Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903362684> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2903362684 abstract "Facial expression recognition (FER) is a challenging problem with important applications. Applying deep learning techniques for dynamic FER is advantageous in terms of automatically generating discriminative expression features. However, inadequate training data in small expression databases aggravates overfitting and hinders the performance of deep networks. Recent studies have shown that dense connectivity in convolutional neural networks can encourage feature sharing and alleviate overfitting when training with small datasets. Still, traditional dense structures are too deep for FER with insufficient training samples. In this paper, we propose a relatively shallow CNN structure with densely connected short paths for FER. Instead of using transition layers to down-sample feature maps between dense blocks, we introduce dense connectivity across pooling to enforce feature sharing in the shallow CNN structure. Extensive experiments show that our method achieves competitive performance on benchmark datasets CK+ and Oulu-CASIA." @default.
- W2903362684 created "2018-12-11" @default.
- W2903362684 creator A5034213282 @default.
- W2903362684 creator A5076550599 @default.
- W2903362684 creator A5080483357 @default.
- W2903362684 date "2018-08-01" @default.
- W2903362684 modified "2023-10-03" @default.
- W2903362684 title "Dynamic Facial Expression Recognition Based on Convolutional Neural Networks with Dense Connections" @default.
- W2903362684 cites W132448360 @default.
- W2903362684 cites W1951380363 @default.
- W2903362684 cites W1974210421 @default.
- W2903362684 cites W2008646744 @default.
- W2903362684 cites W2024868105 @default.
- W2903362684 cites W2035372623 @default.
- W2903362684 cites W2060312700 @default.
- W2903362684 cites W2087681821 @default.
- W2903362684 cites W2097117768 @default.
- W2903362684 cites W2103943262 @default.
- W2903362684 cites W2112796928 @default.
- W2903362684 cites W2134860945 @default.
- W2903362684 cites W2139916508 @default.
- W2903362684 cites W2141990597 @default.
- W2903362684 cites W2189774688 @default.
- W2903362684 cites W2194775991 @default.
- W2903362684 cites W2205937646 @default.
- W2903362684 cites W2217426128 @default.
- W2903362684 cites W2246249023 @default.
- W2903362684 cites W2345921676 @default.
- W2903362684 cites W2490049321 @default.
- W2903362684 cites W2591924527 @default.
- W2903362684 cites W2607623277 @default.
- W2903362684 cites W2963446712 @default.
- W2903362684 cites W2963623198 @default.
- W2903362684 cites W3100876745 @default.
- W2903362684 doi "https://doi.org/10.1109/icpr.2018.8545596" @default.
- W2903362684 hasPublicationYear "2018" @default.
- W2903362684 type Work @default.
- W2903362684 sameAs 2903362684 @default.
- W2903362684 citedByCount "13" @default.
- W2903362684 countsByYear W29033626842019 @default.
- W2903362684 countsByYear W29033626842020 @default.
- W2903362684 countsByYear W29033626842021 @default.
- W2903362684 countsByYear W29033626842022 @default.
- W2903362684 countsByYear W29033626842023 @default.
- W2903362684 crossrefType "proceedings-article" @default.
- W2903362684 hasAuthorship W2903362684A5034213282 @default.
- W2903362684 hasAuthorship W2903362684A5076550599 @default.
- W2903362684 hasAuthorship W2903362684A5080483357 @default.
- W2903362684 hasConcept C153180895 @default.
- W2903362684 hasConcept C154945302 @default.
- W2903362684 hasConcept C195704467 @default.
- W2903362684 hasConcept C199360897 @default.
- W2903362684 hasConcept C28490314 @default.
- W2903362684 hasConcept C2987714656 @default.
- W2903362684 hasConcept C31510193 @default.
- W2903362684 hasConcept C41008148 @default.
- W2903362684 hasConcept C81363708 @default.
- W2903362684 hasConcept C90559484 @default.
- W2903362684 hasConceptScore W2903362684C153180895 @default.
- W2903362684 hasConceptScore W2903362684C154945302 @default.
- W2903362684 hasConceptScore W2903362684C195704467 @default.
- W2903362684 hasConceptScore W2903362684C199360897 @default.
- W2903362684 hasConceptScore W2903362684C28490314 @default.
- W2903362684 hasConceptScore W2903362684C2987714656 @default.
- W2903362684 hasConceptScore W2903362684C31510193 @default.
- W2903362684 hasConceptScore W2903362684C41008148 @default.
- W2903362684 hasConceptScore W2903362684C81363708 @default.
- W2903362684 hasConceptScore W2903362684C90559484 @default.
- W2903362684 hasLocation W29033626841 @default.
- W2903362684 hasOpenAccess W2903362684 @default.
- W2903362684 hasPrimaryLocation W29033626841 @default.
- W2903362684 hasRelatedWork W1591965711 @default.
- W2903362684 hasRelatedWork W1982770690 @default.
- W2903362684 hasRelatedWork W2584335650 @default.
- W2903362684 hasRelatedWork W2799893153 @default.
- W2903362684 hasRelatedWork W2908861653 @default.
- W2903362684 hasRelatedWork W2977314777 @default.
- W2903362684 hasRelatedWork W2995914718 @default.
- W2903362684 hasRelatedWork W3000095492 @default.
- W2903362684 hasRelatedWork W3018375584 @default.
- W2903362684 hasRelatedWork W3186847174 @default.
- W2903362684 isParatext "false" @default.
- W2903362684 isRetracted "false" @default.
- W2903362684 magId "2903362684" @default.
- W2903362684 workType "article" @default.