Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896863246> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2896863246 abstract "In this work we propose a novel method to address illumination invariance for racial expression recognition. We propose a Deep Convolutional Network (CNN) pre-trained as a Deep Stacked Convolutional Autoencoder (SCAE) in a greedy layer-wise unsupervised fashion. The SCAE model learns to encode racial expression images and produce a feature vector with relatively similar illumination, regardless of the luminance level of the input image. Moreover, we propose fine-tuning the stacked shallow autoencoders after each one of these is trained greedily, rather than just at the end, and show that this approach significantly improves the set of illumination invariant features learnt by the SCAE. Finally, we propose the use of a variant rectifier linear unit transfer function that helps the SCAE model reduce or increase the illumination of images with high or low luminance, and show that the lower and upper bounds greatly influence classification performance. The method proposed provides an increase in classification accuracy of 4% on the KDEF dataset and 8% on the CK+ dataset." @default.
- W2896863246 created "2018-10-26" @default.
- W2896863246 creator A5015102986 @default.
- W2896863246 creator A5059233518 @default.
- W2896863246 creator A5061630027 @default.
- W2896863246 creator A5076935774 @default.
- W2896863246 date "2018-07-01" @default.
- W2896863246 modified "2023-10-01" @default.
- W2896863246 title "Deep Learning for Illumination Invariant Facial Expression Recognition" @default.
- W2896863246 cites W1968308206 @default.
- W2896863246 cites W1984389259 @default.
- W2896863246 cites W2061646053 @default.
- W2896863246 cites W2071411989 @default.
- W2896863246 cites W2103943262 @default.
- W2896863246 cites W2134860945 @default.
- W2896863246 cites W2296659146 @default.
- W2896863246 cites W2568221424 @default.
- W2896863246 cites W2614101701 @default.
- W2896863246 cites W2782360958 @default.
- W2896863246 cites W2963170034 @default.
- W2896863246 doi "https://doi.org/10.1109/ijcnn.2018.8489123" @default.
- W2896863246 hasPublicationYear "2018" @default.
- W2896863246 type Work @default.
- W2896863246 sameAs 2896863246 @default.
- W2896863246 citedByCount "12" @default.
- W2896863246 countsByYear W28968632462018 @default.
- W2896863246 countsByYear W28968632462019 @default.
- W2896863246 countsByYear W28968632462020 @default.
- W2896863246 countsByYear W28968632462021 @default.
- W2896863246 countsByYear W28968632462022 @default.
- W2896863246 crossrefType "proceedings-article" @default.
- W2896863246 hasAuthorship W2896863246A5015102986 @default.
- W2896863246 hasAuthorship W2896863246A5059233518 @default.
- W2896863246 hasAuthorship W2896863246A5061630027 @default.
- W2896863246 hasAuthorship W2896863246A5076935774 @default.
- W2896863246 hasConcept C108583219 @default.
- W2896863246 hasConcept C153180895 @default.
- W2896863246 hasConcept C154945302 @default.
- W2896863246 hasConcept C190470478 @default.
- W2896863246 hasConcept C195704467 @default.
- W2896863246 hasConcept C2987714656 @default.
- W2896863246 hasConcept C31510193 @default.
- W2896863246 hasConcept C31972630 @default.
- W2896863246 hasConcept C33923547 @default.
- W2896863246 hasConcept C37914503 @default.
- W2896863246 hasConcept C41008148 @default.
- W2896863246 hasConceptScore W2896863246C108583219 @default.
- W2896863246 hasConceptScore W2896863246C153180895 @default.
- W2896863246 hasConceptScore W2896863246C154945302 @default.
- W2896863246 hasConceptScore W2896863246C190470478 @default.
- W2896863246 hasConceptScore W2896863246C195704467 @default.
- W2896863246 hasConceptScore W2896863246C2987714656 @default.
- W2896863246 hasConceptScore W2896863246C31510193 @default.
- W2896863246 hasConceptScore W2896863246C31972630 @default.
- W2896863246 hasConceptScore W2896863246C33923547 @default.
- W2896863246 hasConceptScore W2896863246C37914503 @default.
- W2896863246 hasConceptScore W2896863246C41008148 @default.
- W2896863246 hasLocation W28968632461 @default.
- W2896863246 hasOpenAccess W2896863246 @default.
- W2896863246 hasPrimaryLocation W28968632461 @default.
- W2896863246 hasRelatedWork W1591965711 @default.
- W2896863246 hasRelatedWork W1982770690 @default.
- W2896863246 hasRelatedWork W2025991752 @default.
- W2896863246 hasRelatedWork W2353481744 @default.
- W2896863246 hasRelatedWork W2503569529 @default.
- W2896863246 hasRelatedWork W2733060750 @default.
- W2896863246 hasRelatedWork W3000095492 @default.
- W2896863246 hasRelatedWork W3018375584 @default.
- W2896863246 hasRelatedWork W3142505183 @default.
- W2896863246 hasRelatedWork W3108696707 @default.
- W2896863246 isParatext "false" @default.
- W2896863246 isRetracted "false" @default.
- W2896863246 magId "2896863246" @default.
- W2896863246 workType "article" @default.