Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955557105> ?p ?o ?g. }
- W2955557105 endingPage "77824" @default.
- W2955557105 startingPage "77816" @default.
- W2955557105 abstract "This paper deals with the problem of training convolutional neural networks (CNNs) with facial action units (AUs). In particular, we focus on the imbalance problem of the training datasets for facial emotion classification. Since training a CNN with an imbalanced dataset tends to yield a learning bias toward the major classes and eventually leads to deterioration in the classification accuracy, it is required to increase the number of training images for the minority classes to have evenly distributed training images over all classes. However, it is difficult to find the images with a similar facial emotion for the oversampling. In this paper, we propose to use the AU features to retrieve an image with a similar emotion. The query selection from the minority class and the AU-based retrieval processes repeat until the numbers of training data over all classes are balanced. Also, to improve the classification accuracy, the AU features are fused with the CNN features to train a support vector machine (SVM) for final classification. The experiments have been conducted on three imbalanced facial image datasets, RAF-DB, FER2013, and ExpW. The results demonstrate that the CNNs trained with the AU features improve the classification accuracy by 3%-4%." @default.
- W2955557105 created "2019-07-12" @default.
- W2955557105 creator A5007348138 @default.
- W2955557105 creator A5049278507 @default.
- W2955557105 date "2019-01-01" @default.
- W2955557105 modified "2023-10-03" @default.
- W2955557105 title "Facial Action Units for Training Convolutional Neural Networks" @default.
- W2955557105 cites W1941659294 @default.
- W2955557105 cites W2033184625 @default.
- W2955557105 cites W2096945460 @default.
- W2955557105 cites W2097117768 @default.
- W2955557105 cites W2112796928 @default.
- W2955557105 cites W2117539524 @default.
- W2955557105 cites W2123402141 @default.
- W2955557105 cites W2148143831 @default.
- W2955557105 cites W2294246171 @default.
- W2955557105 cites W2325078646 @default.
- W2955557105 cites W2325939864 @default.
- W2955557105 cites W2345322310 @default.
- W2955557105 cites W2407034139 @default.
- W2955557105 cites W2426725031 @default.
- W2955557105 cites W2436394355 @default.
- W2955557105 cites W2440599146 @default.
- W2955557105 cites W2551429935 @default.
- W2955557105 cites W2738672149 @default.
- W2955557105 cites W2749768874 @default.
- W2955557105 cites W2755308081 @default.
- W2955557105 cites W2763110968 @default.
- W2955557105 cites W2767106145 @default.
- W2955557105 cites W2788588508 @default.
- W2955557105 cites W2791757685 @default.
- W2955557105 cites W2798285655 @default.
- W2955557105 cites W2799949160 @default.
- W2955557105 cites W2810154616 @default.
- W2955557105 cites W2887015488 @default.
- W2955557105 cites W2891511425 @default.
- W2955557105 cites W2896206046 @default.
- W2955557105 cites W2898604512 @default.
- W2955557105 cites W2899247293 @default.
- W2955557105 cites W2899412438 @default.
- W2955557105 cites W2907178645 @default.
- W2955557105 cites W2963446712 @default.
- W2955557105 cites W2964347177 @default.
- W2955557105 cites W2889120127 @default.
- W2955557105 doi "https://doi.org/10.1109/access.2019.2921241" @default.
- W2955557105 hasPublicationYear "2019" @default.
- W2955557105 type Work @default.
- W2955557105 sameAs 2955557105 @default.
- W2955557105 citedByCount "10" @default.
- W2955557105 countsByYear W29555571052019 @default.
- W2955557105 countsByYear W29555571052020 @default.
- W2955557105 countsByYear W29555571052021 @default.
- W2955557105 countsByYear W29555571052022 @default.
- W2955557105 countsByYear W29555571052023 @default.
- W2955557105 crossrefType "journal-article" @default.
- W2955557105 hasAuthorship W2955557105A5007348138 @default.
- W2955557105 hasAuthorship W2955557105A5049278507 @default.
- W2955557105 hasBestOaLocation W29555571051 @default.
- W2955557105 hasConcept C115961682 @default.
- W2955557105 hasConcept C119857082 @default.
- W2955557105 hasConcept C120665830 @default.
- W2955557105 hasConcept C121332964 @default.
- W2955557105 hasConcept C12267149 @default.
- W2955557105 hasConcept C144024400 @default.
- W2955557105 hasConcept C153180895 @default.
- W2955557105 hasConcept C153294291 @default.
- W2955557105 hasConcept C154945302 @default.
- W2955557105 hasConcept C192209626 @default.
- W2955557105 hasConcept C197323446 @default.
- W2955557105 hasConcept C2776257435 @default.
- W2955557105 hasConcept C2777211547 @default.
- W2955557105 hasConcept C2777212361 @default.
- W2955557105 hasConcept C2779304628 @default.
- W2955557105 hasConcept C31258907 @default.
- W2955557105 hasConcept C36289849 @default.
- W2955557105 hasConcept C41008148 @default.
- W2955557105 hasConcept C75294576 @default.
- W2955557105 hasConcept C81363708 @default.
- W2955557105 hasConceptScore W2955557105C115961682 @default.
- W2955557105 hasConceptScore W2955557105C119857082 @default.
- W2955557105 hasConceptScore W2955557105C120665830 @default.
- W2955557105 hasConceptScore W2955557105C121332964 @default.
- W2955557105 hasConceptScore W2955557105C12267149 @default.
- W2955557105 hasConceptScore W2955557105C144024400 @default.
- W2955557105 hasConceptScore W2955557105C153180895 @default.
- W2955557105 hasConceptScore W2955557105C153294291 @default.
- W2955557105 hasConceptScore W2955557105C154945302 @default.
- W2955557105 hasConceptScore W2955557105C192209626 @default.
- W2955557105 hasConceptScore W2955557105C197323446 @default.
- W2955557105 hasConceptScore W2955557105C2776257435 @default.
- W2955557105 hasConceptScore W2955557105C2777211547 @default.
- W2955557105 hasConceptScore W2955557105C2777212361 @default.
- W2955557105 hasConceptScore W2955557105C2779304628 @default.
- W2955557105 hasConceptScore W2955557105C31258907 @default.
- W2955557105 hasConceptScore W2955557105C36289849 @default.
- W2955557105 hasConceptScore W2955557105C41008148 @default.
- W2955557105 hasConceptScore W2955557105C75294576 @default.
- W2955557105 hasConceptScore W2955557105C81363708 @default.