检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhang, Wenchao Fu, Chong Xie, Haoyu Zhu, Mai Tie, Ming Chen, Junxin School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Science and Technology on Space Physics Laboratory Beijing100076 China College of Medicine and Biological Information Engineering Northeastern University Shenyang110819 China

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing network resource allocation with graph pointer neural network in large-scale AI systems

引用

Digital Communications and networks 2024年

作者： Peiying Zhang Yilin Li Athanasios V. Vasilakos Konstantin Igorevich Kostromitin Jianyong Zhang Mohsen Guizani Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an 710071 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250013 China Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam 31441 Saudi Arabia Department of Physics of Nanoscale Systems South Ural State University Chelyabinsk 454080 the Russian Federation Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Key Lab of All Optical Network and Advanced Telecommunication of EMC Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi 999041 United Arab Emirates

For increasingly complex communication demands of large-scale AI communication systems, the Space-Air-Ground Integrated network (SAGIN) better caters to demands but also raises concerns about resource scarcity and diversity. This paper innovatively combines Graph Pointer Neural networks (GPNN) and Reinforcement Learning (RL) to enhance resource allocation efficiency. The method leverages the advantages of GPNN in handling graph data and RL in optimizing decisions in dynamic environments. It also targets the optimization goal of maximizing resource allocation while minimizing deployment latency. This paper begins by modeling SAGIN and elucidating the SAGIN logical architecture based on Software-defined networking (SDN). Subsequently, it introduces an SFC deployment algorithm aimed at joint optimization of resource allocation and latency. The algorithm leverages GPNN and RL to deploy virtual nodes and links, with the goal of optimizing resource allocation and deployment latency. Experiment findings conclusively demonstrate that the efficacy of proposed algorithm in effectively weighing limited heterogeneous resources and minimum mapping delay. Notably, when compared to three other SFC mapping algorithms MLRL, NFVdeep, and RL, the proposed algorithm consistently outperforms them, with an average improvement of 10.17% in long-term average reward/cost, 11.21% in link resource utilization ratio, 15.34% in node resource utilization ratio, and 16.38% in acceptance ratio.

关键词： Space-air-ground integrated network Topological structure Reinforcement learning Service function chain Graph pointer neural network

来源：评论

学校读者我要写书评

暂无评论

A Slice-Guided Method of Indoor Scene Structure Retrieving 12th

A Slice-Guided Method of Indoor Scene Structure Retrieving

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Wang, Lijuan Wang, Yinghui Wang, Ningna Ning, Xiaojuan Lv, Ke Huang, Liangyi Xi’an University of Technology South Jinhua Road no. 5 Xi’an710032 China Xi’an Technology University Mid Xuefu Road no. 2 Xi’an710021 China Shaanxi Key Laboratory of Network Computing and Security Technology South Jinhua Road no. 5 Xi’an710032 China *** B.V. Vijzelstraat 66-80 Amsterdam1017HL Netherlands Institute of Automation Chinese Academy of Sciences Beijing China School of Engineering and Applied Science George Washington University Washington DC20052 United States

ISBN: (纸本)9783030237110

The structure information of indoor scene is necessary for a robot who works in a room. In order to achieve structure of an indoor scene, a slice-guided method of indoor scene structure retrieving is proposed in this paper. We present a slicing based approach that transforms three-dimensional (3D) segmentations into two-dimensional (2D) segmentation and segments different kinds of primitive shapes while keeping the global topology structure of the indoor scene. The global topology structure is represented by a graph. The graph is compared with the given indoor scene template. The matched objects and the topology relation between them are finally presented. Our experiment results show that the proposed method performs well on several typical indoor scenes, even if some data are missing. © 2019, Springer Nature Switzerland AG.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Exploiting Meta-Path with Attention Mechanism for Fine-Grained User Location Prediction in LBSNs 3

Exploiting Meta-Path with Attention Mechanism for Fine-Grain...

引用

2019 3rd International Conference on Data Mining, Communications and Information technology, DMCIT 2019

作者： Wang, Zhixiao Yan, Wenyao Wang, Wendong Gao, Ang Yu, Lei Yang, Shaobo Nie, GaoYang School of Computer Science and Engineering Xi'an University of Technology Xi'an710048 China Telematics Group University of Goettingen Goettingen37077 Germany Shaanxi Key Laboratory of Network Computing and Security Xi'an710048 China School of Electronic and Information Engineering Xi'an Jiaotong University Xi'an710048 China College of Xi'an Innovation Yan'an University Xi'an710100 China Yan'an University Yan'an716000 China National Satellite Meteorological Center China Meteorological Administration Beijing100081 China

Based on the huge volumes of user check-in data in LBSNs, users' intrinsic mobility patterns can be well explored, which is fundamental for predicting where a user will visit next given his/her historical check-in records. As there are various types of nodes and interactions in LBSNs, they can be treated as Heterogeneous Information network (HIN) where multiple semantic meta-paths can be extracted. Inspired by the recent success of meta-path context based embedding techniques in HIN, in this paper, we design a deep neural network framework leveraging various meta-path contexts for fine-grained user location prediction. Experimental results based on two real-world LBSN datasets demonstrate the best effectiveness of the proposed approach using various evaluation metrics than others. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Slice-Based Window Detection from Scene Point Clouds

Slice-Based Window Detection from Scene Point Clouds

引用

International Conference on Virtual Reality and Visualization (ICVRV)

作者： Wen Hao Yinghui Wang Wei Liang Xiaojuan Ning Ye Li Institute of Computer Science and Engineering Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China

ISBN: (纸本)9781538684986;9781538684979

In this paper, we propose a comprehensive strategy to detect the windows from scene point clouds. First, the planar points are extracted after computing the dimensionality structure of each point. The planar points are then grouped into clusters based on the normal direction and distance between points. Next, the building walls are extracted from the scene point clouds according to a collection of characteristics such as surface area, normal direction, and topological relationship. Finally, the building facade is sliced both horizontally and vertically. A slice-based algorithm based on the point number is proposed to locate the windows. The experimental results demonstrate that our method can detect the window location quickly and effectively.

关键词： Windows Three-dimensional displays Microsoft Windows Two dimensional displays Clustering algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Joint object contour points and semantics for instance segmentation

arXiv

引用

arXiv 2020年

作者： Zhang, Wenchao Fu, Chong Zhu, Mai Cao, Lin Tie, Ming Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China Science and Technology on Space Physics Laboratory Beijing100076 China School of Computer Science University of Auckland New Zealand

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation process when making instance segmentation datasets, in this paper, we propose Mask Point R-CNN aiming at promoting the neural network’s attention to the object boundary. Specifically, we innovatively extend the original human keypoint detection task to the contour point detection of any object. Based on this analogy, we present an contour point detection auxiliary task to Mask R-CNN, which can boost the gradient flow between different tasks by effectively using feature fusion strategies and multi-task joint training. As a consequence, the model will be more sensitive to the edges of the object and can capture more geometric features. Quantitatively, the experimental results show that our approach outperforms vanilla Mask R-CNN by 3.8% on Cityscapes dataset and 0.8% on COCO dataset. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An attribute-based encryption scheme with LSSS key-policy from lattices

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and computing 2018年 613卷 217-230页

作者： Liu, Lihua Wang, Shangping Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an University of Technology Xi’an710054 China School of Mathematics and Computer Science Shaanxi University of Technology HanzhongShaanxi723001 China

ISBN: (纸本)9783319607436

A new attribute-based encryption scheme (ABE) from lattices with Linear Secret Sharing Scheme (LSSS) key-policy is presented. In the new scheme, the key of an attribute under an access policy represented by LSSS is generated by the use of the sample-pre algorithm on lattices. Every attribute has its own authority, and the private key of each attribute under an access policy is produced by its own authority alone. The new scheme has the advantage of fine-grained access control, and also could support multi-authority attribute management, thus it facilitates the practical management of attribute encryption system. The security of the new scheme is proved in the selective-attribute attack model under learning with errors (LWE) assumption, and the security parameter selecting is discussed in detail. © 2018, Springer International Publishing AG.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Novel Color Orthogonal Moments-Based Image Representation and Recognition

Research Square

引用

Research Square 2020年

作者： He, Bing Liu, Jun Yang, Tengfei Xiao, Bin Peng, Yanguo School of Physics and Electrical Engineering Weinan Normal University Weinan714000 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts & Telecommunications Xi’an710121 China School of Computer Science and Technology Weinan Normal University Weinan714000 China School of Cyberspace Security Xi’an University of Posts & Telecommunications Xi’an710121 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China School of Computer Science and Technology Xidian University Xi’an710071 China

Inspired by quaternion algebra and the idea of fractional-order transformation, we propose a new set of quaternion fractional-order generalized Laguerre orthogonal moments (QFr-GLMs) based on fractional-order generalized Laguerre polynomials. Firstly, the proposed QFr-GLMs are directly constructed in Cartesian coordinate space, avoiding the need for conversion between Cartesian and polar coordinates;therefore, they are better image descriptors than circularly orthogonal moments constructed in polar coordinates. Moreover, unlike the latest Zernike moments based on quaternion and fractional-order transformations, which extract only the global features from color images, our proposed QFr-GLMs can extract both the global and local color features. This paper also derives a new set of invariant color-image descriptors by QFr-GLMs, enabling geometric-invariant pattern recognition in color images. Finally, the performances of our proposed QFr-GLMs and moment invariants were evaluated in simulation experiments of correlated color images. Both theoretical analysis and experimental results demonstrate the value of the proposed QFr-GLMs and their geometric invariants in the representation and recognition of color images. © 2020, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Trust-PBFT: A PeerTrust-Based Practical Byzantine Consensus Algorithm

Trust-PBFT: A PeerTrust-Based Practical Byzantine Consensus ...

引用

International Conference on networking and network Applications (NaNA)

作者： Wei Tong Xuewen Dong Jiawei Zheng Shaanxi Key Laboratory of Network and System Security Xidian University Xi'an China School of Cyber Engineering Xidian University Xi'an China School of Computer Science and Technology Xidian University Xi'an China

ISBN: (数字)9781728126296

ISBN: (纸本)9781728126302

Blockchain is becoming increasingly popular, while the performance problems have confused its implementation, especially the limited size of the distributed network. In this paper, we propose Trust-PBFT, a combination of PeerTrust P2P trust calculation model and PBFT consensus algorithm. We first introduce PeerTrust to evaluate the trustworthy of the nodes that qualify as participants of PBFT, which replaces the original that all nodes participate in so that the size of the distributed network can be expanded arbitrarily. Besides, in order to simplify the structure of block storage, particularly the storage of the feedbacks of transaction used to calculate trust value of nodes, we design a tri-chain architecture to store accounts, transactions and feedbacks in three blockchains, respectively. Moreover, due to the introduction of PeerTrust, a weak benefit is to improve the fault tolerance performance efficiently. Finally, we design simulation experiments to evaluate the fault tolerance performance and scalability of Trust-PBFT.

关键词： Peer-to-peer computing Fault tolerance Fault tolerant systems Fabrics Computer architecture Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Transferring knowledge distillation for multilingual social event detection

arXiv

引用

arXiv 2021年

作者： Ren, Jiaqian Peng, Hao Jiang, Lei Wu, Jia Tong, Yongxin Wang, Lihong Bai, Xu Wang, Bo Yang, Qiang Institute of Information Engineering Chinese Academy of Sciences The School of Cyber Security University of Chinese Academy of Sciences Beijing100041 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China The School of Cyber Science and Technology Beihang University Beijing100083 China Institute of Information Engineering Chinese Academy of Sciences Beijing100041 China The Department of Computing Macquarie University Sydney Australia The State Key Laboratory of Software Development Environment The School of Computer Science and Engineering Beihang University Beijing100083 China The National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong AI Group WeBank Co. Ltd. China

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the more common multilingual settings and lesser-spoken languages relatively unexplored. Thus, we present a GNN that incorporates cross-lingual word embeddings for detecting events in multilingual data streams. The first exploit is to make the GNN work with multilingual data. For this, we outline a construction strategy that aligns messages in different languages at both the node and semantic levels. Relationships between messages are established by merging entities that are the same but are referred to in different languages. Non-English message representations are converted into English semantic space via the cross-lingual word embeddings. The resulting message graph is then uniformly encoded by a GNN model. In special cases where a lesser-spoken language needs to be detected, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce. © 2021, CC BY.

关键词： Embeddings

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：