检索结果-内蒙古大学图书馆

GACP:graph neural networks with ARMA flters and a parallel CNN for hyperspectral image classification

International Journal of Digital Earth 2023年第1期16卷 1770-1800页

作者： Jing Yang Jie Sun Yaping Ren Shaobo Li Shujie Ding Jianjun Hu School of Mechanical Engineering Guizhou UniversityGuiyangPeople’s Republic of China State Key Laboratory of Public Big Data Guizhou UniversityGuiyangPeople’s Republic of China School of Intelligent Systems Science and Engineering Jinan UniversityZhuhaiPeople’s Republic of China Department of Computer Science and Engineering University of South CarolinaColumbiaSCUSA

In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote *** many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral *** on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)***,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny *** conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.

关键词： Graph neural networks word convolutional neural networks hyperspectral image classification attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Adversarial-based Feature Disentanglement Learning for Cross-database Micro-Expression Recognition 22

Asymmetric Adversarial-based Feature Disentanglement Learnin...

引用

30th ACM International Conference on Multimedia (MM)

作者： Xu, Shiting Zhou, Zhiheng Shang, Junyuan South China Univ Technol Sch Elect & Informat Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

ISBN: (纸本)9781450392037

Recently, micro-expression recognition (MER) has gained tremendous progress. However, most methods are based on individualdata-base micro-expression recognition and are difficult to generalize into complicated scenarios. Therefore, cross-database micro-expression recognition (CDMER) has drawn growing attention due to its robustness and generalizability. In this paper, we propose a novel CDMER algorithm with asymmetric adversarial-based feature disentanglement learning, which implements the disentanglement of domain features and emotion features aiming to learn domain-invariant and discriminative representation. Furthermore, to facilitate the feature disentanglement learning, a Domain Information Filtering (DF) module is designed to filter out the domain component of the micro-expression features (emotion feature). Extensive experiments on the SMIC and CASME II databases have shown that our proposed method outperforms the state-of-the-art method and has superior performance against excessive domain discrepancies.

关键词： micro-expression neural networks domain adaptation

来源：评论

学校读者我要写书评

暂无评论

CoGAP: A Personalized Federated Learning Method Using Collaborative Optimization for Medical Image Classification

CoGAP: A Personalized Federated Learning Method Using Collab...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Shenhai Li, Congyu Wen, Sian Gao, Xi Yu, Lei College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China Emergency Department The Second Affiliated Hospital of Chongqing Medical University Chongqing China

ISBN: (纸本)9798350368741

Federated learning (FL) has been widely used in medical image processing to protect data privacy, but it has issues with data heterogeneity. Personalized federated learning have emerged to tackle these issues but often focuses too much on personalized models at the expense of global models. To address these problem, we propose a personalized federated learning method CoGAP, using collaborative optimization to enhance both personalized and global model performance. On the client side, it employs adaptive weight aggregation to initialize personalized models and uses a training strategy based on L2 regularization. On the server side, it implements a gradient accumulation-based aggregation method. These modules facilitate a collaborative optimization process where the global model guides the personalized models, and the personalized models provide positive feedback to the global model, ultimately leading to mutual improvement for both. We conducted extensive comparative experiments on the OCT2017 dataset, as well as the BloodMnist and PathMnist (subsets from MedMnist), to evaluate both global and personalized models. Results show that CoGAP own a unique strength which not only outperforms other personalized federated learning methods in personalization capability while also remarkably achieving satisfying global generalization. Code is available at https://***/lcyCQUPT/CoGAP. © 2025 IEEE.

关键词： collaborative optimization federated learning medical image classification

来源：评论

学校读者我要写书评

暂无评论

3D-STARNET: Spatial-Temporal Attention Residual Network for Robust Action Recognition

引用

APPLIED SCIENCES-BASEL 2024年第16期14卷 7154页

作者： Yang, Jun Sun, Shulong Chen, Jiayue Xie, Haizhen Wang, Yan Yang, Zenglong China Univ Min & Technol Big Data & Internet Things Res Ctr Beijing 100083 Peoples R China Minist Emergency Management Key Lab Intelligent Min & Robot Beijing 100083 Peoples R China

Existing skeleton-based action recognition methods face the challenges of insufficient spatiotemporal feature mining and a low efficiency of information transmission. To solve these problems, this paper proposes a model called the Spatial-Temporal Attention Residual Network for 3D human action recognition (3D-STARNET). This model significantly improves the performance of action recognition through the following three main innovations: (1) the conversion from skeleton points to heat maps. Using Gaussian transform to convert skeleton point data into heat maps effectively reduces the model's strong dependence on the original skeleton point data and enhances the stability and robustness of the data;(2) a spatiotemporal attention mechanism (STA). A novel spatiotemporal attention mechanism is proposed, focusing on the extraction of key frames and key areas within frames, which significantly enhances the model's ability to identify behavioral patterns;(3) a multi-stage residual structure (MS-Residual). The introduction of a multi-stage residual structure improves the efficiency of data transmission in the network, solves the gradient vanishing problem in deep networks, and helps to improve the recognition efficiency of the model. Experimental results on the NTU-RGBD120 dataset show that 3D-STARNET has significantly improved the accuracy of action recognition, and the top1 accuracy of the overall network reached 96.74%. This method not only solves the robustness shortcomings of existing methods, but also improves the ability to capture spatiotemporal features, providing an efficient and widely applicable solution for action recognition based on skeletal data.

关键词： action recognition spatiotemporal attention multi-staged residual skeleton 3D CNN

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch Attention Transformer for Visual Commonsense Reasoning

Dual-Branch Attention Transformer for Visual Commonsense Rea...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Xuerui Ma Zongwen Bai Meili Zhou Yiqun Gao Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Visual Commonsense Reasoning (VCR) is a challenging task that requires a model to select the correct answer in the context of a given image and question, while also providing a reasonable explanation to justify the chosen answer. In this paper, we propose a novel dual-branch attention network model that effectively models dense intra-modal and inter-modal interactions. Our model utilizes a self-attention mechanism to attend to visual and textual information independently, while employing a bidirectional guided attention mechanism to facilitate effective interaction between different modalities, thus correlating visual information with textual information. By stacking multiple dual-branch attention modules (DBAs), our model is capable of deeply exploring data features and extracting more powerful and informative prior features. By achieving a common focus on visual and textual information, we enhance the subtlety of our understanding and significantly improve our ability to perform visual reasoning. Our comprehensive and qualitative assessments on the public VCR dataset illustrate that our methodology surpasses most models, providing a new solution for Visual Commonsense Reasoning tasks.

关键词： Visualization Accuracy Computational modeling Stacking Semantics Feature extraction Transformers data models Commonsense reasoning Video recording

来源：评论

学校读者我要写书评

暂无评论

Collaborative Optimization of Truck-Drone Based on Multi-agent Reinforcement Learning 11th

Collaborative Optimization of Truck-Drone Based on Multi-a...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Zhang, Wenhao Wang, Guoyin Liu, Qun Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing 400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing 401331 China

ISBN: (纸本)9783031927409

This study proposes a novel Multi-Head Attention-enhanced Proximal Policy Optimization (MHA-PPO) algorithm for collaborative truck-drone delivery systems in dynamic logistics scenarios. To address the limitations of traditional multi-agent reinforcement learning in handling complex spatiotemporal dependencies and real-time decision-making, we integrate a multi-head attention mechanism into the PPO framework, enabling adaptive feature fusion of heterogeneous agent observations (e.g., drone positions, truck routes, and package urgency levels). A key innovation lies in the design of a variable emergency mechanism that models a random urgency generation module and dynamically adjusts task priorities based on the urgency of customer demand for packages. The system is implemented in a high-fidelity Unity simulation environment incorporating 3D urban terrain, realistic drone aerodynamics, and traffic flow patterns. Comparative experiments against baseline algorithms (PPO, Multi-Agent Proximal Policy Optimization (MAPPO), Multi-Head Attention Deep Deterministic Policy Gradient (MHA-DDPG)) demonstrate that our MHA-PPO achieves superior performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multi-agent problem Reinforcement learning Task allocation Truck-drone cooperative delivery

来源：评论

学校读者我要写书评

暂无评论

GENERAL IMPLICIT SUBGRADIENT EXTRAGRADIENT METHODS FOR MONOTONE BILEVEL EQUILIBRIUM PROBLEMS

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2022年第3期84卷 3-20页

作者： Ceng, Lu-Chuan Zhao, Xiaopeng Zhu, Li-Jun Department of Mathematics Shanghai Normal University Shanghai200234 China School of Mathematical Sciences Tiangong University Tianjin300387 China The Key Laboratory of Intelligent Information and Big Data Processing of NingXia North Minzu University Yinchuan750021 China

In this paper, we introduce the general implicit subgradient extragradient method for solving the monotone bilevel equilibrium problem (MBEP) with a general system of variational inclusions (GSVI) and a common fixed-point problem of finitely many nonexpansive mappings and a strictly pseudocontractive mapping (CFPP) constraints. The strong convergence result for the proposed algorithm is established under the monotonicity assumption of the cost bifunctions with Lipschitz-type continuous conditions recently presented by Mastroeni in the auxiliary problem principle, and also applied for finding a common solution of variational inequality, variational inclusion and fixed-point problems. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

A Context-Free Method for Robust Grasp Detection: Learning to Overcome Contextual Bias

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2022年第12期69卷 13121-13130页

作者： Li, Yuanhao Huang, Panfeng Ma, Zhiqiang Chen, Lu Northwestern Polytech Univ Res Ctr Intelligent Robot Sch Astronaut Xian 710060 Peoples R China Northwestern Polytech Univ Natl Key Lab Aerosp Flight Dynam Xian 710060 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Peoples R China

The vision-based grasp detection method is an important technique used to research the grasping task of robots. Unfortunately, the performances of these research methods in practice are worse than the state-of-the-art accuracy on public datasets, because shifts in data distribution owing to real-world conditions are common in the real world and neural network-based methods are sensitive to small data changes. These disturbances mainly change the image texture, causing the performance of grasp detection methods to decline sharply. However, the evaluation metric of existing models does not reflect the actual robustness of the method. Therefore, we propose a new solution. First, referring to the existing research on image classification methods, we propose a benchmark to verify the realistic robustness of the grasp detection model. Second, to improve the robustness of the model, we randomly transfer texture knowledge from other images to provide variable texture information for network training. This forces the model to rely more on the contour features of the object than on the texture when making decisions;we call this approach "context-free." We verify the effectiveness of our method for robustness enhancement in various grasp tasks and test the proposed method in a real robot grasping scene.

关键词： Context-free deep neural network grasp robustness robotic grasp detection

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: accelerating distributed GNN training leveraging feature-centric model migration 25

LeapGNN: accelerating distributed GNN training leveraging fe...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Xuechen Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University and Zhejiang Lab and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Bridged Vision and Language: Learning Cross-Modal Knowledge Representation for Relation Extraction

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第1期34卷 561-575页

作者： Feng, Junhao Wang, Guohua Zheng, Changmeng Cai, Yi Fu, Ze Wang, Yaowei Wei, Xiao-Yong Li, Qing South China Univ Technol SCUT Sch Software Engn Guangzhou 510640 Peoples R China South China Univ Technol SCUT Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510640 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China Sichuan Univ Sch Comp Sci Chengdu 610017 Peoples R China

In natural language processing, relation extraction (RE) is to detect and classify the semantic relationship of two given entities within a sentence. Previous RE methods consider only the textual contents and suffer performance decline in social media when texts lack contexts. Incorporating text-related visual information can supplement the missing semantics for relation extraction in social media posts. However, textual relations are usually abstract and of high-level semantics, which causes the semantic gap between visual contents and textual expressions. In this paper, we propose RECK - a neural network for relation extraction with cross-modal knowledge representations. Different from previous multimodal methods training a common subspace for all modalities, we bridge the semantic gaps by explicitly selecting knowledge paths from external knowledge through the cross-modal object-entity pairs. We further extend the paths into a knowledge graph, and adopt a graph attention network to capture the multi-grained relevant concepts which can provide higher level and key semantics information from external knowledge. Besides, we employ a cross-modal attention mechanism to align and fuse the multimodal information. Experimental results on a multimodal RE dataset show that our model achieves new state-of-the-art performance with knowledge evidence.

关键词： Multimodal relation extraction graph attention network knowledge graphs

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：