检索结果-内蒙古大学图书馆

Robust person re-identification via graph convolution networks

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

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

引用

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

A spectral graph convolution for signed directed graphs via magnetic Laplacian

引用

NEURAL NETWORKS 2023年第1期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

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

Ready for emerging threats to recommender systems? A graph convolution-based generative shilling attack

引用

INFORMATION SCIENCES 2021年 578卷 683-701页

作者： Wu, Fan Gao, Min Yu, Junliang Wang, Zongwei Liu, Kecheng Wang, Xu Chongqing Univ Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing 401331 Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing 401331 Peoples R China Univ Queensland Sch Informat Technol & Elect Engn St Lucia Qld 4072 Australia Univ Reading Infomat Res Ctr Henley Business Sch Reading RG6 6UD Berks England Chongqing Univ Sch Mech Engn Chongqing 400044 Peoples R China

To explore the robustness of recommender systems, researchers have proposed various shilling attack models and analyzed their adverse effects. Primitive attacks are highly fea-sible but less effective due to simplistic handcrafted rules, while upgraded attacks are more powerful but costly and difficult to deploy because they require more knowledge from rec-ommendations. In this paper, we explore a novel shilling attack called graph convolution-based generative shilling ATtack (GOAT) to balance the attacks' feasibility and effective-ness. GOAT adopts the primitive attacks' paradigm that assigns items for fake users by sampling and the upgraded attacks' paradigm that generates fake ratings by a deep learning-based model. It deploys a generative adversarial network (GAN) that learns the real rating distribution to generate fake ratings. Additionally, the generator combines a tai-lored graph convolution structure that leverages the correlations between co-rated items to smoothen the fake ratings and enhance their authenticity. The extensive experiments on two public datasets evaluate GOAT's performance from multiple perspectives. Our study of the GOAT demonstrates technical feasibility for building a more powerful and intelligent attack model with a much-reduced cost, enables analysis the threat of such an attack and guides for investigating necessary prevention measures. (c) 2021 Elsevier Inc. All rights reserved.

关键词： Collaborative filtering Shilling attack Generative adversarial networks graph convolution Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Condition-Adaptive graph convolution Learning for Skeleton-Based Gait Recognition

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 4773-4784页

作者： Huang, Xiaohu Wang, Xinggang Jin, Zhidianqiu Yang, Bo He, Botao Feng, Bin Liu, Wenyu Hubei Key Lab Smart Internet Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Wuhan Fiber Home Digital Technol Co Ltd Wuhan 430074 Peoples R China CICT Mobile Commun Technol Co Ltd Wuhan 430074 Peoples R China

graph convolutional networks have been widely applied in skeleton-based gait recognition. A key challenge in this task is to distinguish the individual walking styles of different subjects across various views. Existing state-of-the-art methods employ uniform convolutions to extract features from diverse sequences and ignore the effects of viewpoint changes. To overcome these limitations, we propose a condition-adaptive graph (CAG) convolution network that can dynamically adapt to the specific attributes of each skeleton sequence and the corresponding view angle. In contrast to using fixed weights for all joints and sequences, we introduce a joint-specific filter learning (JSFL) module in the CAG method, which produces sequence-adaptive filters at the joint level. The adaptive filters capture fine-grained patterns that are unique to each joint, enabling the extraction of diverse spatial-temporal information about body parts. Additionally, we design a view-adaptive topology learning (VATL) module that generates adaptive graph topologies. These graph topologies are used to correlate the joints adaptively according to the specific view conditions. Thus, CAG can simultaneously adjust to various walking styles and viewpoints. Experiments on the two most widely used datasets (i.e., CASIA-B and OU-MVLP) show that CAG surpasses all previous skeleton-based methods. Moreover, the recognition performance can be enhanced by simply combining CAG with appearance-based methods, demonstrating the ability of CAG to provide useful complementary information.

关键词： Skeleton-based gait recognition graph convolution adaptive feature learning

来源：评论

学校读者我要写书评

暂无评论

An adaptive dual graph convolution fusion network for aspect-based sentiment analysis

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2024年第6期23卷 1-23页

作者： Wang, Chunmei Luo, Yuan Meng, Chunli Yuan, Feiniu Shanghai Normal Univ Coll Informat Mech & Elect Engn Shanghai Peoples R China

Aspect-based Sentiment Analysis (ABSA), also known as fine-grained sentiment analysis, aims to predict the sentiment polarity of specific aspect words in the sentence. Some studies have explored the semantic correlation between words in sentences through attention-based methods. Other studies have learned syntactic knowledge by using graph convolution networks to introduce dependency relations. These methods have achieved satisfactory results in the ABSA tasks. However, due to the complexity of language, effectively capturing semantic and syntactic knowledge remains a challenging research question. Therefore, we propose an Adaptive Dual graph convolution Fusion Network (AD-GCFN) for aspect-based sentiment analysis. This model uses two graph convolution networks: one for the semantic layer to learn semantic correlations by an attention mechanism, and the other for the syntactic layer to learn syntactic structure by dependency parsing. To reduce the noise caused by the attention mechanism, we designed a module that dynamically updates the graph structure information for adaptively aggregating node information. To effectively fuse semantic and syntactic information, we propose a cross-fusion module that uses the double random similarity matrix to obtain the syntactic features in the semantic space and the semantic features in the syntactic space, respectively. Additionally, we employ two regularizers to further improve the ability to capture semantic correlations. The orthogonal regularizer encourages the semantic layer to learn word semantics without overlap, while the differential regularizer encourages the semantic and syntactic layers to learn different parts. Finally, the experimental results on three benchmark datasets show that the AD-GCFN model is superior to the contrast models in terms of accuracy and macro-F1.

关键词： graph convolution attention mechanism double random matrix regularization

来源：评论

学校读者我要写书评

暂无评论

graph convolution and Self Attention Based Non-maximum Suppression 16th

Graph Convolution and Self Attention Based Non-maximum Suppr...

引用

16th International Symposium on Neural Networks (ISNN)

作者： Qiu, Zhe Gu, Xiaodong Fudan Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9783030227968;9783030227951

Non-maximum suppression is an integral and last part of object detection. Traditional NMS algorithm sorts the detection boxes according to their class scores. The detection boxes with maximum score are always selected while all other boxes with a sufficient overlap with the preserved boxes are discarded. This strategy is simple and effective. However, there still need some improvements in this process because the algorithm makes a 'hard' decision (accept or reject) for each box. In this paper, we formulate the non-maximum suppression as a rescoring process and construct a network called NmsNet which utilizes graph convolution and self attention mechanism to predict each box as an object or redundant one. We evaluate our method on the VOC2007 dataset. The experimental results show that our method achieves a higher MAP compared with the traditional greedy NMS and the Soft NMS.

关键词： graph convolution Self attention Non-maximum suppression

来源：评论

学校读者我要写书评

暂无评论

graph Transfer Learning via Adversarial Domain Adaptation With graph convolution

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第5期35卷 4908-4922页

作者： Dai, Quanyu Wu, Xiao-Ming Xiao, Jiaren Shen, Xiao Wang, Dan Huawei Noahs Ark Lab Shenzhen 518055 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China Univ Hong Kong Dept Mech Engn Pokfulam Hong Kong 999077 Peoples R China Hainan Univ Sch Comp Sci & Technol Haikou 570228 Peoples R China

This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing methods for single network learning cannot solve this problem due to the domain shift across networks. Some multi-network learning methods heavily rely on the existence of cross-network connections, thus are inapplicable for this problem. To tackle this problem, we propose a novel graph transfer learning framework AdaGCN by leveraging the techniques of adversarial domain adaptation and graph convolution. It consists of two components: a semi-supervised learning component and an adversarial domain adaptation component. The former aims to learn class discriminative node representations with given label information of the source and target networks, while the latter contributes to mitigating the distribution divergence between the source and target domains to facilitate knowledge transfer. Extensive empirical evaluations on real-world datasets show that AdaGCN can successfully transfer class information with a low label rate on the source network and a substantial divergence between the source and target domains.

关键词： Task analysis Transfer learning Knowledge engineering Adaptation models Proteins Knowledge transfer convolution graph nework transfer learning node classification graph convolution domain adaptation adversarial learning

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

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：