Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327779834> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4327779834 endingPage "17" @default.
- W4327779834 startingPage "3" @default.
- W4327779834 abstract "Facial Expression Recognition (FER) is increasingly gaining importance in various emerging affective computing applications. In this article, we propose a Facial Expression Recognition (FER) method, based on kernel enhanced Convolutional Neural Network (CNN) model. Our method improves the performance of a CNN without increasing its depth nor its width. It consists of expanding the linear kernel function, used at different levels of a CNN. The expansion is performed by combining multiple polynomial kernels with different degrees. By doing so, we allow the network to automatically learn the suitable kernel for the specific target task. The network can either uses one specific kernel or a combination of multiple kernels. In the latter case we will have a kernel in the form of a Taylor series kernel. This kernel function is more sensitive to subtle details than the linear one and is able to better fit the input data. The sensitivity to subtle visual details is a key factor for a better facial expression recognition. Furthermore, this method uses the same number of parameters as a convolution layer or a dense layer. The experiments conducted on FER datasets show that the use of our method allows the network to outperform ordinary CNNs." @default.
- W4327779834 created "2023-03-19" @default.
- W4327779834 creator A5010455422 @default.
- W4327779834 creator A5031504099 @default.
- W4327779834 creator A5072667310 @default.
- W4327779834 creator A5091159751 @default.
- W4327779834 date "2023-01-01" @default.
- W4327779834 modified "2023-10-14" @default.
- W4327779834 title "Expanding Convolutional Neural Network Kernel for Facial Expression Recognition" @default.
- W4327779834 cites W1677182931 @default.
- W4327779834 cites W1887369574 @default.
- W4327779834 cites W2041616772 @default.
- W4327779834 cites W2140095548 @default.
- W4327779834 cites W2738672149 @default.
- W4327779834 cites W2740620254 @default.
- W4327779834 cites W2963544278 @default.
- W4327779834 cites W2964347177 @default.
- W4327779834 cites W3082416619 @default.
- W4327779834 cites W3091302562 @default.
- W4327779834 cites W3103732786 @default.
- W4327779834 cites W3194062877 @default.
- W4327779834 cites W4206291413 @default.
- W4327779834 cites W4239510810 @default.
- W4327779834 cites W4283273830 @default.
- W4327779834 doi "https://doi.org/10.1007/978-3-031-28540-0_1" @default.
- W4327779834 hasPublicationYear "2023" @default.
- W4327779834 type Work @default.
- W4327779834 citedByCount "0" @default.
- W4327779834 crossrefType "book-chapter" @default.
- W4327779834 hasAuthorship W4327779834A5010455422 @default.
- W4327779834 hasAuthorship W4327779834A5031504099 @default.
- W4327779834 hasAuthorship W4327779834A5072667310 @default.
- W4327779834 hasAuthorship W4327779834A5091159751 @default.
- W4327779834 hasConcept C114614502 @default.
- W4327779834 hasConcept C122280245 @default.
- W4327779834 hasConcept C12267149 @default.
- W4327779834 hasConcept C140417398 @default.
- W4327779834 hasConcept C153180895 @default.
- W4327779834 hasConcept C154945302 @default.
- W4327779834 hasConcept C160446489 @default.
- W4327779834 hasConcept C195704467 @default.
- W4327779834 hasConcept C33923547 @default.
- W4327779834 hasConcept C41008148 @default.
- W4327779834 hasConcept C45347329 @default.
- W4327779834 hasConcept C50644808 @default.
- W4327779834 hasConcept C74193536 @default.
- W4327779834 hasConcept C75866337 @default.
- W4327779834 hasConcept C81363708 @default.
- W4327779834 hasConceptScore W4327779834C114614502 @default.
- W4327779834 hasConceptScore W4327779834C122280245 @default.
- W4327779834 hasConceptScore W4327779834C12267149 @default.
- W4327779834 hasConceptScore W4327779834C140417398 @default.
- W4327779834 hasConceptScore W4327779834C153180895 @default.
- W4327779834 hasConceptScore W4327779834C154945302 @default.
- W4327779834 hasConceptScore W4327779834C160446489 @default.
- W4327779834 hasConceptScore W4327779834C195704467 @default.
- W4327779834 hasConceptScore W4327779834C33923547 @default.
- W4327779834 hasConceptScore W4327779834C41008148 @default.
- W4327779834 hasConceptScore W4327779834C45347329 @default.
- W4327779834 hasConceptScore W4327779834C50644808 @default.
- W4327779834 hasConceptScore W4327779834C74193536 @default.
- W4327779834 hasConceptScore W4327779834C75866337 @default.
- W4327779834 hasConceptScore W4327779834C81363708 @default.
- W4327779834 hasLocation W43277798341 @default.
- W4327779834 hasOpenAccess W4327779834 @default.
- W4327779834 hasPrimaryLocation W43277798341 @default.
- W4327779834 hasRelatedWork W1550105856 @default.
- W4327779834 hasRelatedWork W1558903433 @default.
- W4327779834 hasRelatedWork W2090258569 @default.
- W4327779834 hasRelatedWork W2092427412 @default.
- W4327779834 hasRelatedWork W2097184312 @default.
- W4327779834 hasRelatedWork W2121506664 @default.
- W4327779834 hasRelatedWork W2168277226 @default.
- W4327779834 hasRelatedWork W2560973894 @default.
- W4327779834 hasRelatedWork W2604913466 @default.
- W4327779834 hasRelatedWork W3008135798 @default.
- W4327779834 isParatext "false" @default.
- W4327779834 isRetracted "false" @default.
- W4327779834 workType "book-chapter" @default.