Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383751018> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4383751018 endingPage "70872" @default.
- W4383751018 startingPage "70865" @default.
- W4383751018 abstract "The ability to recognize facial expressions using computer vision is a crucial task, with numerous potential applications. Although deep neural networks have achieved high performance, it is still difficult to use them in the recognition of facial expressions. This is because different facial expressions have varying degrees of similarities among themselves, and numerous variations cause diversity in the same facial images. In this study, we propose a novel divide-and-conquer-based learning strategy to improve the performance of facial expression recognition (FER). The face area in an image was detected using MobileNet, and a ResNet-18 model was used as a backbone deep neural network for recognizing facial expressions. Thereafter, groups that included similar facial expressions were categorized by analyzing the confusion matrix, which is the inference result of the trained ResNet-18 model, and these similar facial expression groups were utilized to re-train the deep learning model. In the experiments, the proposed method was evaluated using two thermal (Tufts and RWTH) and two RGB (RAF and FER2013) datasets, and higher FER performances, which were 97.75% for Tufts, 86.11% for RWTH, 90.81% for RAF, and 77.83% for FER2013, were achieved. As such, the proposed method can accurately classify large amounts of facial expression data." @default.
- W4383751018 created "2023-07-11" @default.
- W4383751018 creator A5027028606 @default.
- W4383751018 creator A5057429218 @default.
- W4383751018 date "2023-01-01" @default.
- W4383751018 modified "2023-10-18" @default.
- W4383751018 title "CNN Learning Strategy for Recognizing Facial Expressions" @default.
- W4383751018 cites W1034159276 @default.
- W4383751018 cites W1964504906 @default.
- W4383751018 cites W2032254851 @default.
- W4383751018 cites W2070375989 @default.
- W4383751018 cites W2103943262 @default.
- W4383751018 cites W2112796928 @default.
- W4383751018 cites W2117539524 @default.
- W4383751018 cites W2145310492 @default.
- W4383751018 cites W2165698076 @default.
- W4383751018 cites W2194775991 @default.
- W4383751018 cites W2572324811 @default.
- W4383751018 cites W2581082139 @default.
- W4383751018 cites W2584487694 @default.
- W4383751018 cites W2744909235 @default.
- W4383751018 cites W2799041689 @default.
- W4383751018 cites W2809598685 @default.
- W4383751018 cites W2889978276 @default.
- W4383751018 cites W2902038035 @default.
- W4383751018 cites W2906004658 @default.
- W4383751018 cites W2921644959 @default.
- W4383751018 cites W2945731770 @default.
- W4383751018 cites W2964050365 @default.
- W4383751018 cites W2970124028 @default.
- W4383751018 cites W2988916019 @default.
- W4383751018 cites W3023340129 @default.
- W4383751018 cites W3034552680 @default.
- W4383751018 cites W3036381403 @default.
- W4383751018 cites W3044580164 @default.
- W4383751018 cites W3093232475 @default.
- W4383751018 cites W3161346624 @default.
- W4383751018 cites W4200610936 @default.
- W4383751018 cites W4205166102 @default.
- W4383751018 cites W4210729356 @default.
- W4383751018 cites W4283826580 @default.
- W4383751018 cites W4291278543 @default.
- W4383751018 cites W4311414773 @default.
- W4383751018 cites W4312465353 @default.
- W4383751018 cites W4360602654 @default.
- W4383751018 doi "https://doi.org/10.1109/access.2023.3294099" @default.
- W4383751018 hasPublicationYear "2023" @default.
- W4383751018 type Work @default.
- W4383751018 citedByCount "1" @default.
- W4383751018 crossrefType "journal-article" @default.
- W4383751018 hasAuthorship W4383751018A5027028606 @default.
- W4383751018 hasAuthorship W4383751018A5057429218 @default.
- W4383751018 hasBestOaLocation W43837510181 @default.
- W4383751018 hasConcept C108583219 @default.
- W4383751018 hasConcept C144024400 @default.
- W4383751018 hasConcept C153180895 @default.
- W4383751018 hasConcept C154945302 @default.
- W4383751018 hasConcept C195704467 @default.
- W4383751018 hasConcept C2776214188 @default.
- W4383751018 hasConcept C2779304628 @default.
- W4383751018 hasConcept C28490314 @default.
- W4383751018 hasConcept C2987714656 @default.
- W4383751018 hasConcept C31510193 @default.
- W4383751018 hasConcept C31972630 @default.
- W4383751018 hasConcept C36289849 @default.
- W4383751018 hasConcept C41008148 @default.
- W4383751018 hasConcept C50644808 @default.
- W4383751018 hasConceptScore W4383751018C108583219 @default.
- W4383751018 hasConceptScore W4383751018C144024400 @default.
- W4383751018 hasConceptScore W4383751018C153180895 @default.
- W4383751018 hasConceptScore W4383751018C154945302 @default.
- W4383751018 hasConceptScore W4383751018C195704467 @default.
- W4383751018 hasConceptScore W4383751018C2776214188 @default.
- W4383751018 hasConceptScore W4383751018C2779304628 @default.
- W4383751018 hasConceptScore W4383751018C28490314 @default.
- W4383751018 hasConceptScore W4383751018C2987714656 @default.
- W4383751018 hasConceptScore W4383751018C31510193 @default.
- W4383751018 hasConceptScore W4383751018C31972630 @default.
- W4383751018 hasConceptScore W4383751018C36289849 @default.
- W4383751018 hasConceptScore W4383751018C41008148 @default.
- W4383751018 hasConceptScore W4383751018C50644808 @default.
- W4383751018 hasLocation W43837510181 @default.
- W4383751018 hasOpenAccess W4383751018 @default.
- W4383751018 hasPrimaryLocation W43837510181 @default.
- W4383751018 hasRelatedWork W1775397219 @default.
- W4383751018 hasRelatedWork W1899364738 @default.
- W4383751018 hasRelatedWork W2103413230 @default.
- W4383751018 hasRelatedWork W2248182120 @default.
- W4383751018 hasRelatedWork W2347601237 @default.
- W4383751018 hasRelatedWork W2807287270 @default.
- W4383751018 hasRelatedWork W2897995864 @default.
- W4383751018 hasRelatedWork W2908959303 @default.
- W4383751018 hasRelatedWork W3194078543 @default.
- W4383751018 hasRelatedWork W43171467 @default.
- W4383751018 hasVolume "11" @default.
- W4383751018 isParatext "false" @default.
- W4383751018 isRetracted "false" @default.
- W4383751018 workType "article" @default.