检索结果-内蒙古大学图书馆

Action recognition method based on multi-stream attention-enhanced recursive graph convolution

APPLIED INTELLIGENCE 2024年第20期54卷 10133-10147页

作者： Wang, Huaijun Bai, Bingqian Li, Junhuai Ke, Hui Xiang, Wei Xian Univ Technol Sch Comp Sci & Engn 5 South Jinhua Rd Xian 710048 Shaanxi Peoples R China Shaanxi Key Lab Network Comp & Secur Technol 5 South Jinhua Rd Xian 710048 Shaanxi Peoples R China La Trobe Univ Sch Comp Engn & Math Sci Melbourne 3086 Australia

Skeleton-based action recognition methods have become a research hotspot due to their robustness against variations in lighting, complex backgrounds, and viewpoint changes. Addressing the issues of long-distance joint associations and time-varying joint correlations in skeleton data, this paper proposes a Multi-Stream Attention-Enhanced Recursive graph convolution method for action recognition. This method extracts four types of features from the skeleton data: joints, bones, joint movements, and bone movements. It models the potential relationships between non-adjacent nodes through adaptive graph convolution and utilizes a long short-term memory network for recursive learning of the graph structure to capture the temporal correlations of joints. Additionally, a spatio-temporal channel attention module is introduced to enable the model to focus more on important joints, frames, and channel features, further improving performance. Finally, the recognition results of the four branches are fused at the decision level to complete the action recognition. Experimental results on public datasets (UTD-MHAD, CZU-MHAD) and a self-constructed dataset (KTH-Skeleton) demonstrate that the proposed method achieves accuracies of 94.65%, 95.01%, and 97.50%, respectively, fully proving the good performance of the method.

关键词： Skeleton data Multi-stream attention graph convolution Action recognition

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of fluorescence molecular tomography based on graph convolution networks

引用

JOURNAL OF OPTICS 2020年第4期22卷

作者： Li, Dongsheng Chen, Chunxiao Li, Jianfei Yan, Qiang Nanjing Univ Aeronaut & Astronaut Dept Biomed Engn Nanjing 211106 Peoples R China

Fluorescence molecular tomography (FMT) is a promising method for cancer detection and drug development. The ability to obtain accurate 3D distribution of fluorophores by FMT is mainly hindered by the difficulties in reconstruction. While conventional reconstruction methods were based on regularization, the emerging of graph convolution made it possible to implement the reconstruction processing by deep learning. Meanwhile, the graph convolution could make full use of the topological information of FMT data. In this paper, we proposed a deep graph convolution framework with ResNet-like architectures for FMT reconstruction, which could achieve reconstruction with fewer parameters and relatively high speed. Through simulation studies as well as experiments on animals, the results showed that our method significantly improved the reconstruction of fluorophores compared with traditional methods.

关键词： fluorescence molecular tomography deep learning graph convolution

来源：评论

学校读者我要写书评

暂无评论

A spectral graph convolution for signed directed graphs via magnetic Laplacian

引用

NEURAL NETWORKS 2023年 164卷 562-574页

作者： Ko, Taewook Choi, Yoonhyuk Kim, Chong -Kwon Seoul Natl Univ Seoul South Korea Korea Inst Energy Technol Naju South Korea

Signed directed graphs contain both sign and direction information on their edges, providing richer information about real-world phenomena compared to unsigned or undirected graphs. However, analyzing such graphs is more challenging due to their complexity, and the limited availability of existing methods. Consequently, despite their potential uses, signed directed graphs have received less research attention. In this paper, we propose a novel spectral graph convolution model that effectively captures the underlying patterns in signed directed graphs. To this end, we introduce a complex Hermitian adjacency matrix that can represent both sign and direction of edges using complex numbers. We then define a magnetic Laplacian matrix based on the adjacency matrix, which we use to perform spectral convolution. We demonstrate that the magnetic Laplacian matrix is positive semi-definite (PSD), which guarantees its applicability to spectral methods. Compared to traditional Laplacians, the magnetic Laplacian captures additional edge information, which makes it a more informative tool for graph analysis. By leveraging the information of signed directed edges, our method generates embeddings that are more representative of the underlying graph structure. Furthermore, we showed that the proposed method has wide applicability for various graph types and is the most generalized Laplacian form. We evaluate the effectiveness of the proposed model through extensive experiments on several real-world datasets. The results demonstrate that our method outperforms state-of-the-art techniques in signed directed graph embedding. (c) 2023 The Authors. Published by Elsevier Ltd.

关键词： graph convolution Spectral convolution Magnetic Laplacian Signed directed graphs Link sign prediction Link existence prediction

来源：评论

学校读者我要写书评

暂无评论

Topology -learnable graph convolution for skeleton -based action recognition

引用

PATTERN RECOGNITION LETTERS 2020年 135卷 286-292页

作者： Zhu, Guangming Zhang, Liang Li, Hongsheng Shen, Peiyi Shah, Syed Afaq Ali Bennamoun, Mohammed Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Murdoch Univ Dept Comp Sci & Software Engn Perth WA 6000 Australia Univ Western Australia Dept Comp Sci & Software Engn Perth WA 6000 Australia

graph convolutional networks (GCNs) generalize convolutional neural networks into irregular graph-like structures. Generally, graph topologies are set by hand and fixed over all layers. Handcrafted connections may not be optimal and cannot fully use the self-learning ability of deep learning. In this work, we explore a topology-learnable graph convolution for skeleton-based action recognition. Specifically, a spatial graph convolution can be decomposed into a feature learning component that evolves the features of each graph vertex, and a graph vertex fusion component in which the latent graph topologies can be learned adaptively. Different initialization strategies for the learnable fusion matrix are evaluated. Experimental results that are based on the spatial-temporal GCNs for skeleton-based action recognition, demonstrate that convolution can work on graphs like on images, even if only a specific fusion matrix initialization that uses adjacency matrices is applied. Moreover, the self-learning process can learn the latent topology of a graph beyond the handcrafted topology, thereby making graph convolution flexible and universal.

关键词： Action recognition graph convolution graph topology Skeleton

来源：评论

学校读者我要写书评

暂无评论

Multiscale Adjacency Matrix CNN: Learning on Multispectral LiDAR Point Cloud via Multiscale Local graph convolution

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 855-870页

作者： Yang, Jian Luo, Binhan Gan, Ruilin Wang, Ao Shi, Shuo Du, Lin China Univ Geosci Sch Geog & Informat Engn Wuhan 430074 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China

Multispectral LiDAR can rapidly acquire 3D and spectral information of objects, providing richer features for point cloud semantic segmentation. Despite the remarkable performance of existing graph neural networks in point cloud segmentation, extracting local features still poses challenges in multispectral LiDAR point cloud scenes due to the uneven distribution of geometric and spectral information. To address the prevailing challenges, cutting-edge research predominantly focuses on extracting multiscale local features, compensating for feature extraction shortcomings. Thus, we propose a multiscale adjacency matrix convolutional neural network (MS-AMCNN) for multispectral LiDAR point cloud segmentation. In the MS-AMCNN, a local adjacency matrix convolution module was first proposed to efficiently leverage the point cloud's topological relationships and perceive local geometric features. Subsequently, a multiscale feature extraction architecture was adopted to fuse local geometric features and utilize a global self-attention module to globally model the semantic features of multiscale. The network effectively captures global and local representative features of the point cloud by harnessing the capabilities of convolutional neural networks in local feature modeling and the self-attention mechanism in global semantic feature learning. Experimental results on the Titan dataset demonstrate that the proposed MS-AMCNN network achieves a promising multispectral LiDAR point cloud segmentation performance with an overall accuracy of 94.39% and a mean intersection over union (MIoU) of 86.57%. Compared with other state-of-the-art methods, such as DGCNN, which achieved an MIoU of 85.43%, and RandLA-net, with an MIoU of 85.20%, the proposed approach achieves optimal performance in segmentation.

关键词： Point cloud compression Feature extraction Laser radar Three-dimensional displays convolution Data mining convolutional neural networks Deep learning graph convolution multiscale structure multispectral LiDAR point cloud segmentation self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Elastic Embedding through graph convolution-based Regression for Semi-supervised Classification

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2021年第4期15卷 1–11页

作者： Dornaika, F. Univ Basque Country UPV EHU Manuel Lardizabal 1 San Sebastian 20018 Spain IKERBASQUE Fdn Bilbao Spain

This article introduces a scheme for semi-supervised learning by estimating a flexible non-linear data representation that exploits Spectral graph convolutions structure. Structured data are exploited in order to determine non-linear and linear models. The introduced scheme takes advantage of data-driven graphs at two levels. First, it incorporates manifold smoothness that is naturally encoded by the graph itself. Second, the regression model is built on the convolved data samples that are derived from the data and their associated graph. The proposed semi-supervised embedding can tackle the problem of over-fitting on neighborhood structures for image data. The proposed graph convolution-based Semi-supervised Embedding paves the way to new theoretical and application perspectives related to the non-linear embedding. Indeed, building flexible models that adopt convolved data samples can enhance both the data representation and the final performance of the learning system. Several experiments are conducted on six image datasets for comparing the introduced scheme with some state-of-the-art semi-supervised approaches. This empirical evaluation shows the effectiveness of the proposed embedding scheme.

关键词： Semi-supervised learning graph-based embedding elastic embedding graph convolution

来源：评论

学校读者我要写书评

暂无评论

Robust person re-identification via graph convolution networks

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第19期80卷 29129-29138页

作者： Kim, Guisik Shu, Dong Wook Kwon, Junseok Chung Ang Univ Sch Comp Sci & Engn Seoul South Korea

Person re-identification (re-id) aims to identity the same person over multiple cameras;it has been successfully applied to various computer vision applications as a fundamental method. Owing to the development of deep learning, person re-id methods, which typically use triplet networks based on triplet loss, have demonstrated great success. However, the appearances of people are similar and hence difficult to distinguish in many cases. Therefore, we present a novel graph convolution network and enhances traditional triplet loss functions. Our method defines reference, positive, and negative features for triplet loss as three vertices of a graph, respectively, and adjusts their mutual distance through learning. The method adopts graph convolutions efficiently, thereby affording low computational costs. Experimental results demonstrate that our method is superior to the baseline on the Market-1501 dataset. The proposed GCN-based triplet loss considerably contributes to improve re-identification methods quantitatively and qualitatively.

关键词： Person re-identification graph convolution

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal short-term traffic flow prediction model based on dynamical-learning graph convolution mechanism

引用

INFORMATION SCIENCES 2022年 611卷 522-539页

作者： Chen, Zhijun Lu, Zhe Chen, Qiushi Zhong, Hongliang Zhang, Yishi Xue, Jie Wu, Chaozhong Wuhan Univ Technol Intelligent Transportat Syst Res Ctr Wuhan 430063 Peoples R China Wuhan Univ Technol Sch Transportat & Logist Engn Wuhan 430063 Peoples R China Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Wuhan Univ Technol Sch Management Wuhan 430070 Peoples R China Wuhan Univ Technol Res Inst Digital Governance & Management Decis In Wuhan 430070 Peoples R China Delft Univ Technol Fac Technol Policy & Management Safety & Secur Sci Grp S3G NL-2628 BX Delft Netherlands

Short-term traffic flow prediction is a core branch of intelligent traffic systems (ITS) and plays an important role in traffic management. The graph convolution network (GCN) is widely used in traffic prediction models to efficiently handle the graphical structural data of road networks. However, the influence weights among different road sections are usually distinct in real life and are difficult to analyze manually. The traditional GCN mechanism, which relies on a manually set adjacency matrix, is unable to dynamically learn such spatial patterns during training. To address this drawback, this study proposes a novel location graph convolutional network (location-GCN). The location-GCN solves this problem by adding a new learnable matrix to the GCN mechanism, using the absolute value of this matrix to represent the distinct influence levels among different nodes. Subsequently, long short-term memory (LSTM) is employed in the proposed traffic prediction model. Moreover, trigonometric function encoding was used in this study to enable the short-term input sequence to convey long-term periodic information. Finally, the proposed model was compared with the baseline models and evaluated on two real-world traffic flow datasets. The results show that our model is more accurate and robust than the other representative traffic prediction models. (C) 2022 Elsevier Inc. All rights reserved.

关键词： Short-term traffic flow prediction graph convolution Intelligent connected transportation Deep learning Group vehicle movement prediction

来源：评论

学校读者我要写书评

暂无评论

Contrastive graph convolution Network With Skip Connections for Few-Shot Hyperspectral Image Classification

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷

作者： Liu, Chun Dong, Ao Dong, Dongmei Li, Zheng Yang, Wei Han, Zhigang Guo, Jianzhong Henan Univ Sch Comp & Informat Engn Henan Key Lab Big Data Anal & Proc Henan Engn Lab Spatial Informat Proc Kaifeng 450046 Peoples R China Henan Univ Henan Ind Technol Acad Spatio Temporal Big Data Zhengzhou 450046 Peoples R China Beijing Electromech Engn Inst Beijing 100074 Peoples R China Henan Univ Coll Geog & Environm Sci Zhengzhou 450046 Peoples R China

graph convolution networks (GCNs) have achieved impressive results for few-shot hyperspectral image (HSI) classification. However, current methods focus on migrating labels from support patches to query patches through graph convolution. Less attention has been paid to the patch features generated by graph convolution. This leads to that the methods cannot perceive the abnormal situation that the labels of two patches from different classes are correctly predicted but their features are also similar with each other. Moreover, current methods usually adopt multiple layers of graph convolution for label migration and have not distinguished the impact of different layers. This may result in that important information are submerged in the iterative convolution process. To address these issues, this letter proposes a contrastive graph convolution network with skip connection (CGCN-SC) for few-shot HSI classification. By following the supervised contrastive learning, the contrastive loss modules are proposed to constrain the relationship between the generated features of the patches. It is expected that while migrating labels from labeled patches to unlabeled ones, the generated features of patches from the same classes are close with each other and the features from different classes are far away. Moreover, the skip connection is proposed to be incorporated into the graph convolution network to allow high-level abstract information to be combined with low-level features that may be lost during graph convolution. Through extensive experiments, the proposed method has shown better performance when compared with a set of related methods. All the codes are available at github https://***/dongao11/CGCN.

关键词： convolution Feature extraction Hyperspectral imaging Task analysis Image classification convolutional neural networks Training Contrastive learning few-shot learning (FSL) graph convolution hyperspectral image (HSI) classification

来源：评论

学校读者我要写书评

暂无评论

Priori separation graph convolution with long-short term temporal modeling for skeleton-based action recognition

引用

APPLIED INTELLIGENCE 2024年第17-18期54卷 7621-7635页

作者： Zang, Tuo Tu, Jianfeng Duan, Mengran Chen, Zhipeng Cheng, Hao Jiang, Hanrui Zhao, Jiahui Liu, Lingfeng East China Jiaotong Univ Sch Informat Engn Nanchang 330013 Peoples R China Jiangxi Minxuan Intelligent Technol Co Ltd Nanchang 330096 Peoples R China

Human action recognition from skeleton motion sequences is widely applied in various fields such as virtual reality, human-computer interaction and kinematic rehabilitation. With the wide use of graph neural networks for extracting spatial features from skeleton anatomy connectivity, spatial-temporal extension of single graph models on human skeleton may improve the network performance. In this paper, we propose a priori separation graph convolution (PS-GCN) network composition with a priori mixed GCN by introducing a hypergraph representation of the skeleton spatial features, and a dynamic adaptive GCN to describe the respective graph model for each sample at each layer of the network of spatial features. For temporal feature analysis, a global attention unit is added to describe the long-term relationship. Moreover, a feature fusion structure is applied for short-term temporal features in the input of the network. The proposed model is evaluated on the NTU-RGB+D, NTU-RGB+D 120 and NW-UCLA datasets via a comprehensive ablative study. The results show that our model is comparable in accuracy to the state-of-the-art methods.

关键词： graph convolution Action recognition Skeleton information

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：