strategies. We present a linear time algorithm that finds an optimal strategy in this class. Copyright © 2020, The Authors. All rights reserved.

关键词： Clustering algorithms

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：