FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1631012836> ?p ?o ?g. }

• W1631012836 abstract "A new architecture based on the Multi-channel Convolutional Neural Network (MCCNN) is proposed for recognizing facial expressions. Two hard-coded feature extractors are replaced by a single channel which is partially trained in an unsupervised fashion as a Convolutional Autoencoder (CAE). One additional channel that contains a standard CNN is left unchanged. Information from both channels converges in a fully connected layer and is then used for classification. We perform two distinct experiments on the JAFFE dataset (leave-one-out and ten-fold cross validation) to evaluate our architecture. Our comparison with the previous model that uses hard-coded Sobel features shows that an additional channel of information with unsupervised learning can significantly boost accuracy and reduce the overall training time. Furthermore, experimental results are compared with benchmarks from the literature showing that our method provides state-of-the-art recognition rates for facial expressions. Our method outperforms previously published methods that used hand-crafted features by a large margin." @default.
• W1631012836 created "2016-06-24" @default.
• W1631012836 creator A5028426362 @default.
• W1631012836 creator A5033486668 @default.
• W1631012836 creator A5073057205 @default.
• W1631012836 date "2015-07-01" @default.
• W1631012836 modified "2023-10-11" @default.
• W1631012836 title "Face expression recognition with a 2-channel Convolutional Neural Network" @default.
• W1631012836 cites W16066432 @default.
• W1631012836 cites W1849277567 @default.
• W1631012836 cites W1965037862 @default.
• W1631012836 cites W1977148657 @default.
• W1631012836 cites W1981918162 @default.
• W1631012836 cites W1983364832 @default.
• W1631012836 cites W1986976163 @default.
• W1631012836 cites W1990537606 @default.
• W1631012836 cites W2003238582 @default.
• W1631012836 cites W2025296793 @default.
• W1631012836 cites W2033909204 @default.
• W1631012836 cites W2074772891 @default.
• W1631012836 cites W2091328698 @default.
• W1631012836 cites W2105793180 @default.
• W1631012836 cites W2106115875 @default.
• W1631012836 cites W2112796928 @default.
• W1631012836 cites W2114759801 @default.
• W1631012836 cites W2114882772 @default.
• W1631012836 cites W2120002154 @default.
• W1631012836 cites W2136922672 @default.
• W1631012836 cites W2137234026 @default.
• W1631012836 cites W2139427956 @default.
• W1631012836 cites W2141125852 @default.
• W1631012836 cites W2144354855 @default.
• W1631012836 cites W2163922914 @default.
• W1631012836 cites W2169835481 @default.
• W1631012836 cites W2170345688 @default.
• W1631012836 doi "https://doi.org/10.1109/ijcnn.2015.7280539" @default.
• W1631012836 hasPublicationYear "2015" @default.
• W1631012836 type Work @default.
• W1631012836 sameAs 1631012836 @default.
• W1631012836 citedByCount "79" @default.
• W1631012836 countsByYear W16310128362016 @default.
• W1631012836 countsByYear W16310128362017 @default.
• W1631012836 countsByYear W16310128362018 @default.
• W1631012836 countsByYear W16310128362019 @default.
• W1631012836 countsByYear W16310128362020 @default.
• W1631012836 countsByYear W16310128362021 @default.
• W1631012836 countsByYear W16310128362022 @default.
• W1631012836 countsByYear W16310128362023 @default.
• W1631012836 crossrefType "proceedings-article" @default.
• W1631012836 hasAuthorship W1631012836A5028426362 @default.
• W1631012836 hasAuthorship W1631012836A5033486668 @default.
• W1631012836 hasAuthorship W1631012836A5073057205 @default.
• W1631012836 hasConcept C101738243 @default.
• W1631012836 hasConcept C108583219 @default.
• W1631012836 hasConcept C119857082 @default.
• W1631012836 hasConcept C127162648 @default.
• W1631012836 hasConcept C138885662 @default.
• W1631012836 hasConcept C144024400 @default.
• W1631012836 hasConcept C153180895 @default.
• W1631012836 hasConcept C154945302 @default.
• W1631012836 hasConcept C195704467 @default.
• W1631012836 hasConcept C2776401178 @default.
• W1631012836 hasConcept C2779304628 @default.
• W1631012836 hasConcept C31258907 @default.
• W1631012836 hasConcept C31510193 @default.
• W1631012836 hasConcept C36289849 @default.
• W1631012836 hasConcept C41008148 @default.
• W1631012836 hasConcept C41895202 @default.
• W1631012836 hasConcept C52622490 @default.
• W1631012836 hasConcept C774472 @default.
• W1631012836 hasConcept C8038995 @default.
• W1631012836 hasConcept C81363708 @default.
• W1631012836 hasConceptScore W1631012836C101738243 @default.
• W1631012836 hasConceptScore W1631012836C108583219 @default.
• W1631012836 hasConceptScore W1631012836C119857082 @default.
• W1631012836 hasConceptScore W1631012836C127162648 @default.
• W1631012836 hasConceptScore W1631012836C138885662 @default.
• W1631012836 hasConceptScore W1631012836C144024400 @default.
• W1631012836 hasConceptScore W1631012836C153180895 @default.
• W1631012836 hasConceptScore W1631012836C154945302 @default.
• W1631012836 hasConceptScore W1631012836C195704467 @default.
• W1631012836 hasConceptScore W1631012836C2776401178 @default.
• W1631012836 hasConceptScore W1631012836C2779304628 @default.
• W1631012836 hasConceptScore W1631012836C31258907 @default.
• W1631012836 hasConceptScore W1631012836C31510193 @default.
• W1631012836 hasConceptScore W1631012836C36289849 @default.
• W1631012836 hasConceptScore W1631012836C41008148 @default.
• W1631012836 hasConceptScore W1631012836C41895202 @default.
• W1631012836 hasConceptScore W1631012836C52622490 @default.
• W1631012836 hasConceptScore W1631012836C774472 @default.
• W1631012836 hasConceptScore W1631012836C8038995 @default.
• W1631012836 hasConceptScore W1631012836C81363708 @default.
• W1631012836 hasLocation W16310128361 @default.
• W1631012836 hasOpenAccess W1631012836 @default.
• W1631012836 hasPrimaryLocation W16310128361 @default.
• W1631012836 hasRelatedWork W1775397219 @default.
• W1631012836 hasRelatedWork W2279398222 @default.
• W1631012836 hasRelatedWork W2592385986 @default.
• W1631012836 hasRelatedWork W2610906757 @default.
• W1631012836 hasRelatedWork W2738823376 @default.

• next