Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892918413> ?p ?o ?g. }
- W2892918413 abstract "Facial expression recognition has significant application value in fields such as human-computer interaction. Recently, Convolutional Neural Networks (CNNs) have been widely utilized for feature extraction and expression recognition. Network ensemble is an important step to improve recognition performance. To improve the inefficiency of existing ensemble strategy, we propose a new ensemble method to efficiently find networks with complementary capabilities. The proposed method is verified on two groups of CNNs with different depth (eight 5-layer shallow CNNs and twelve 11-layer deep VGGNet variants) trained on FER-2013 and RAF-DB, respectively. Experimental results demonstrate that the proposed method achieves the highest recognition accuracy of 74.14% and 85.46% on FER-2013 and RAF-DB database, respectively, to the best of our knowledge, outperforms state-of-the-art CNN-based facial expression recognition methods. In addition, our method also obtains a competitive result of the mean diagonal value in confusion matrix on RAF-DB test set." @default.
- W2892918413 created "2018-10-05" @default.
- W2892918413 creator A5027269981 @default.
- W2892918413 creator A5046134001 @default.
- W2892918413 date "2018-01-01" @default.
- W2892918413 modified "2023-09-25" @default.
- W2892918413 title "Improving Ensemble Learning Performance with Complementary Neural Networks for Facial Expression Recognition" @default.
- W2892918413 cites W1903029394 @default.
- W2892918413 cites W1908020446 @default.
- W2892918413 cites W1974210421 @default.
- W2892918413 cites W1976948919 @default.
- W2892918413 cites W1998294030 @default.
- W2892918413 cites W2014185685 @default.
- W2892918413 cites W2091451699 @default.
- W2892918413 cites W2097117768 @default.
- W2892918413 cites W2135293965 @default.
- W2892918413 cites W2138206939 @default.
- W2892918413 cites W2157285372 @default.
- W2892918413 cites W2160815625 @default.
- W2892918413 cites W2217426128 @default.
- W2892918413 cites W2244142460 @default.
- W2892918413 cites W2246249023 @default.
- W2892918413 cites W2280370717 @default.
- W2892918413 cites W2480418144 @default.
- W2892918413 cites W2486769752 @default.
- W2892918413 cites W2520774990 @default.
- W2892918413 cites W2730601341 @default.
- W2892918413 cites W2738672149 @default.
- W2892918413 cites W2744909235 @default.
- W2892918413 cites W2964014798 @default.
- W2892918413 cites W4241005218 @default.
- W2892918413 doi "https://doi.org/10.1007/978-3-030-01418-6_73" @default.
- W2892918413 hasPublicationYear "2018" @default.
- W2892918413 type Work @default.
- W2892918413 sameAs 2892918413 @default.
- W2892918413 citedByCount "0" @default.
- W2892918413 crossrefType "book-chapter" @default.
- W2892918413 hasAuthorship W2892918413A5027269981 @default.
- W2892918413 hasAuthorship W2892918413A5046134001 @default.
- W2892918413 hasConcept C108583219 @default.
- W2892918413 hasConcept C138602881 @default.
- W2892918413 hasConcept C138885662 @default.
- W2892918413 hasConcept C153180895 @default.
- W2892918413 hasConcept C154945302 @default.
- W2892918413 hasConcept C169903167 @default.
- W2892918413 hasConcept C178790620 @default.
- W2892918413 hasConcept C185592680 @default.
- W2892918413 hasConcept C199360897 @default.
- W2892918413 hasConcept C2776401178 @default.
- W2892918413 hasConcept C2779227376 @default.
- W2892918413 hasConcept C2987714656 @default.
- W2892918413 hasConcept C31510193 @default.
- W2892918413 hasConcept C41008148 @default.
- W2892918413 hasConcept C41895202 @default.
- W2892918413 hasConcept C52622490 @default.
- W2892918413 hasConcept C81363708 @default.
- W2892918413 hasConcept C90559484 @default.
- W2892918413 hasConceptScore W2892918413C108583219 @default.
- W2892918413 hasConceptScore W2892918413C138602881 @default.
- W2892918413 hasConceptScore W2892918413C138885662 @default.
- W2892918413 hasConceptScore W2892918413C153180895 @default.
- W2892918413 hasConceptScore W2892918413C154945302 @default.
- W2892918413 hasConceptScore W2892918413C169903167 @default.
- W2892918413 hasConceptScore W2892918413C178790620 @default.
- W2892918413 hasConceptScore W2892918413C185592680 @default.
- W2892918413 hasConceptScore W2892918413C199360897 @default.
- W2892918413 hasConceptScore W2892918413C2776401178 @default.
- W2892918413 hasConceptScore W2892918413C2779227376 @default.
- W2892918413 hasConceptScore W2892918413C2987714656 @default.
- W2892918413 hasConceptScore W2892918413C31510193 @default.
- W2892918413 hasConceptScore W2892918413C41008148 @default.
- W2892918413 hasConceptScore W2892918413C41895202 @default.
- W2892918413 hasConceptScore W2892918413C52622490 @default.
- W2892918413 hasConceptScore W2892918413C81363708 @default.
- W2892918413 hasConceptScore W2892918413C90559484 @default.
- W2892918413 hasLocation W28929184131 @default.
- W2892918413 hasOpenAccess W2892918413 @default.
- W2892918413 hasPrimaryLocation W28929184131 @default.
- W2892918413 hasRelatedWork W2191045312 @default.
- W2892918413 hasRelatedWork W2231516625 @default.
- W2892918413 hasRelatedWork W2246249023 @default.
- W2892918413 hasRelatedWork W2614041639 @default.
- W2892918413 hasRelatedWork W2767013295 @default.
- W2892918413 hasRelatedWork W2886900713 @default.
- W2892918413 hasRelatedWork W2902923584 @default.
- W2892918413 hasRelatedWork W2915046743 @default.
- W2892918413 hasRelatedWork W2952910595 @default.
- W2892918413 hasRelatedWork W2989573210 @default.
- W2892918413 hasRelatedWork W3010490140 @default.
- W2892918413 hasRelatedWork W3011242243 @default.
- W2892918413 hasRelatedWork W3036455739 @default.
- W2892918413 hasRelatedWork W3039081519 @default.
- W2892918413 hasRelatedWork W3089733125 @default.
- W2892918413 hasRelatedWork W3105627983 @default.
- W2892918413 hasRelatedWork W3157230091 @default.
- W2892918413 hasRelatedWork W3183413734 @default.
- W2892918413 hasRelatedWork W3208592491 @default.
- W2892918413 hasRelatedWork W3211240005 @default.
- W2892918413 isParatext "false" @default.
- W2892918413 isRetracted "false" @default.