Matches in SemOpenAlex for { <https://semopenalex.org/work/W2983573090> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2983573090 abstract "Convolutional neural networks (CNNs) have recently shown remarkable performance in remote sensing scene image classification. However, long-range dependencies (e.g. non-local similarities) within the scene are often ignored by CNNs. To address this issue, in this paper we develop a new high-order self-attention network (HoSA) for remote sensing scene classification. Specifically, we embed two novel modules, i.e., a self-attention module and a high order pooling module, into off-the-shelf CNN models and then fine-tune the whole network. The advantages of our newly proposed HoSA network are twofold. Firstly, with the self-attention module, the HoSA can capture long-range dependencies within the scenes for high-level semantic feature extraction. Secondly, by means of its high-order pooling mechanism, our newly developed HoSA can further explore high-order information contained in the features. Our experiments with a widely used remote sensing scene data set demonstrate that the proposed HoSA network exhibits better classification performance than the baseline and several well-known methods." @default.
- W2983573090 created "2019-11-22" @default.
- W2983573090 creator A5054292278 @default.
- W2983573090 creator A5057842658 @default.
- W2983573090 creator A5064842058 @default.
- W2983573090 creator A5065061505 @default.
- W2983573090 date "2019-07-01" @default.
- W2983573090 modified "2023-09-27" @default.
- W2983573090 title "High-Order Self-Attention Network for Remote Sensing Scene Classification" @default.
- W2983573090 cites W1980038761 @default.
- W2983573090 cites W2098676252 @default.
- W2983573090 cites W2190186811 @default.
- W2983573090 cites W2620429297 @default.
- W2983573090 cites W2744582969 @default.
- W2983573090 cites W2783165089 @default.
- W2983573090 cites W2829067510 @default.
- W2983573090 cites W2963091558 @default.
- W2983573090 cites W2963403868 @default.
- W2983573090 doi "https://doi.org/10.1109/igarss.2019.8898320" @default.
- W2983573090 hasPublicationYear "2019" @default.
- W2983573090 type Work @default.
- W2983573090 sameAs 2983573090 @default.
- W2983573090 citedByCount "2" @default.
- W2983573090 countsByYear W29835730902021 @default.
- W2983573090 crossrefType "proceedings-article" @default.
- W2983573090 hasAuthorship W2983573090A5054292278 @default.
- W2983573090 hasAuthorship W2983573090A5057842658 @default.
- W2983573090 hasAuthorship W2983573090A5064842058 @default.
- W2983573090 hasAuthorship W2983573090A5065061505 @default.
- W2983573090 hasConcept C115961682 @default.
- W2983573090 hasConcept C124101348 @default.
- W2983573090 hasConcept C138885662 @default.
- W2983573090 hasConcept C153180895 @default.
- W2983573090 hasConcept C154945302 @default.
- W2983573090 hasConcept C177264268 @default.
- W2983573090 hasConcept C199360897 @default.
- W2983573090 hasConcept C2776401178 @default.
- W2983573090 hasConcept C41008148 @default.
- W2983573090 hasConcept C41895202 @default.
- W2983573090 hasConcept C52622490 @default.
- W2983573090 hasConcept C58489278 @default.
- W2983573090 hasConcept C70437156 @default.
- W2983573090 hasConcept C75294576 @default.
- W2983573090 hasConcept C81363708 @default.
- W2983573090 hasConceptScore W2983573090C115961682 @default.
- W2983573090 hasConceptScore W2983573090C124101348 @default.
- W2983573090 hasConceptScore W2983573090C138885662 @default.
- W2983573090 hasConceptScore W2983573090C153180895 @default.
- W2983573090 hasConceptScore W2983573090C154945302 @default.
- W2983573090 hasConceptScore W2983573090C177264268 @default.
- W2983573090 hasConceptScore W2983573090C199360897 @default.
- W2983573090 hasConceptScore W2983573090C2776401178 @default.
- W2983573090 hasConceptScore W2983573090C41008148 @default.
- W2983573090 hasConceptScore W2983573090C41895202 @default.
- W2983573090 hasConceptScore W2983573090C52622490 @default.
- W2983573090 hasConceptScore W2983573090C58489278 @default.
- W2983573090 hasConceptScore W2983573090C70437156 @default.
- W2983573090 hasConceptScore W2983573090C75294576 @default.
- W2983573090 hasConceptScore W2983573090C81363708 @default.
- W2983573090 hasLocation W29835730901 @default.
- W2983573090 hasOpenAccess W2983573090 @default.
- W2983573090 hasPrimaryLocation W29835730901 @default.
- W2983573090 hasRelatedWork W2912089046 @default.
- W2983573090 hasRelatedWork W2944971001 @default.
- W2983573090 hasRelatedWork W2954156245 @default.
- W2983573090 hasRelatedWork W2985929670 @default.
- W2983573090 hasRelatedWork W3045603631 @default.
- W2983573090 hasRelatedWork W3047889186 @default.
- W2983573090 hasRelatedWork W3081449033 @default.
- W2983573090 hasRelatedWork W3082634341 @default.
- W2983573090 hasRelatedWork W3086451439 @default.
- W2983573090 hasRelatedWork W3101082097 @default.
- W2983573090 hasRelatedWork W3112650590 @default.
- W2983573090 hasRelatedWork W3114860340 @default.
- W2983573090 hasRelatedWork W3133018110 @default.
- W2983573090 hasRelatedWork W3159088339 @default.
- W2983573090 hasRelatedWork W3175037443 @default.
- W2983573090 hasRelatedWork W3188567309 @default.
- W2983573090 hasRelatedWork W3196798006 @default.
- W2983573090 hasRelatedWork W3207726089 @default.
- W2983573090 hasRelatedWork W3213005772 @default.
- W2983573090 hasRelatedWork W3213288046 @default.
- W2983573090 isParatext "false" @default.
- W2983573090 isRetracted "false" @default.
- W2983573090 magId "2983573090" @default.
- W2983573090 workType "article" @default.