Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000820603> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2000820603 abstract "In this paper, we propose to construct a deep architecture, AU-aware Deep Networks (AUDN), for facial expression recognition by elaborately utilizing the prior knowledge that the appearance variations caused by expression can be decomposed into a batch of local facial Action Units (AUs). The proposed AUDN is composed of three sequential modules: the first module consists of two layers, i.e., a convolution layer and a max-pooling layer, which aim to generate an over-complete representation encoding all expression-specific appearance variations over all possible locations; In the second module, an AU-aware receptive field layer is designed to search subsets of the over-complete representation, each of which aims at best simulating the combination of AUs; In the last module, multilayer Restricted Boltzmann Machines (RBM) are exploited to learn hierarchical features, which are then concatenated for final expression recognition. Experiments on three expression databases CK+, MMI and SFEW demonstrate the effectiveness of AUDN in both lab-controlled and wild environments. All our results are better than or at least competitive to the best known results." @default.
- W2000820603 created "2016-06-24" @default.
- W2000820603 creator A5045678161 @default.
- W2000820603 creator A5050297728 @default.
- W2000820603 creator A5076531809 @default.
- W2000820603 creator A5083420537 @default.
- W2000820603 date "2013-04-01" @default.
- W2000820603 modified "2023-09-27" @default.
- W2000820603 title "AU-aware Deep Networks for facial expression recognition" @default.
- W2000820603 cites W1595126664 @default.
- W2000820603 cites W1997838579 @default.
- W2000820603 cites W2004586880 @default.
- W2000820603 cites W2014915963 @default.
- W2000820603 cites W2035161948 @default.
- W2000820603 cites W2083021723 @default.
- W2000820603 cites W2096044434 @default.
- W2000820603 cites W2100495367 @default.
- W2000820603 cites W2103943262 @default.
- W2000820603 cites W2108445559 @default.
- W2000820603 cites W2116064496 @default.
- W2000820603 cites W2125127226 @default.
- W2000820603 cites W2130325614 @default.
- W2000820603 cites W2132549764 @default.
- W2000820603 cites W2134557905 @default.
- W2000820603 cites W2136922672 @default.
- W2000820603 cites W2141303268 @default.
- W2000820603 cites W2145310492 @default.
- W2000820603 cites W2153678774 @default.
- W2000820603 cites W2154053567 @default.
- W2000820603 cites W2162915993 @default.
- W2000820603 cites W2172197449 @default.
- W2000820603 doi "https://doi.org/10.1109/fg.2013.6553734" @default.
- W2000820603 hasPublicationYear "2013" @default.
- W2000820603 type Work @default.
- W2000820603 sameAs 2000820603 @default.
- W2000820603 citedByCount "54" @default.
- W2000820603 countsByYear W20008206032013 @default.
- W2000820603 countsByYear W20008206032015 @default.
- W2000820603 countsByYear W20008206032016 @default.
- W2000820603 countsByYear W20008206032017 @default.
- W2000820603 countsByYear W20008206032018 @default.
- W2000820603 countsByYear W20008206032019 @default.
- W2000820603 countsByYear W20008206032020 @default.
- W2000820603 countsByYear W20008206032021 @default.
- W2000820603 countsByYear W20008206032022 @default.
- W2000820603 countsByYear W20008206032023 @default.
- W2000820603 crossrefType "proceedings-article" @default.
- W2000820603 hasAuthorship W2000820603A5045678161 @default.
- W2000820603 hasAuthorship W2000820603A5050297728 @default.
- W2000820603 hasAuthorship W2000820603A5076531809 @default.
- W2000820603 hasAuthorship W2000820603A5083420537 @default.
- W2000820603 hasConcept C153180895 @default.
- W2000820603 hasConcept C154945302 @default.
- W2000820603 hasConcept C195704467 @default.
- W2000820603 hasConcept C28490314 @default.
- W2000820603 hasConcept C2987714656 @default.
- W2000820603 hasConcept C31510193 @default.
- W2000820603 hasConcept C41008148 @default.
- W2000820603 hasConceptScore W2000820603C153180895 @default.
- W2000820603 hasConceptScore W2000820603C154945302 @default.
- W2000820603 hasConceptScore W2000820603C195704467 @default.
- W2000820603 hasConceptScore W2000820603C28490314 @default.
- W2000820603 hasConceptScore W2000820603C2987714656 @default.
- W2000820603 hasConceptScore W2000820603C31510193 @default.
- W2000820603 hasConceptScore W2000820603C41008148 @default.
- W2000820603 hasLocation W20008206031 @default.
- W2000820603 hasOpenAccess W2000820603 @default.
- W2000820603 hasPrimaryLocation W20008206031 @default.
- W2000820603 hasRelatedWork W1560999061 @default.
- W2000820603 hasRelatedWork W1591194399 @default.
- W2000820603 hasRelatedWork W1591965711 @default.
- W2000820603 hasRelatedWork W1982770690 @default.
- W2000820603 hasRelatedWork W2078674814 @default.
- W2000820603 hasRelatedWork W2140205990 @default.
- W2000820603 hasRelatedWork W2997678817 @default.
- W2000820603 hasRelatedWork W3000095492 @default.
- W2000820603 hasRelatedWork W3018375584 @default.
- W2000820603 hasRelatedWork W3194078543 @default.
- W2000820603 isParatext "false" @default.
- W2000820603 isRetracted "false" @default.
- W2000820603 magId "2000820603" @default.
- W2000820603 workType "article" @default.