检索结果-内蒙古大学图书馆

REGINA-Reasoning graph convolutional networks in Human Action Recognition

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2021年 16卷 5442-5451页

作者： Degardin, Bruno Lopes, Vasco Proenca, Hugo Univ Beira Interior Inst Telecomunicacoes IT Dept Comp Sci P-6201001 Covilha Portugal Univ Beira Interior NOVA LINCS P-6201001 Covilha Portugal

It is known that the kinematics of the human body skeleton reveals valuable information in action recognition. Recently, modeling skeletons as spatio-temporal graphs with graph convolutional networks (GCNs) has been reported to solidly advance the state-of-the-art performance. However, GCN-based approaches exclusively learn from raw skeleton data, and are expected to extract the inherent structural information on their own. This paper describes REGINA, introducing a novel way to REasoning graph convolutional networks IN Human Action recognition. The rationale is to provide to the GCNs additional knowledge about the skeleton data, obtained by handcrafted features, in order to facilitate the learning process, while guaranteeing that it remains fully trainable in an end-to-end manner. The challenge is to capture complementary information over the dynamics between consecutive frames, which is the key information extracted by state-of-the-art GCN techniques. Moreover, the proposed strategy can be easily integrated in the existing GCN-based methods, which we also regard positively. Our experiments were carried out in well-known action recognition datasets and enabled to conclude that REGINA contributes for solid improvements in performance when incorporated to other GCN-based approaches, without any other adjustment regarding the original method. For reproducibility, the REGINA code and all the experiments carried out will be publicly available at https://***/DegardinBruno.

关键词： Skeleton Convolution Spatiotemporal phenomena Kernel Feature extraction convolutional codes Joints Action recognition graph convolutional networks human behavior analysis skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

HesGCN: Hessian graph convolutional networks for semi-supervised classification

引用

INFORMATION SCIENCES 2020年 514卷 484-498页

作者： Fu, Sichao Liu, Weifeng Tao, Dapeng Zhou, Yicong Nie, Liqiang China Univ Petr East China Coll Control Sci & Engn Qingdao 266580 Peoples R China Yunnan Univ Sch Informat Sci & Engn Kunming 650091 Yunnan Peoples R China Univ Macau Fac Sci & Technol Macau 999078 Peoples R China Shandong Univ Sch Comp Sci & Technol Qingdao 266237 Peoples R China

Manifold or local geometry of samples have been recognized as a powerful tool in machine learning areas, especially in the graph-based semi-supervised learning (GSSL) problems. Over recent decades, plenty of manifold assumption-based SSL algorithms (MSSL) have been proposed including graph embedding and graph regularization models, where the objective is to utilize the local geometry of data distributions. One of most representative MSSL approaches is graph convolutional networks (GCN), which effectively generalizes the convolutional neural networks to deal with the graphs with the arbitrary structures by constructing and fusing the Laplacian-based structure information. However, the null space of the Laplacian remains unchanged along the underlying manifold, it causes the poor extrapolating ability of the model. In this paper, we introduce a variant of GCN, i.e. Hessian graph convolutional networks (HesGCN). In particularly, we get a more efficient convolution layer rule by optimizing the one-order spectral graph Hessian convolutions. In addition, the spectral graph Hessian convolutions is a combination of the Hessian matrix and the spectral graph convolutions. Hessian gets a richer null space by the existence of its two-order derivatives, which can describe the intrinsic local geometry structure of data accurately. Thus, HesGCN can learn more efficient data features by fusing the original feature information with its structure information based on Hessian. We conduct abundant experiments on four public datasets. Extensive experiment results validate the superiority of our proposed HesGCN compared with many state-of-the-art methods. (C) 2019 Elsevier Inc. All rights reserved.

关键词： graph convolutional networks Hessian Semi-supervised learning Manifold assumption

来源：评论

学校读者我要写书评

暂无评论

Dependency-enhanced graph convolutional networks for aspect-based sentiment analysis

引用

NEURAL COMPUTING & APPLICATIONS 2023年第19期35卷 14195-14211页

作者： Zhao, Meng Yang, Jing Shang, Fanshu Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China

Aspect-based sentiment analysis aims to extract aspect and opinion terms, and identify the sentiment polarities for such terms. The majority of research has proposed effective methods in individual subtasks, and some multi-task learning models have been designed to deal with combining two subtasks, such as extracting aspect terms and opinions in pairs. Recently, there have been some studies on triple extraction tasks that attempt to simultaneously extract target terms (aspects, opinions) and sentiment polarities from a sentence. However, these studies ignore the directional dependency relations between terms and context, and the intrinsic dependence between these terms has not been well exploited. In this paper, we propose a novel dependency-enhanced graph convolutional network (DE-GCN) for multi-variate extraction tasks. We re-integrate the directional dependency relations in the graph convolution to reconstruct the time-series information representation. In addition, we construct a dependency aggregator to enhance dependency relations between contexts. We conduct experiments on extensive experiments and comparisons on these subtasks. Experimental results on four datasets show the effectiveness of our proposed model.

关键词： Aspect-based sentiment analysis graph convolutional networks Dependency syntactic tree Aspect sentiment triple extraction

来源：评论

学校读者我要写书评

暂无评论

Leveraging graph convolutional networks for semi-supervised fault diagnosis of HVAC systems in data-scarce contexts

引用

Building Simulation 2023年第8期16卷 1499-1517页

作者： Cheng Fan Yiwen Lin Marco Savino Piscitelli Roberto Chiosa Huilong Wang Alfonso Capozzoli Yuanyuan Ma Key Laboratory for Resilient Infrastructures of Coastal Cities Ministry of EducationShenzhen UniversityShenzhenChina Sino-Australia Joint Research Center in BIM and Smart Construction Shenzhen UniversityShenzhenChina College of Civil and Transportation Engineering Shenzhen UniversityShenzhenChina Department of Energy TEBE research groupBAEDA LabPolitecnico di TorinoTorinoItaly

The continuous accumulation of operational data has provided an ideal platform to devise and implement customized data analytics for smart HVAC fault detection and *** practice,the potentials of advanced supervised learning algorithms have not been fully realized due to the lack of sufficient labeled *** tackle such data challenges,this study proposes a graph neural network-based approach to effectively utilizing both labeled and unlabeled operational data for optimum *** specifically,a graph generation method is proposed to transform tabular building operational data into association graphs,based on which graph convolutions are performed to derive useful insights for fault *** experiments have been designed to evaluate the values of the methods *** datasets on HVAC air-side operations have been used to ensure the generalizability of results *** data scenarios,which vary in training data amounts and imbalance ratios,have been created to comprehensively quantify behavioral patterns of representative graph convolution networks and their *** research results indicate that graph neural networks can effectively leverage associations among labeled and unlabeled data samples to achieve an increase of 2.86%–7.30%in fault classification accuracies,providing a novel and promising solution for smart building management.

关键词： fault detection and diagnosis graph convolutional networks semi-supervised learning HVAC systems machine learning

来源：评论

学校读者我要写书评

暂无评论

Dual-aligned unsupervised domain adaptation with graph convolutional networks

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第11期81卷 14979-14997页

作者： Wu, Fei Wei, Pengfei Gao, Guangwei Hu, Chang-Hui Ge, Qi Jing, Xiao-Yuan Nanjing Univ Posts & Telecommun Coll Automat Nanjing Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing Peoples R China Natl Inst Informat Digital Content & Media Sci Res Div Tokyo Japan Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing Peoples R China Wuhan Univ Sch Comp Wuhan Peoples R China

In recent years, graph convolutional networks have achieved great success in unsupervised domain adaptation task. Although these works make effort to reduce the distribution difference between domains, they do not take into account the issue of distribution difference reduction in the class level. In this paper, we propose a Dual-aligned Unsupervised Domain Adaptation with graph convolutional networks (DUDA-GCN) framework to align domain distributions and the distributions of two domains corresponding to each category jointly. The framework contains two parts, i.e., a cross-domain feature extractor and a dual aligner of distribution. The former adopts a two-channel sub-network, with each channel to fully explore the relation among within-domain samples, based on GCN with shared weights to learn common feature representations of two domains. The dual aligner contains an adversarial domain discriminator and a category aligner, where the domain discriminator is designed to reduce the distribution difference across domains. A pseudo-label generator is designed to generate pseudo-labels for unlabeled samples. With the generated pseudo-labels of unlabeled samples and the real labels of labeled samples, the category aligner aligns the sample distributions across domains of the same category. Extensive empirical evaluation on three real-world datasets shows that DUDA-GCN can perform better than state-of-the-art related domain adaptation methods.

关键词： Unsupervised domain adaptation Dual alignment graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection

引用

NEUROCOMPUTING 2021年 444卷 332-337页

作者： Luo, Weixin Liu, Wen Gao, Shenghua ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

This paper focus on analyzing graph connection of human joints for skeleton based video anomaly detection, which is more effective and efficient than those image-level reconstruction based or prediction based methods that may be affected by complex background. Specifically, we propose a spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection. In other words, we build a normal graph describing graph connection of joints in normal data, where joints of abnormal events will be outliers of this graph. To our knowledge, this is the first work to apply graph convolutional networks on skeleton-based video anomaly detection. Experiments show that our proposed normal graph achieves the-state-of-art performance, compared to those image-level reconstruction-based or prediction-based methods, as well as RNN based methods upon joints. (c) 2020 Published by Elsevier B.V.

关键词： graph convolutional networks Anomaly detection Skeleton

来源：评论

学校读者我要写书评

暂无评论

Towards efficient allocation of graph convolutional networks on hybrid computation-in-memory architecture

引用

Science China(Information Sciences) 2021年第6期64卷 112-125页

作者： Jiaxian CHEN Guanquan LIN Jiexin CHEN Yi WANG College of Computer Science and Software Engineering Shenzhen University

graph convolutional networks(GCNs) have been applied successfully in social networks and recommendation systems to analyze graph data. Unlike conventional neural networks, GCNs introduce an aggregation phase, which is both computation-and memory-intensive. This phase aggregates features from the neighboring vertices in the graph, which incurs significant amounts of irregular data and memory *** emerging computation-in-memory(CIM) architecture presents a promising solution to alleviate the problem of irregular accesses and provide fast near-data processing for GCN applications by integrating both three-dimensional stacked CIM and general-purpose processing units in the system. This paper presents graph-CIM, which exploits the hybrid CIM architecture to determine the allocation of GCN ***-CIM models the GCN application process as a directed acyclic graph(DAG) and allocates tasks on the hybrid CIM architecture. It achieves fine-grained graph partitioning to capture the irregular characteristics of the aggregation phase of GCN applications. We use a set of representative GCN models and standard graph datasets to evaluate the effectiveness of graph-CIM. The experimental results show that graph-CIM can significantly reduce the processing latency and data-movement overhead compared with the representative schemes.

关键词： computation-in-memory graph convolutional networks hybrid architecture scheduling inference accelerator

来源：评论

学校读者我要写书评

暂无评论

Beyond Low-Pass Filtering: graph convolutional networks With Automatic Filtering

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第7期35卷 6687-6697页

作者： Wu, Zonghan Pan, Shirui Long, Guodong Jiang, Jing Zhang, Chengqi Univ Technol Sydney Australian Artificial Intelligence Inst Sydney NSW 2007 Australia Monash Univ Clayton Vic 3800 Australia Griffith Univ Sch Informat & Commun Technol Southport Qld 4222 Australia

graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the potentially useful middle and high frequency band of graph signals are ignored. Second, the bandwidth of existing graph convolutional filters is fixed. Parameters of a graph convolutional filter only transform the graph inputs without changing the curvature of a graph convolutional filter function. In reality, we are uncertain about whether we should retain or cut off the frequency at a certain point unless we have expert domain knowledge. In this paper, we propose Automatic graph convolutional networks (AutoGCN) to capture the full spectrum of graph signals and automatically update the bandwidth of graph convolutional filters. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form. Experimental results show that AutoGCN achieves significant improvement over baseline methods which only work as low-pass filters.

关键词： Convolution Laplace equations Bandwidth graph neural networks Fourier transforms High frequency Eigenvalues and eigenfunctions graph convolutional networks graph signal processing graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Combing Type-Aware Attention and graph convolutional networks for Event Detection

引用

Computers, Materials & Continua 2023年第1期74卷 641-654页

作者： Kun Ding Lu Xu Ming Liu Xiaoxiong Zhang Liu Liu Daojian Zeng Yuting Liu Chen Jin The Sixty-Third Research Institute National University of Defense TechnologyNanjing210007China Hunan Normal University Changsha410000China School of Computer&Software Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science University of ManchesterManchesterM139PLUK

Event detection(ED)is aimed at detecting event occurrences and categorizing *** task has been previously solved via recognition and classification of event triggers(ETs),which are defined as the phrase or word most clearly expressing event ***,current approaches require both annotated triggers as well as event types in training ***,triggers are non-essential in ED,and it is time-wasting for annotators to identify the“most clearly”word from a sentence,particularly in longer *** decrease manual effort,we evaluate event detectionwithout *** propose a novel framework that combines Type-aware Attention and graph convolutional networks(TA-GCN)for event ***,the task is identified as a multi-label classification *** first encode the input sentence using a novel type-aware neural network with attention ***,a graph convolutional networks(GCN)-based multilabel classification model is exploited for event *** results demonstrate the effectiveness.

关键词： Event detection information extraction type-aware attention graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Multiple graph convolutional networks for aspect-based sentiment analysis

引用

APPLIED INTELLIGENCE 2023年第10期53卷 12985-12998页

作者： Ma, Yuting Song, Rui Gu, Xue Shen, Qiang Xu, Hao Jilin Univ Coll Software Changchun 130012 Peoples R China Jilin Univ Sch Artificial Intelligence Changchun 130012 Peoples R China Univ Minho Dept Ind Elect P-4800058 Guimaraes Portugal Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

Aspect-based sentiment analysis is a fine-grained sentiment analysis task that identifies the sentiment polarity of different aspects in a sentence. Recently, several studies have used graph convolution networks (GCN) to obtain the relationship between aspects and context words with the dependency tree of sentences. However, errors introduced by the dependency parser and the complexity and variety of sentence structures have led to incorrect predictions of sentiment polarity. Therefore, we propose a multiple GCN (MultiGCN) model to solve this problem. The proposed MultiGCN comprises a rational GCN (RGCN) to extract syntactic structure information of sentences, a contextual encoder to extract semantic content information of sentences, a common information extraction module to combine structure and content information, and a fusion mechanism that allows interaction among the aforementioned components. Further, we propose difference and similarity losses and combine them with traditional loss function to jointly minimize the difference between the values predicted by the model and those of the labels. The experimental results show that the prediction performance of our proposed method is more than that of the state-of-the-art models.

关键词： Aspect-based sentiment analysis graph convolutional networks Information extraction Fusion mechanism Loss function

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：