Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292995209> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4292995209 endingPage "15" @default.
- W4292995209 startingPage "1" @default.
- W4292995209 abstract "Facial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion attention lightweight wide residual network. The network first uses an improved random erasing method to preprocess facial expression images, which improves the generalizability of the model. The use of a modified depthwise separable convolution in the feature extraction network reduces the computational effort associated with the network parameters and enhances the characterization of the extracted features through a channel shuffle operation. Then, an improved bottleneck block is used to reduce the dimensionality of the upper layer network feature map to further reduce the number of network parameters while enhancing the network feature extraction capability. Finally, an optimized multiscale feature lightweight attention mechanism module is embedded to further improve the feature extractability of the network for human facial expressions. The experimental results show that the accuracy of the model is 73.21%, 98.72%, and 95.21% on FER2013, CK+ and JAFFE, respectively, with a covariance of 10.14 M. Compared with other networks, the model proposed in this paper has faster computing speed and better accuracy at the same time." @default.
- W4292995209 created "2022-08-25" @default.
- W4292995209 creator A5019564703 @default.
- W4292995209 creator A5031572073 @default.
- W4292995209 creator A5052712018 @default.
- W4292995209 date "2022-08-24" @default.
- W4292995209 modified "2023-09-29" @default.
- W4292995209 title "Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition" @default.
- W4292995209 cites W2995396423 @default.
- W4292995209 cites W2997263156 @default.
- W4292995209 cites W2998508940 @default.
- W4292995209 cites W3082115608 @default.
- W4292995209 cites W3094115835 @default.
- W4292995209 cites W3107506847 @default.
- W4292995209 cites W3111002277 @default.
- W4292995209 cites W3118007634 @default.
- W4292995209 cites W3119502086 @default.
- W4292995209 cites W3119707211 @default.
- W4292995209 cites W3134165013 @default.
- W4292995209 cites W3138248881 @default.
- W4292995209 cites W3146366485 @default.
- W4292995209 cites W3157999215 @default.
- W4292995209 cites W3163887038 @default.
- W4292995209 cites W3188609350 @default.
- W4292995209 cites W3189654580 @default.
- W4292995209 cites W3197895210 @default.
- W4292995209 cites W3205895757 @default.
- W4292995209 cites W3209195665 @default.
- W4292995209 cites W3210731676 @default.
- W4292995209 cites W3211081651 @default.
- W4292995209 cites W4200179985 @default.
- W4292995209 cites W4205620190 @default.
- W4292995209 cites W4213253068 @default.
- W4292995209 cites W4220658596 @default.
- W4292995209 cites W4220711080 @default.
- W4292995209 cites W4220932905 @default.
- W4292995209 cites W4224237609 @default.
- W4292995209 cites W4229004725 @default.
- W4292995209 doi "https://doi.org/10.1155/2022/6523234" @default.
- W4292995209 hasPublicationYear "2022" @default.
- W4292995209 type Work @default.
- W4292995209 citedByCount "0" @default.
- W4292995209 crossrefType "journal-article" @default.
- W4292995209 hasAuthorship W4292995209A5019564703 @default.
- W4292995209 hasAuthorship W4292995209A5031572073 @default.
- W4292995209 hasAuthorship W4292995209A5052712018 @default.
- W4292995209 hasBestOaLocation W42929952091 @default.
- W4292995209 hasConcept C11413529 @default.
- W4292995209 hasConcept C138885662 @default.
- W4292995209 hasConcept C149635348 @default.
- W4292995209 hasConcept C153180895 @default.
- W4292995209 hasConcept C154945302 @default.
- W4292995209 hasConcept C155512373 @default.
- W4292995209 hasConcept C195704467 @default.
- W4292995209 hasConcept C2776401178 @default.
- W4292995209 hasConcept C2780513914 @default.
- W4292995209 hasConcept C41008148 @default.
- W4292995209 hasConcept C41895202 @default.
- W4292995209 hasConcept C45347329 @default.
- W4292995209 hasConcept C50644808 @default.
- W4292995209 hasConcept C52622490 @default.
- W4292995209 hasConcept C81363708 @default.
- W4292995209 hasConceptScore W4292995209C11413529 @default.
- W4292995209 hasConceptScore W4292995209C138885662 @default.
- W4292995209 hasConceptScore W4292995209C149635348 @default.
- W4292995209 hasConceptScore W4292995209C153180895 @default.
- W4292995209 hasConceptScore W4292995209C154945302 @default.
- W4292995209 hasConceptScore W4292995209C155512373 @default.
- W4292995209 hasConceptScore W4292995209C195704467 @default.
- W4292995209 hasConceptScore W4292995209C2776401178 @default.
- W4292995209 hasConceptScore W4292995209C2780513914 @default.
- W4292995209 hasConceptScore W4292995209C41008148 @default.
- W4292995209 hasConceptScore W4292995209C41895202 @default.
- W4292995209 hasConceptScore W4292995209C45347329 @default.
- W4292995209 hasConceptScore W4292995209C50644808 @default.
- W4292995209 hasConceptScore W4292995209C52622490 @default.
- W4292995209 hasConceptScore W4292995209C81363708 @default.
- W4292995209 hasLocation W42929952091 @default.
- W4292995209 hasLocation W42929952092 @default.
- W4292995209 hasOpenAccess W4292995209 @default.
- W4292995209 hasPrimaryLocation W42929952091 @default.
- W4292995209 hasRelatedWork W2016461833 @default.
- W4292995209 hasRelatedWork W2059299633 @default.
- W4292995209 hasRelatedWork W2295021132 @default.
- W4292995209 hasRelatedWork W2732542196 @default.
- W4292995209 hasRelatedWork W2760085659 @default.
- W4292995209 hasRelatedWork W2940977206 @default.
- W4292995209 hasRelatedWork W2969680539 @default.
- W4292995209 hasRelatedWork W2977314777 @default.
- W4292995209 hasRelatedWork W2995914718 @default.
- W4292995209 hasRelatedWork W3014195705 @default.
- W4292995209 hasVolume "2022" @default.
- W4292995209 isParatext "false" @default.
- W4292995209 isRetracted "false" @default.
- W4292995209 workType "article" @default.