检索结果-内蒙古大学图书馆

IEEE/CVF Conference on computer Vision and Pattern Recognition

作者： Qiudan Zhang Xu Wang Shiqi Wang Shikai Li Sam Kwong Jianmin Jiang College of Computer Science and Software Engineering Shenzhen University Department of Computer Science City University of Hong Kong

The human visual system excels at biasing the stereoscopic visual signals by the attention mechanisms. Traditional methods relying on the low-level features and depth relevant information for stereoscopic video saliency prediction have fundamental limitations. For example, it is cumbersome to model the interactions between multiple visual cues including spatial, temporal, and depth information as a result of the sophistication. In this paper, we argue that the high-level features are crucial and resort to the deep learning framework to learn the saliency map of stereoscopic videos. Driven by spatio-temporal coherence from consecutive frames, the model first imitates the mechanism of saliency by taking advantage of the 3D convolutional neural network. Subsequently, the saliency originated from the intrinsic depth is derived based on the correlations between left and right views in a data-driven manner. Finally, a Convolutional Long Short-Term Memory (Conv-LSTM) based fusion network is developed to model the instantaneous interactions between spatio-temporal and depth attributes, such that the ultimate stereoscopic saliency maps over time are produced. Moreover, we establish a new large-scale stereoscopic video saliency dataset (SVS) including 175 stereoscopic video sequences and their fixation density annotations, aiming to comprehensively study the intrinsic attributes for stereoscopic video saliency detection. Extensive experiments show that our proposed model can achieve superior performance compared to the state-of-the-art methods on the newly built dataset for stereoscopic videos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hybrid filtering-based network document recommendation system in cloud storage

A hybrid filtering-based network document recommendation sys...

引用

International Journal of Computational science and engineering

作者： Wu, Yuezhong Liu, Qin Li, Changyun Wang, Guojun School of Information Science and Engineering Central South University Changsha410083 China School of Computer Science Hunan University of Technology Zhuzhou412007 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory School of Computer Science Hunan University of Technology Zhuzhou412007 China School of Computer Science and Educational Software Guangzhou University Guangzhou510006 China

Since the key requirement of users is to efficiently obtain personalised services from mass network document resources, a hybrid filtering-based network document recommendation system is designed with the method of incorporating the content-based recommendation and collaborative filtering recommendation based on the powerful and extensible storage and computing power in cloud storage. The proposed system realises the main service module on Hadoop and Mahout platforms, and processes the documents containing the information of user interests by applying AHP-based attribute weighted fusion method. Based on the network interaction, the proposed system not only has advantages on the extensible storage space and high recommendation precision but also has an essential role in realising network resources sharing and personalised recommendation. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Storage as a service (STaaS) Collaborative filtering Information retrieval systems Recommender systems Cloud storages Collaborative filtering recommendations Content based recommendation Document recommendation Network interaction Personalised recommendations Recommendation precision User interest model

来源：评论

学校读者我要写书评

暂无评论

PAT: Preference-Aware Transfer Learning for Recommendation with Heterogeneous Feedback

PAT: Preference-Aware Transfer Learning for Recommendation w...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Feng Liang Wei Dai Yunfeng Huang Weike Pan Zhong Ming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In this paper, we study an important recommendation problem with heterogeneous feedback of users' grade scores such as 5-star grade scores and like/dislike binary ratings assigned to items. As a response, we address the problem from a transfer learning perspective, i.e., taking the grade scores as the target data and the binary ratings as the auxiliary data, in order to share knowledge between two different types of data more sufficiently. Technically, besides the observed explicit feedback of grade scores and binary ratings, we propose to exploit the implicit preference context beneath the feedback, which is incorporated into the prediction process of users' grade scores to items. Finally, we develop a novel and generic transfer learning solution, i.e., preference-aware transfer (PAT), which embodies several recent algorithms as parts of our solution and special cases. To verify our novel solution, we then conduct extensive empirical studies on two large and public datasets and find that our PAT performs significantly better than the state-of-the-art methods.

关键词： Collaboration Matrix decomposition Predictive models Data models Probabilistic logic Training Context modeling

来源：评论

学校读者我要写书评

暂无评论

Structural combinatorial of network information system of systems based on evolutionary optimization ***

TechRxiv

引用

TechRxiv 2020年

作者： Zhang, Tingting Lan, Yushi Song, Aiguo Liu, Kun Wang, Nan Computer and military software engineering PLA Army Engineering University Nanjing China National defense key laboratory China Electronics Technology Group Corporation Nanjing China College of Instrument Science and Engineering Southeast University Nanjing China College of Command and Control Engineering PLA Army Engineering University Nanjing China

The network information system is a military information network system with evolution characteristics. Evolution is a process of replacement between disorder and order, chaos and equilibrium. Given that the concept of evolution originates from biological systems, in this article, the evolution of network information architecture is analyzed by genetic algorithms, and the network information architecture is represented by chromosomes. Besides, the genetic algorithm is also applied to find the optimal chromosome in the architecture space. The evolutionary simulation is used to predict the optimal scheme of the network information architecture and provide a reference for system construction. © 2020, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on API-Misuse Bugs in Open-Source C Programs

An Empirical Study on API-Misuse Bugs in Open-Source C Progr...

引用

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： Zuxing Gu Jiecheng Wu Jiaxiang Liu Min Zhou Ming Gu School of Software Tsinghua University China College of Computer Science & Software Engineering Shenzhen University China

Today, large and complex software is developed with integrated components using application programming interfaces (APIs). Correct usage of APIs in practice presents a challenge due to implicit constraints, such as call conditions or call orders. API misuse, i.e., violation of these constraints, is a well-known source of bugs, some of which can cause serious security vulnerabilities. Although researchers have developed many API-misuse detectors over the last two decades, recent studies show that API misuses are still prevalent. In this paper, we provide a comprehensive empirical study on API-misuse bugs in open-source C programs. To understand the nature of API misuses in practice, we analyze 830 API-misuse bugs from six popular programs across different domains. For all the studied bugs, we summarize their root causes, fix patterns and usage statistics. Furthermore, to understand the capabilities and limitations of state-of-the-art static analysis detectors for API-misuse detection, we develop APIMU4C, a dataset of API-misuse bugs in C code based on our empirical study results, and evaluate three widely-used detectors on it qualitatively and quantitatively. We share all the findings and present possible directions towards more powerful API-misuse detectors.

关键词： computer bugs Detectors Static analysis Open source software Benchmark testing Libraries

来源：评论

学校读者我要写书评

暂无评论

Adaptive Transfer Learning for Heterogeneous One-Class Collaborative Filtering

Adaptive Transfer Learning for Heterogeneous One-Class Colla...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiancong Chen Weike Pan Zhong Ming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In this paper, we study a recent and important recommendation problem called heterogeneous one-class collaborative filtering (HOCCF), where we have two different types of one-class feedback, i.e., a set of browses and a set of purchases, for preference learning. Previous methods exploit the browses and purchases by extending some existing methods on modeling homogeneous one-class feedback in an integrative or sequential manner. However, an integrative method may be of high complexity in model training due to the expanded prediction rule, and a sequential method is of inconvenience in deployment because more than one parametric models have to be maintained. In this paper, we convert the HOCCF problem to an adaptive transfer learning task, where we first model browses via a factorization model from a perspective of the role of browser, and then adaptively refine the learned model parameters via purchases from a perspective of the dependent role of purchaser. Based on this conversion, we design a novel solution called role-based adaptive factorization (ROAF), and then derive two specific variants with pairwise preference learning and pointwise preference learning. Finally, we conduct extensive empirical studies on two large datasets, and find that our ROAF is a very promising solution in terms of recommendation accuracy, besides its convenience of one single parametric model in deployment.

关键词： Browsers Adaptation models Parametric statistics Training Bayes methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Sequence-Aware Factored Mixed Similarity Model for Next-Item Recommendation

Sequence-Aware Factored Mixed Similarity Model for Next-Item...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Liulan Zhong Jing Lin Weike Pan Zhong Ming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Sequence-aware next-item recommendation has recently been studied because of the noteworthy usefulness of the sequential information integrated into recommendation algorithms. Following the development thread of sequential recommendation methods, especially the factored Markov chains segment, we propose a novel sequence-aware factored mixed similarity model (S-FMSM) based on a well-designed fusing similarity model with factored high-order Markov chains (i.e., Fossil). Unlike the baseline methods that model the general representation and the sequential representation in two divided factorization components, we use a factored mixed similarity model that unites the general similarity and the sequential relationship between two successive items for their sequential representation learning. Experiments on six datasets show that our newly introduced general similarity can notably improve the results of the recommended ranking lists. And a study on tuning the prior tradeoff parameter indicates the importance of the general similarity on different datasets.

关键词： Markov processes Linear programming Probability Big Data Collaboration Feeds Conferences

来源：评论

学校读者我要写书评

暂无评论

Symmetric Learning Data Augmentation Model for Underwater Target Noise Data Expansion

引用

computers, Materials & Continua 2018年第12期57卷 521-532页

作者： Ming He Hongbin Wang Lianke Zhou Pengming Wang Andrew Ju College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China College of Computer and Information Engineering Heilongjiang University of Science and TechnologyHarbin150022China School of Software and Microelectronics Harbin University of Science and TechnologyHarbin150080China Department of Computer Science and Information Systems University of LimerickLimerickIreland

An important issue for deep learning models is the acquisition of training of *** abundant data from a real production environment for training,deep learning models would not be as widely used as they are ***,the cost of obtaining abundant real-world environment is high,especially for underwater *** is more straightforward to simulate data that is closed to that from real *** this paper,a simple and easy symmetric learning data augmentation model(SLDAM)is proposed for underwater target radiate-noise data expansion and *** SLDAM,taking the optimal classifier of an initial dataset as the discriminator,makes use of the structure of the classifier to construct a symmetric generator based on antagonistic *** generates data similar to the initial dataset that can be used to supplement training data *** model has taken into consideration feature loss and sample loss function in model training,and is able to reduce the dependence of the generation and expansion on the feature *** verified that the SLDAM is able to data expansion with low calculation *** results showed that the SLDAM is able to generate new data without compromising data recognition accuracy,for practical application in a production environment.

关键词： Data augmentation symmetric learning data expansion underwater target noise data

来源：评论

学校读者我要写书评

暂无评论

Delay-Tolerant Rendezvous-Based Data Collection for Target Tracking in Large-Scale Wireless Sensor Networks with UGV 1

引用

5th International Conference on Artificial Intelligence and Security, ICAIS 2019

作者： Zhang, Jian Xu, Jiang Wang, Tianbao College of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Engineering Center of Network Monitoring Nanjing210044 China School of Electrical and Information Engineering Jiangsu University Zhenjiang212013 China

ISBN: (数字)9783030242657

ISBN: (纸本)9783030242640

Energy efficiency receives significant attention in wireless sensor networks. In this paper, a UGV is employed as an energy-efficient solution to prolong the network lifetime in target tracking. Data collection strategies for target tracking are investigated including the amount of data and the transmitted distances. For contributed data, the quantization technology is exploited for energy efficiency. Considering the uncertainty of sensing data, we determine a group from intra-cluster members to gather data. And then, we formulate our design a selection optimization problem, maximizing the utilization of the quality of contributed data using information matrix. As a result, we develop an optimization algorithm named rendezvous-based data collection (RDC). Furthermore, two stages of data collection for target tracking are analyzed with a UGV. Simulations verify that the proposed scheme achieves network energy saving as well as energy balance in the framework of target tracking. © 2019, Springer Nature Switzerland AG.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

In this paper, we focus on a recently studied problem in recommendation called heterogeneous one-class collaborative filtering (HOCCF), which consists of different types of feedback, e.g., target feedback and auxiliary feedback. The main challenge of HOCCF is how to make good use of the large-scale and ambiguous auxiliary feedback to assist the task of learning users'true preferences. Inspired by a recent method that jointly learns the similarity among items associated with the target feedback and auxiliary feedback in a transfer learning manner, we further extend this method by learning additional similarity among users for better modeling users' preferences. Specifically, we jointly learn the item-based similarity and user-based similarity by leveraging the target feedback and auxiliary feedback, and then aggregate the dual similarity into one single prediction rule for estimating users' preferences, which is thus termed as dual similarity learning model (DSLM). Extensive empirical studies on three public datasets show that our DSLM with dual similarity is more effective in terms of recommendation accuracy, demonstrating that our method strikes a good balance between the item-based similarity and user-based similarity.

关键词： Collaboration IP networks Aggregates Big Data Predictive models Indexes Uncertainty

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：