检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Hua, Yuncheng Li, Yuan-Fang Haffari, Gholamreza Qi, Guilin Wu, Tongtong School of Computer Science and Engineering Southeast University China Faculty of Information Technology Monash University Australia Southeast University Monash University Joint Research Institute China Key Laboratory of Computer Network and Information Integration Southeast University China

Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different types, harboring inherently different characteristics, e.g., difficulty level. This paper proposes a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions. Our method quickly and effectively adapts the meta-learned programmer to new questions based on the most similar questions retrieved from the training data. The meta-learned policy is then used to learn a good programming policy, utilizing the trial trajectories and their rewards for similar questions in the support set. Our method achieves state-of-the-art performance on the CQA dataset (Saha et al., 2018) while using only five trial trajectories for the top-5 retrieved questions in each support set, and meta-training on tasks constructed from only 1% of the training set. We have released our code at https://***/DevinJake/MRL-CQA. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Group whitening: Balancing learning efficiency and representational capacity

arXiv

引用

arXiv 2020年

作者： Huang, Lei Zhou, Yi Liu, Li Zhu, Fan Shao, Ling SKLSDE Institute of Artificial Intelligence Beihang University Beijing China MOE Key Laboratory of Computer Network and Information Integration Southeast University China Abu Dhabi United Arab Emirates

Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population statistics for inference can be avoided through group normalization (GN). This paper proposes group whitening (GW), which exploits the advantages of the whitening operation and avoids the disadvantages of normalization within mini-batches. In addition, we analyze the constraints imposed on features by normalization, and show how the batch size (group number) affects the performance of batch (group) normalized networks, from the perspective of model's representational capacity. This analysis provides theoretical guidance for applying GW in practice. Finally, we apply the proposed GW to ResNet and ResNeXt architectures and conduct experiments on the ImageNet and COCO benchmarks. Results show that GW consistently improves the performance of different architectures, with absolute gains of 1.02% ∼ 1.49% in top-1 accuracy on ImageNet and 1.82% ∼ 3.21% in bounding box AP on COCO. Copyright © 2020, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

An OpenCV-based Framework for Table information Extraction

An OpenCV-based Framework for Table Information Extraction

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Jiayi Yuan Hongye Li Meng Wang Ruyang Liu Chuanyou Li Beilun Wang College of Software Engineering Southeast University Nanjing China MOE Key Laboratory of Computer Network and Information Integration China Chien-Shiung Wu College Southeast University Nanjing China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Portable Document Format (PDF), as one of the most popular file format, is especially useful for educational documents such as text books, articles, or papers in which we can preserve the original graphic appearance and conveniently share online. Detecting and extracting information from tables in PDF files can provide a plethora of structural data to construct educational knowledge graphs. However, most of the existing methods rely on PDF parsing tools and natural language processing techniques, which generally require training samples and are frail in handling cross-page tables. In light of this, in this paper, we propose a novel OpenCV-based framework to extract the metadata and specific values from PDF tables. Specifically, we first highlight the visual outline of the tables. Then, we locate tables using horizontal and vertical lines and get the coordinates of tabular frames in each PDF page. Once the tables are successfully detected, for each table, we detect the cross-page scenarios and use the Optical Character Recognition (OCR) engine to extract the specific values in each table cell. Differing from other machine learning based methods, the proposed method can achieve table information extraction accurately without labeled data. We conduct extensive experiments on real-world PDF files. The results demonstrate that our approach can effectively deal with cross-page tables and only need 6.12 seconds on average to process a table.

关键词： Portable document format Data mining Image color analysis information retrieval Tools Metadata Optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning with Spike Neural networks for Traffic Sign Recognition

arXiv

引用

arXiv 2022年

作者： Xie, Kan Zhang, Zhe Li, Bo Kang, Jiawen Niyato, Dusit Xie, Shengli Wu, Yi The School of Automation Guangdong University of Technology Guangzhou510006 China The Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China The Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China The Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China The School of Data Science and Technology Heilongjiang University Harbin150080 China The Institute for Cryptology & Network Security Heilongjiang University Harbin150080 China School of Computer Science and Engineering Nanyang Technological University Singapore

With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collaborative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well. Copyright © 2022, The Authors. All rights reserved.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Control Task Assignment Algorithm based on sub-graph isomorphism

A Control Task Assignment Algorithm based on sub-graph isomo...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Feng Yu Xixian Li Huimin Zhang Li-e Wang College of computer science Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China Guangxi Key Lab of Multi-source Information Mining & Security Guilin China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

To enhance the controllability and trustworthiness of the Internet, a new network control architecture has been presented with control task extracted to the intra-domain control node and executed in distributed multi-domain cooperative style. The study on control task assigning approach plays a central role in this network control pattern and shares some features with virtual network mapping problem. Different from the previous heuristics-based algorithms, we designs a baseline assigning algorithm which tests if the control task request can be mapped to a sub-graph of substrate control network or not without control task migration. Subsequently, an extend version is described under task migration considered. Our experiment evaluations show the impact of parameters on the runtime and assigning accuracy rate.

关键词： Cloud computing Backtracking Runtime Heuristic algorithms Process control Big Data Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Secure Data Propagation in Edge-Cloud Orchestrated Computing Paradigms: Statistcs and Taxonomy

Secure Data Propagation in Edge-Cloud Orchestrated Computing...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Feng Yu Xixian Li Huimin Zhang Li-e Wang College of computer science Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China Guangxi Key Lab of Multi-source Information Mining &Security Guilin China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

Despite the importance of the secure data propagation in the edge-cloud orchestrated computing paradigms, to the best of our knowledge, there is lack of systematic and comprehensive review on this research topic. The purpose of this article is to provide a systematic literature survey on secure data propagation in edge-cloud orchestrated computing environment to examine the current technical achievements published between 2010 and February 2020. The brief contributions of the paper are as follows: (1)providing a comprehensive literature review of the secure data propagation approaches in the edge-cloud orchestrated computing paradigms, (2) designing a methodology for document retrieval and selection, (3) presenting analysis and comparison for main technique methods of secure data propagation in hybrid edge-cloud environment.

关键词： Systematics Bibliographies Taxonomy Big Data

来源：评论

学校读者我要写书评

暂无评论

Tigc-Net: Transformer-Improved Graph Convolution network for Spatio-Temporal Prediction

SSRN

引用

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learning

arXiv

引用

arXiv 2022年

作者： Ma, Chuan Li, Jun Wei, Kang Liu, Bo Ding, Ming Yuan, Long Han, Zhu Poor, H. Vincent Zhejiang Laboratory Hangzhou311121 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210096 China The Department of Computing Hong Kong Polytechnic University 999077 Hong Kong The University of Technology SydneyNSW2007 Australia Data61 CSIRO NSW2015 Australia The School of Computer Science Nanjing University of Science and Technology Nanjing210096 China The Department of Electrical and Computer Engineering The University of Houston HoustonTX77004 United States Department of Computer Science and Engineering Kyung Hee University Seoul Korea Republic of The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Motivated by the advancing computational capacity of distributed end-user equipment (UE), as well as the increasing concerns about sharing private data, there has been considerable recent interest in machine learning (ML) and artificial intelligence (AI) that can be processed on distributed UEs. Specifically, in this paradigm, parts of a ML process are outsourced to multiple distributed UEs. Then the processed information is aggregated on a certain level at a central server, which turns a centralized ML process into a distributed one, and brings about significant benefits. However, this new distributed ML paradigm raises new risks of privacy and security issues. In this paper, we provide a survey on the emerging security and privacy risks of distributed ML from a unique perspective of information exchange levels, which are defined according to the key steps of a ML process, i.e.: i) the level of pre-processed data, ii) the level of learning models, iii) the level of extracted knowledge and, iv) the level of intermediate results. We explore and analyze the potential of threats for each information exchange level based on an overview of the current state-of-the-art attack mechanisms, and then discuss the possible defense methods against such threats. Finally, we complete the survey by providing an outlook on the challenges and possible directions for future research in this critical area. Copyright © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Uncertain Ontology Embeddings

Uncertain Ontology Embeddings

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Khaoula Boutouhami Guilin Qi Qiu Ji Jiatao Zhang Huan Gao School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China School of Modern Posts & Institute of Modern Posts Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

Ontologies are an expressive power used as a crucial element to enrich knowledge graphs by their rich data and ontological concepts that are often necessary for logical inference. Recently, ontology embedding has gained increasing attention in real-world ontologies for its ability to learn sub-sumption axioms, unary and binary assertions in these ontologies, while maintaining some syntactic, semantic properties and deductive closures. In general, learning methods assume an ontology to be complete while there are different situations in which it can be excepted to be uncertain, for example when they are provided by human annotators in classification, or even missing. However, embedding such uncertain ontologies is typically ignored. In this paper, we propose a novel embedding approach, UOE, which can embed uncertain lightweight ontology encoded in DL-lite in order to better capture the relationships between the uncertainty and the ontologies in the semantic space. Experimental results show that our model can robustly learn representations of uncertain ontologies when evaluated on publicly available datasets used on machine learning benchmarks.

关键词： Training Uncertainty Semantics Ontologies Benchmark testing Syntactics Task analysis

来源：评论

学校读者我要写书评

暂无评论

4D-CBCT Reconstruction via Motion Compensataion Learning Induced Sparse Tensor Constraint 12

4D-CBCT Reconstruction via Motion Compensataion Learning Ind...

引用

12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

作者： Liu, Jin Kang, Yanqin Hu, Dianlin Chen, Yang College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781728148526

The challenge in 4D-CBCT reconstruction is the lacked of projections at each phase, which result in a reconstruction image full of streak artifacts and motion blurring with the conventional analytical algorithms. Aiming at improving the overall quality of 4D-CBCT images, we propose a motion compensation learning induced sparse tensor constraint reconstruction (MCL-STCR) method which tries to explore the high correlation in 4D-CBCT images for different phases. In this method, we additionally conduct motion compensation on the 4D-CBCT volume by using trained image motion compensation convolutional neural network (CNN). Then the compensated 4D-CBCT volume is viewed as a pseudostatic sequence, of which the sparse tensor constraint was imposed on. The cost function of proposed MCL-STCR is optimized by a variable splitting algorithm. Its comparison to other methods through simulated dynamic phantom and lung data experiments demonstrated that the proposed method can lead to a promising improvement of 4D-CBCT reconstruction. © 2019 IEEE.

关键词： Image reconstruction

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：