FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224882649> ?p ?o ?g. }

• W4224882649 endingPage "219" @default.
• W4224882649 startingPage "201" @default.
• W4224882649 abstract "Hyperspectral image classification (HSIC) is essential in remote sensing image analysis. Applying a graph neural network (GNN) to hyperspectral image (HSI) classification has attracted increasing attention. However, the available GNNs for HSIC only adopt a kind of graph filter and an aggregator, which cannot well deal with the problems of land cover discrimination, noise impaction, and spatial feature learning. To overcome these problems, a graph convolution with adaptive filters and aggregator fusion (AF2GNN) is developed for HSIC. To reduce the number of graph nodes, a superpixel segment algorithm is employed to refine the local spatial features of the HSI. A two-layer 1D CNN is proposed to transform the spectral features of superpixels. In addition, a linear function is designed to combine the different graph filters, with which the graph filter can be adaptively determined by training different weight matrices. Moreover, degree-scalers are defined to combine the multiple filters and present the graph structure. Finally, the AF2GNN is proposed to realize the adaptive filters and aggregator fusion mechanism within a single network. In the proposed network, a softMax function is utilized for graph feature interpretation and pixel-label prediction. Compared with state-of-the-art methods, the proposed method achieves superior experimental results." @default.
• W4224882649 created "2022-04-27" @default.
• W4224882649 creator A5000432967 @default.
• W4224882649 creator A5011264725 @default.
• W4224882649 creator A5031319754 @default.
• W4224882649 creator A5046153352 @default.
• W4224882649 creator A5064517198 @default.
• W4224882649 creator A5074354427 @default.
• W4224882649 creator A5090470209 @default.
• W4224882649 date "2022-07-01" @default.
• W4224882649 modified "2023-10-16" @default.
• W4224882649 title "AF2GNN: Graph convolution with adaptive filters and aggregator fusion for hyperspectral image classification" @default.
• W4224882649 cites W1521436688 @default.
• W4224882649 cites W1535602073 @default.
• W4224882649 cites W2005672614 @default.
• W4224882649 cites W2029061115 @default.
• W4224882649 cites W2029316659 @default.
• W4224882649 cites W2049667262 @default.
• W4224882649 cites W2054022051 @default.
• W4224882649 cites W2083541351 @default.
• W4224882649 cites W2085529604 @default.
• W4224882649 cites W2135431554 @default.
• W4224882649 cites W2144966944 @default.
• W4224882649 cites W2152057649 @default.
• W4224882649 cites W2194775991 @default.
• W4224882649 cites W2548791488 @default.
• W4224882649 cites W2614326984 @default.
• W4224882649 cites W2757242159 @default.
• W4224882649 cites W2766534319 @default.
• W4224882649 cites W2793941577 @default.
• W4224882649 cites W2804902458 @default.
• W4224882649 cites W2890133123 @default.
• W4224882649 cites W2892621946 @default.
• W4224882649 cites W2899003677 @default.
• W4224882649 cites W2914331134 @default.
• W4224882649 cites W2914429466 @default.
• W4224882649 cites W2937638900 @default.
• W4224882649 cites W2963446712 @default.
• W4224882649 cites W2971851282 @default.
• W4224882649 cites W2984795071 @default.
• W4224882649 cites W2991494819 @default.
• W4224882649 cites W3011645114 @default.
• W4224882649 cites W3017001049 @default.
• W4224882649 cites W3047443805 @default.
• W4224882649 cites W3085067733 @default.
• W4224882649 cites W3088864412 @default.
• W4224882649 cites W3157130577 @default.
• W4224882649 cites W3162367524 @default.
• W4224882649 cites W3178695133 @default.
• W4224882649 cites W3184219885 @default.
• W4224882649 cites W4240485910 @default.
• W4224882649 cites W4281633835 @default.
• W4224882649 cites W4312513332 @default.
• W4224882649 cites W4312610489 @default.
• W4224882649 cites W4313132151 @default.
• W4224882649 doi "https://doi.org/10.1016/j.ins.2022.04.006" @default.
• W4224882649 hasPublicationYear "2022" @default.
• W4224882649 type Work @default.
• W4224882649 citedByCount "46" @default.
• W4224882649 countsByYear W42248826492022 @default.
• W4224882649 countsByYear W42248826492023 @default.
• W4224882649 crossrefType "journal-article" @default.
• W4224882649 hasAuthorship W4224882649A5000432967 @default.
• W4224882649 hasAuthorship W4224882649A5011264725 @default.
• W4224882649 hasAuthorship W4224882649A5031319754 @default.
• W4224882649 hasAuthorship W4224882649A5046153352 @default.
• W4224882649 hasAuthorship W4224882649A5064517198 @default.
• W4224882649 hasAuthorship W4224882649A5074354427 @default.
• W4224882649 hasAuthorship W4224882649A5090470209 @default.
• W4224882649 hasConcept C132525143 @default.
• W4224882649 hasConcept C153180895 @default.
• W4224882649 hasConcept C154945302 @default.
• W4224882649 hasConcept C159078339 @default.
• W4224882649 hasConcept C33923547 @default.
• W4224882649 hasConcept C41008148 @default.
• W4224882649 hasConcept C80444323 @default.
• W4224882649 hasConceptScore W4224882649C132525143 @default.
• W4224882649 hasConceptScore W4224882649C153180895 @default.
• W4224882649 hasConceptScore W4224882649C154945302 @default.
• W4224882649 hasConceptScore W4224882649C159078339 @default.
• W4224882649 hasConceptScore W4224882649C33923547 @default.
• W4224882649 hasConceptScore W4224882649C41008148 @default.
• W4224882649 hasConceptScore W4224882649C80444323 @default.
• W4224882649 hasLocation W42248826491 @default.
• W4224882649 hasOpenAccess W4224882649 @default.
• W4224882649 hasPrimaryLocation W42248826491 @default.
• W4224882649 hasRelatedWork W1869808405 @default.
• W4224882649 hasRelatedWork W2028628118 @default.
• W4224882649 hasRelatedWork W2031007444 @default.
• W4224882649 hasRelatedWork W2775464024 @default.
• W4224882649 hasRelatedWork W2783789044 @default.
• W4224882649 hasRelatedWork W2972973180 @default.
• W4224882649 hasRelatedWork W3173596272 @default.
• W4224882649 hasRelatedWork W3211035526 @default.
• W4224882649 hasRelatedWork W4291701050 @default.
• W4224882649 hasRelatedWork W4293272463 @default.
• W4224882649 hasVolume "602" @default.
• W4224882649 isParatext "false" @default.

• next