FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204505238> ?p ?o ?g. }

• W3204505238 abstract "It is well known that hyperspectral images (HSI) contain rich spatial-spectral contextual information, and how to effectively combine both spectral and spatial information using DNN for HSI classification has become a new research hotspot. Compared with CNN with square kernels, GCN have exhibited exciting potential to model spatial contextual structure and conduct flexible convolution on arbitrarily irregular image regions. However, current GCN only using first-order spectral-spatial signatures can result in boundary blurring and isolated misclassification. To address these, we first designed the graph-based second-order pooling (GSOP) operation to obtain contextual nodes information in non-Euclidean space for GCN. Further, we proposed a novel multi-stream hybridized convolutional network (MSHCNet) with combination of first and second order statistics in Euclidean/non-Euclidean spaces to learn and fuse multi-view complementary information to segment HSIs. Specifically, our MSHCNet adopted four parallel streams, which contained G-stream, utilizing the irregular correlation between adjacent land covers in terms of first-order graph in non-Euclidean space; C-stream, adopting convolution operator to learn regular spatial-spectral features in Euclidean space; N-stream, combining first and second order features to learn representative and discriminative regular spatial-spectral features of Euclidean space; S-stream, using GSOP to capture boundary correlations and obtain graph representations from all nodes in graphs of non-Euclidean space. Besides, these feature representations learned from four different streams were fused to integrate the multi-view complementary information for HSI classification. Finally, we evaluated our proposed MSHCNet on three hyperspectral datasets, and experimental results demonstrated that our method significantly outperformed state-of-the-art eight methods." @default.
• W3204505238 created "2021-10-11" @default.
• W3204505238 creator A5041620666 @default.
• W3204505238 creator A5047632784 @default.
• W3204505238 creator A5052603284 @default.
• W3204505238 creator A5054214235 @default.
• W3204505238 creator A5083988319 @default.
• W3204505238 date "2021-10-07" @default.
• W3204505238 modified "2023-09-27" @default.
• W3204505238 title "MSHCNet: Multi-Stream Hybridized Convolutional Networks with Mixed Statistics in Euclidean/Non-Euclidean Spaces and Its Application to Hyperspectral Image Classification." @default.
• W3204505238 cites W1501856433 @default.
• W3204505238 cites W1521436688 @default.
• W3204505238 cites W1950365613 @default.
• W3204505238 cites W1966580635 @default.
• W3204505238 cites W2018482939 @default.
• W3204505238 cites W2029316659 @default.
• W3204505238 cites W2043665634 @default.
• W3204505238 cites W2071528823 @default.
• W3204505238 cites W2085842814 @default.
• W3204505238 cites W2087263574 @default.
• W3204505238 cites W2089109970 @default.
• W3204505238 cites W2121169814 @default.
• W3204505238 cites W2150120952 @default.
• W3204505238 cites W2161854574 @default.
• W3204505238 cites W2167397429 @default.
• W3204505238 cites W2299115575 @default.
• W3204505238 cites W2312996138 @default.
• W3204505238 cites W2314785379 @default.
• W3204505238 cites W2500751094 @default.
• W3204505238 cites W2516282711 @default.
• W3204505238 cites W2547846938 @default.
• W3204505238 cites W2572303978 @default.
• W3204505238 cites W2743091961 @default.
• W3204505238 cites W2757242159 @default.
• W3204505238 cites W2765277922 @default.
• W3204505238 cites W2779530678 @default.
• W3204505238 cites W2887785636 @default.
• W3204505238 cites W2892621946 @default.
• W3204505238 cites W2897559184 @default.
• W3204505238 cites W2902323880 @default.
• W3204505238 cites W2920405132 @default.
• W3204505238 cites W2921084751 @default.
• W3204505238 cites W2940678725 @default.
• W3204505238 cites W2963043672 @default.
• W3204505238 cites W2964311892 @default.
• W3204505238 cites W2991494819 @default.
• W3204505238 cites W3024007459 @default.
• W3204505238 cites W3031015423 @default.
• W3204505238 cites W3034090344 @default.
• W3204505238 cites W3120356488 @default.
• W3204505238 cites W3122774149 @default.
• W3204505238 hasPublicationYear "2021" @default.
• W3204505238 type Work @default.
• W3204505238 sameAs 3204505238 @default.
• W3204505238 citedByCount "0" @default.
• W3204505238 crossrefType "posted-content" @default.
• W3204505238 hasAuthorship W3204505238A5041620666 @default.
• W3204505238 hasAuthorship W3204505238A5047632784 @default.
• W3204505238 hasAuthorship W3204505238A5052603284 @default.
• W3204505238 hasAuthorship W3204505238A5054214235 @default.
• W3204505238 hasAuthorship W3204505238A5083988319 @default.
• W3204505238 hasConcept C105795698 @default.
• W3204505238 hasConcept C114614502 @default.
• W3204505238 hasConcept C120174047 @default.
• W3204505238 hasConcept C129782007 @default.
• W3204505238 hasConcept C132525143 @default.
• W3204505238 hasConcept C153180895 @default.
• W3204505238 hasConcept C154945302 @default.
• W3204505238 hasConcept C159078339 @default.
• W3204505238 hasConcept C159620131 @default.
• W3204505238 hasConcept C186450821 @default.
• W3204505238 hasConcept C2524010 @default.
• W3204505238 hasConcept C33923547 @default.
• W3204505238 hasConcept C41008148 @default.
• W3204505238 hasConcept C70437156 @default.
• W3204505238 hasConcept C80444323 @default.
• W3204505238 hasConcept C83665646 @default.
• W3204505238 hasConcept C97931131 @default.
• W3204505238 hasConceptScore W3204505238C105795698 @default.
• W3204505238 hasConceptScore W3204505238C114614502 @default.
• W3204505238 hasConceptScore W3204505238C120174047 @default.
• W3204505238 hasConceptScore W3204505238C129782007 @default.
• W3204505238 hasConceptScore W3204505238C132525143 @default.
• W3204505238 hasConceptScore W3204505238C153180895 @default.
• W3204505238 hasConceptScore W3204505238C154945302 @default.
• W3204505238 hasConceptScore W3204505238C159078339 @default.
• W3204505238 hasConceptScore W3204505238C159620131 @default.
• W3204505238 hasConceptScore W3204505238C186450821 @default.
• W3204505238 hasConceptScore W3204505238C2524010 @default.
• W3204505238 hasConceptScore W3204505238C33923547 @default.
• W3204505238 hasConceptScore W3204505238C41008148 @default.
• W3204505238 hasConceptScore W3204505238C70437156 @default.
• W3204505238 hasConceptScore W3204505238C80444323 @default.
• W3204505238 hasConceptScore W3204505238C83665646 @default.
• W3204505238 hasConceptScore W3204505238C97931131 @default.
• W3204505238 hasLocation W32045052381 @default.
• W3204505238 hasOpenAccess W3204505238 @default.
• W3204505238 hasPrimaryLocation W32045052381 @default.
• W3204505238 hasRelatedWork W1978430152 @default.
• W3204505238 hasRelatedWork W2075105027 @default.

• next