FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328007417> ?p ?o ?g. }

• W4328007417 endingPage "27973" @default.
• W4328007417 startingPage "27963" @default.
• W4328007417 abstract "Principal Component Analysis Network (PCANet) is a feature learning algorithm which is widely used in face recognition and object classification. However, original PCANet still has some shortages. One is that PCA algorithm only extracts features by considering the global structure. The other lies in that the original PCANet only employs one particular single layer convolutional results, which loses the information of other convolutional layers. In this paper, we propose a new simple and efficient convolutional neural network called global and local structure network (GLSNet) to address the problems. The network extracts the features both from the global structure and the local structure of the original data space. Specifically, a principal component analysis (PCA) convolutional layer which learns the filters by PCA algorithm is used to remove the noises and redundant information at the first stage. Then at the second stage, another PCA convolution is added to extract features by considering the global structure. As for the local structure, we use the neighborhood preserving embedding (NPE) algorithm to learn the convolutional filters. At the output stage, the global structure feature extracted by PCA convolution and the local structure feature extracted by NPE convolution is concatenated as a united feature. Furthermore, the first layer convolutional feature is also taken into consideration to obtain shallow-level information. Finally, these features are concatenated as a united feature, and a spatial pyramid pooling layer is followed to pool above the united features. To test the effectiveness of the proposed algorithm, the experiments on some image datasets, including three types: human face dataset, object dataset, and handprinted dataset, proceeded. And it performs better than the original PCANet and some improvement algorithms of PCANet, such as PLDANet, and MMPCANet." @default.
• W4328007417 created "2023-03-22" @default.
• W4328007417 creator A5045657343 @default.
• W4328007417 creator A5046520540 @default.
• W4328007417 creator A5057522977 @default.
• W4328007417 date "2023-01-01" @default.
• W4328007417 modified "2023-09-30" @default.
• W4328007417 title "Global and Local Structure Network for Image Classification" @default.
• W4328007417 cites W1502638562 @default.
• W4328007417 cites W1616446408 @default.
• W4328007417 cites W1967106605 @default.
• W4328007417 cites W1979743748 @default.
• W4328007417 cites W1988805924 @default.
• W4328007417 cites W1997011019 @default.
• W4328007417 cites W1998563045 @default.
• W4328007417 cites W1999113165 @default.
• W4328007417 cites W2025112904 @default.
• W4328007417 cites W2027461913 @default.
• W4328007417 cites W2028880308 @default.
• W4328007417 cites W2063385051 @default.
• W4328007417 cites W2063603851 @default.
• W4328007417 cites W2072072671 @default.
• W4328007417 cites W2080183044 @default.
• W4328007417 cites W2090922444 @default.
• W4328007417 cites W2097117768 @default.
• W4328007417 cites W2102544846 @default.
• W4328007417 cites W2104210067 @default.
• W4328007417 cites W2104978738 @default.
• W4328007417 cites W2109255472 @default.
• W4328007417 cites W2112796928 @default.
• W4328007417 cites W2136922672 @default.
• W4328007417 cites W2155759509 @default.
• W4328007417 cites W2161969291 @default.
• W4328007417 cites W2162915993 @default.
• W4328007417 cites W2295124130 @default.
• W4328007417 cites W2318574684 @default.
• W4328007417 cites W2597485909 @default.
• W4328007417 cites W2611159092 @default.
• W4328007417 cites W2618530766 @default.
• W4328007417 cites W2783380896 @default.
• W4328007417 cites W2787475547 @default.
• W4328007417 cites W2900663851 @default.
• W4328007417 cites W2919115771 @default.
• W4328007417 cites W2955429674 @default.
• W4328007417 cites W2962949934 @default.
• W4328007417 cites W3000274722 @default.
• W4328007417 cites W3048718703 @default.
• W4328007417 cites W3102431071 @default.
• W4328007417 cites W3142475087 @default.
• W4328007417 cites W3157976194 @default.
• W4328007417 cites W3206824631 @default.
• W4328007417 cites W4220806492 @default.
• W4328007417 cites W4220851674 @default.
• W4328007417 cites W4229458319 @default.
• W4328007417 cites W4289236186 @default.
• W4328007417 cites W4303954731 @default.
• W4328007417 doi "https://doi.org/10.1109/access.2023.3258972" @default.
• W4328007417 hasPublicationYear "2023" @default.
• W4328007417 type Work @default.
• W4328007417 citedByCount "1" @default.
• W4328007417 countsByYear W43280074172023 @default.
• W4328007417 crossrefType "journal-article" @default.
• W4328007417 hasAuthorship W4328007417A5045657343 @default.
• W4328007417 hasAuthorship W4328007417A5046520540 @default.
• W4328007417 hasAuthorship W4328007417A5057522977 @default.
• W4328007417 hasBestOaLocation W43280074171 @default.
• W4328007417 hasConcept C138885662 @default.
• W4328007417 hasConcept C153180895 @default.
• W4328007417 hasConcept C154945302 @default.
• W4328007417 hasConcept C27438332 @default.
• W4328007417 hasConcept C2776401178 @default.
• W4328007417 hasConcept C41008148 @default.
• W4328007417 hasConcept C41895202 @default.
• W4328007417 hasConcept C45347329 @default.
• W4328007417 hasConcept C50644808 @default.
• W4328007417 hasConcept C52622490 @default.
• W4328007417 hasConcept C70437156 @default.
• W4328007417 hasConcept C81363708 @default.
• W4328007417 hasConcept C83665646 @default.
• W4328007417 hasConceptScore W4328007417C138885662 @default.
• W4328007417 hasConceptScore W4328007417C153180895 @default.
• W4328007417 hasConceptScore W4328007417C154945302 @default.
• W4328007417 hasConceptScore W4328007417C27438332 @default.
• W4328007417 hasConceptScore W4328007417C2776401178 @default.
• W4328007417 hasConceptScore W4328007417C41008148 @default.
• W4328007417 hasConceptScore W4328007417C41895202 @default.
• W4328007417 hasConceptScore W4328007417C45347329 @default.
• W4328007417 hasConceptScore W4328007417C50644808 @default.
• W4328007417 hasConceptScore W4328007417C52622490 @default.
• W4328007417 hasConceptScore W4328007417C70437156 @default.
• W4328007417 hasConceptScore W4328007417C81363708 @default.
• W4328007417 hasConceptScore W4328007417C83665646 @default.
• W4328007417 hasFunder F4320313575 @default.
• W4328007417 hasFunder F4320324805 @default.
• W4328007417 hasLocation W43280074171 @default.
• W4328007417 hasOpenAccess W4328007417 @default.
• W4328007417 hasPrimaryLocation W43280074171 @default.
• W4328007417 hasRelatedWork W2295021132 @default.

• next