Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385377050> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4385377050 endingPage "400" @default.
- W4385377050 startingPage "389" @default.
- W4385377050 abstract "Heritage buildings have essential cultural and economic values, with constant change and destruction. Existing technologies that classify architectural heritage images can promote the recording and protection of heritage buildings. However, the background information of architectural heritage images is complex and changeable, making it difficult to extract the key feature information. In order to address the above problem, this paper proposes a pyramidal attention convolution residual network (PECA-Net) based on ResNet18, in which pyramidal convolution (PyConv) and attention mechanism have been adopted. PyConv is introduced into residual blocks instead of standard convolution, which can extract detailed information on different scales without increasing the parameter space of the model. Then, we propose a dual-pooling channel attention mechanism (DP-ECA) that effectively improves the ability to extract key information. Compared with the original ResNet18, experimental results show that the accuracy of our model is increased by 1.86%, and the parameters and FLOPs (floating point operations) are reduced by 0.48M and 0.28G respectively." @default.
- W4385377050 created "2023-07-30" @default.
- W4385377050 creator A5036232396 @default.
- W4385377050 creator A5037117751 @default.
- W4385377050 creator A5056098918 @default.
- W4385377050 date "2023-01-01" @default.
- W4385377050 modified "2023-10-16" @default.
- W4385377050 title "PECA-Net: Pyramidal Attention Convolution Residual Network for Architectural Heritage Images Classification" @default.
- W4385377050 cites W2120419212 @default.
- W4385377050 cites W2124386111 @default.
- W4385377050 cites W2183341477 @default.
- W4385377050 cites W2194775991 @default.
- W4385377050 cites W2412782625 @default.
- W4385377050 cites W2565246530 @default.
- W4385377050 cites W2618530766 @default.
- W4385377050 cites W2752782242 @default.
- W4385377050 cites W2760432156 @default.
- W4385377050 cites W2884585870 @default.
- W4385377050 cites W2890123247 @default.
- W4385377050 cites W2979852104 @default.
- W4385377050 cites W3034552520 @default.
- W4385377050 cites W3089563436 @default.
- W4385377050 cites W3140854437 @default.
- W4385377050 cites W3146366485 @default.
- W4385377050 cites W3167976421 @default.
- W4385377050 cites W4281750945 @default.
- W4385377050 cites W4309309869 @default.
- W4385377050 cites W50236904 @default.
- W4385377050 cites W81761343 @default.
- W4385377050 doi "https://doi.org/10.1007/978-981-99-4742-3_32" @default.
- W4385377050 hasPublicationYear "2023" @default.
- W4385377050 type Work @default.
- W4385377050 citedByCount "0" @default.
- W4385377050 crossrefType "book-chapter" @default.
- W4385377050 hasAuthorship W4385377050A5036232396 @default.
- W4385377050 hasAuthorship W4385377050A5037117751 @default.
- W4385377050 hasAuthorship W4385377050A5056098918 @default.
- W4385377050 hasConcept C11413529 @default.
- W4385377050 hasConcept C124101348 @default.
- W4385377050 hasConcept C14166107 @default.
- W4385377050 hasConcept C153180895 @default.
- W4385377050 hasConcept C154945302 @default.
- W4385377050 hasConcept C155512373 @default.
- W4385377050 hasConcept C173608175 @default.
- W4385377050 hasConcept C2524010 @default.
- W4385377050 hasConcept C26517878 @default.
- W4385377050 hasConcept C33923547 @default.
- W4385377050 hasConcept C3826847 @default.
- W4385377050 hasConcept C38652104 @default.
- W4385377050 hasConcept C41008148 @default.
- W4385377050 hasConcept C45347329 @default.
- W4385377050 hasConcept C50644808 @default.
- W4385377050 hasConcept C70437156 @default.
- W4385377050 hasConcept C81363708 @default.
- W4385377050 hasConceptScore W4385377050C11413529 @default.
- W4385377050 hasConceptScore W4385377050C124101348 @default.
- W4385377050 hasConceptScore W4385377050C14166107 @default.
- W4385377050 hasConceptScore W4385377050C153180895 @default.
- W4385377050 hasConceptScore W4385377050C154945302 @default.
- W4385377050 hasConceptScore W4385377050C155512373 @default.
- W4385377050 hasConceptScore W4385377050C173608175 @default.
- W4385377050 hasConceptScore W4385377050C2524010 @default.
- W4385377050 hasConceptScore W4385377050C26517878 @default.
- W4385377050 hasConceptScore W4385377050C33923547 @default.
- W4385377050 hasConceptScore W4385377050C3826847 @default.
- W4385377050 hasConceptScore W4385377050C38652104 @default.
- W4385377050 hasConceptScore W4385377050C41008148 @default.
- W4385377050 hasConceptScore W4385377050C45347329 @default.
- W4385377050 hasConceptScore W4385377050C50644808 @default.
- W4385377050 hasConceptScore W4385377050C70437156 @default.
- W4385377050 hasConceptScore W4385377050C81363708 @default.
- W4385377050 hasLocation W43853770501 @default.
- W4385377050 hasOpenAccess W4385377050 @default.
- W4385377050 hasPrimaryLocation W43853770501 @default.
- W4385377050 hasRelatedWork W2291847203 @default.
- W4385377050 hasRelatedWork W2424871898 @default.
- W4385377050 hasRelatedWork W2517027266 @default.
- W4385377050 hasRelatedWork W2756241593 @default.
- W4385377050 hasRelatedWork W3004532561 @default.
- W4385377050 hasRelatedWork W3024389224 @default.
- W4385377050 hasRelatedWork W3106810211 @default.
- W4385377050 hasRelatedWork W3154571607 @default.
- W4385377050 hasRelatedWork W4225850200 @default.
- W4385377050 hasRelatedWork W4312417841 @default.
- W4385377050 isParatext "false" @default.
- W4385377050 isRetracted "false" @default.
- W4385377050 workType "book-chapter" @default.