Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378225852> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4378225852 endingPage "6409" @default.
- W4378225852 startingPage "6409" @default.
- W4378225852 abstract "As emotional states are diverse, simply classifying them through discrete facial expressions has its limitations. Therefore, to create a facial expression recognition system for practical applications, not only must facial expressions be classified, emotional changes must be measured as continuous values. Based on the knowledge distillation structure and the teacher-bounded loss function, we propose a method to maximize the synergistic effect of jointly learning discrete and continuous emotional states of eight expression classes, valences, and arousal levels. The proposed knowledge distillation model uses Emonet, a state-of-the-art continuous estimation method, as the teacher model, and uses a lightweight network as the student model. It was confirmed that performance degradation can be minimized even though student models have multiply-accumulate operations of approximately 3.9 G and 0.3 G when using EfficientFormer and MobileNetV2, respectively, which is much less than the amount of computation required by the teacher model (16.99 G). Together with the significant improvements in computational efficiency (by 4.35 and 56.63 times using EfficientFormer and MobileNetV2, respectively), the decreases in facial expression classification accuracy were approximately 1.35% and 1.64%, respectively. Therefore, the proposed method is optimized for application-level interaction systems in terms of both the amount of computation required and the accuracy." @default.
- W4378225852 created "2023-05-26" @default.
- W4378225852 creator A5025004236 @default.
- W4378225852 creator A5085642896 @default.
- W4378225852 creator A5085880023 @default.
- W4378225852 date "2023-05-24" @default.
- W4378225852 modified "2023-10-01" @default.
- W4378225852 title "Fast and Accurate Facial Expression Image Classification and Regression Method Based on Knowledge Distillation" @default.
- W4378225852 cites W2097117768 @default.
- W4378225852 cites W2108598243 @default.
- W4378225852 cites W2146334809 @default.
- W4378225852 cites W2194775991 @default.
- W4378225852 cites W2745497104 @default.
- W4378225852 cites W2963163009 @default.
- W4378225852 cites W3007476359 @default.
- W4378225852 cites W3013080934 @default.
- W4378225852 cites W3081030157 @default.
- W4378225852 cites W3118530108 @default.
- W4378225852 cites W3137890092 @default.
- W4378225852 cites W4206411193 @default.
- W4378225852 cites W4285250231 @default.
- W4378225852 cites W4309788015 @default.
- W4378225852 cites W4312823769 @default.
- W4378225852 cites W4376278471 @default.
- W4378225852 doi "https://doi.org/10.3390/app13116409" @default.
- W4378225852 hasPublicationYear "2023" @default.
- W4378225852 type Work @default.
- W4378225852 citedByCount "2" @default.
- W4378225852 countsByYear W43782258522023 @default.
- W4378225852 crossrefType "journal-article" @default.
- W4378225852 hasAuthorship W4378225852A5025004236 @default.
- W4378225852 hasAuthorship W4378225852A5085642896 @default.
- W4378225852 hasAuthorship W4378225852A5085880023 @default.
- W4378225852 hasBestOaLocation W43782258521 @default.
- W4378225852 hasConcept C11413529 @default.
- W4378225852 hasConcept C115961682 @default.
- W4378225852 hasConcept C119857082 @default.
- W4378225852 hasConcept C134306372 @default.
- W4378225852 hasConcept C153180895 @default.
- W4378225852 hasConcept C154945302 @default.
- W4378225852 hasConcept C185592680 @default.
- W4378225852 hasConcept C195704467 @default.
- W4378225852 hasConcept C199360897 @default.
- W4378225852 hasConcept C204030448 @default.
- W4378225852 hasConcept C33923547 @default.
- W4378225852 hasConcept C34388435 @default.
- W4378225852 hasConcept C41008148 @default.
- W4378225852 hasConcept C43617362 @default.
- W4378225852 hasConcept C45374587 @default.
- W4378225852 hasConcept C90559484 @default.
- W4378225852 hasConceptScore W4378225852C11413529 @default.
- W4378225852 hasConceptScore W4378225852C115961682 @default.
- W4378225852 hasConceptScore W4378225852C119857082 @default.
- W4378225852 hasConceptScore W4378225852C134306372 @default.
- W4378225852 hasConceptScore W4378225852C153180895 @default.
- W4378225852 hasConceptScore W4378225852C154945302 @default.
- W4378225852 hasConceptScore W4378225852C185592680 @default.
- W4378225852 hasConceptScore W4378225852C195704467 @default.
- W4378225852 hasConceptScore W4378225852C199360897 @default.
- W4378225852 hasConceptScore W4378225852C204030448 @default.
- W4378225852 hasConceptScore W4378225852C33923547 @default.
- W4378225852 hasConceptScore W4378225852C34388435 @default.
- W4378225852 hasConceptScore W4378225852C41008148 @default.
- W4378225852 hasConceptScore W4378225852C43617362 @default.
- W4378225852 hasConceptScore W4378225852C45374587 @default.
- W4378225852 hasConceptScore W4378225852C90559484 @default.
- W4378225852 hasIssue "11" @default.
- W4378225852 hasLocation W43782258521 @default.
- W4378225852 hasOpenAccess W4378225852 @default.
- W4378225852 hasPrimaryLocation W43782258521 @default.
- W4378225852 hasRelatedWork W1497005071 @default.
- W4378225852 hasRelatedWork W2169126105 @default.
- W4378225852 hasRelatedWork W2356303892 @default.
- W4378225852 hasRelatedWork W2961085424 @default.
- W4378225852 hasRelatedWork W2996482199 @default.
- W4378225852 hasRelatedWork W3042772878 @default.
- W4378225852 hasRelatedWork W3096509145 @default.
- W4378225852 hasRelatedWork W3194078543 @default.
- W4378225852 hasRelatedWork W2201024316 @default.
- W4378225852 hasRelatedWork W2217461731 @default.
- W4378225852 hasVolume "13" @default.
- W4378225852 isParatext "false" @default.
- W4378225852 isRetracted "false" @default.
- W4378225852 workType "article" @default.