Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119120717> ?p ?o ?g. }
- W3119120717 abstract "For image recognition, an extensive number of subspace-learning methods have been proposed to overcome the high-dimensionality problem of the features being used. In this paper, we first give an overview of the most popular and state-of-the-art subspace-learning methods, and then, a novel manifold-learning method, named soft locality preserving map (SLPM), is presented. SLPM aims to control the level of spread of the different classes, which is closely connected to the generalizability of the learned subspace. We also do an overview of the extension of manifold learning methods to deep learning by formulating the loss functions for training, and further reformulate SLPM into a soft locality preserving (SLP) loss. These loss functions are applied as an additional regularization to the learning of deep neural networks. We evaluate these subspace-learning methods, as well as their deep-learning extensions, on facial expression recognition. Experiments on four commonly used databases show that SLPM effectively reduces the dimensionality of the feature vectors and enhances the discriminative power of the extracted features. Moreover, experimental results also demonstrate that the learned deep features regularized by SLP acquire a better discriminability and generalizability for facial expression recognition." @default.
- W3119120717 created "2021-01-18" @default.
- W3119120717 creator A5014107463 @default.
- W3119120717 creator A5021340482 @default.
- W3119120717 creator A5038928473 @default.
- W3119120717 creator A5090581248 @default.
- W3119120717 date "2021-01-01" @default.
- W3119120717 modified "2023-10-01" @default.
- W3119120717 title "Subspace learning for facial expression recognition: an overview and a new perspective" @default.
- W3119120717 cites W1582066090 @default.
- W3119120717 cites W1607979445 @default.
- W3119120717 cites W1622838444 @default.
- W3119120717 cites W1631012836 @default.
- W3119120717 cites W1969030392 @default.
- W3119120717 cites W1977005561 @default.
- W3119120717 cites W1979189411 @default.
- W3119120717 cites W1982000202 @default.
- W3119120717 cites W1988678232 @default.
- W3119120717 cites W2000579638 @default.
- W3119120717 cites W2001141328 @default.
- W3119120717 cites W2001619934 @default.
- W3119120717 cites W2002645541 @default.
- W3119120717 cites W2008114799 @default.
- W3119120717 cites W2016293853 @default.
- W3119120717 cites W2022286021 @default.
- W3119120717 cites W2024194293 @default.
- W3119120717 cites W2039051707 @default.
- W3119120717 cites W2053186076 @default.
- W3119120717 cites W2058156885 @default.
- W3119120717 cites W2061199901 @default.
- W3119120717 cites W2066505168 @default.
- W3119120717 cites W2071128523 @default.
- W3119120717 cites W2074388987 @default.
- W3119120717 cites W2078138800 @default.
- W3119120717 cites W2105055468 @default.
- W3119120717 cites W2109255472 @default.
- W3119120717 cites W2130258210 @default.
- W3119120717 cites W2133368777 @default.
- W3119120717 cites W2134262590 @default.
- W3119120717 cites W2145310492 @default.
- W3119120717 cites W2149544470 @default.
- W3119120717 cites W2153635508 @default.
- W3119120717 cites W2153792307 @default.
- W3119120717 cites W2154683974 @default.
- W3119120717 cites W2191179271 @default.
- W3119120717 cites W2194775991 @default.
- W3119120717 cites W2198512331 @default.
- W3119120717 cites W2217426128 @default.
- W3119120717 cites W2293118840 @default.
- W3119120717 cites W2294270764 @default.
- W3119120717 cites W2395802871 @default.
- W3119120717 cites W2472411863 @default.
- W3119120717 cites W2484273982 @default.
- W3119120717 cites W2491131609 @default.
- W3119120717 cites W2508457857 @default.
- W3119120717 cites W2520774990 @default.
- W3119120717 cites W2730601341 @default.
- W3119120717 cites W2730840610 @default.
- W3119120717 cites W2794717016 @default.
- W3119120717 cites W2805755230 @default.
- W3119120717 cites W2889978276 @default.
- W3119120717 cites W2963037989 @default.
- W3119120717 cites W2963712289 @default.
- W3119120717 cites W3007795584 @default.
- W3119120717 cites W3100167649 @default.
- W3119120717 cites W3102431071 @default.
- W3119120717 cites W3104792420 @default.
- W3119120717 cites W3148981562 @default.
- W3119120717 doi "https://doi.org/10.1017/atsip.2020.27" @default.
- W3119120717 hasPublicationYear "2021" @default.
- W3119120717 type Work @default.
- W3119120717 sameAs 3119120717 @default.
- W3119120717 citedByCount "4" @default.
- W3119120717 countsByYear W31191207172021 @default.
- W3119120717 countsByYear W31191207172022 @default.
- W3119120717 countsByYear W31191207172023 @default.
- W3119120717 crossrefType "journal-article" @default.
- W3119120717 hasAuthorship W3119120717A5014107463 @default.
- W3119120717 hasAuthorship W3119120717A5021340482 @default.
- W3119120717 hasAuthorship W3119120717A5038928473 @default.
- W3119120717 hasAuthorship W3119120717A5090581248 @default.
- W3119120717 hasBestOaLocation W31191207171 @default.
- W3119120717 hasConcept C12713177 @default.
- W3119120717 hasConcept C153180895 @default.
- W3119120717 hasConcept C154945302 @default.
- W3119120717 hasConcept C15744967 @default.
- W3119120717 hasConcept C180747234 @default.
- W3119120717 hasConcept C195704467 @default.
- W3119120717 hasConcept C199360897 @default.
- W3119120717 hasConcept C28490314 @default.
- W3119120717 hasConcept C2987714656 @default.
- W3119120717 hasConcept C31510193 @default.
- W3119120717 hasConcept C32834561 @default.
- W3119120717 hasConcept C41008148 @default.
- W3119120717 hasConcept C90559484 @default.
- W3119120717 hasConceptScore W3119120717C12713177 @default.
- W3119120717 hasConceptScore W3119120717C153180895 @default.
- W3119120717 hasConceptScore W3119120717C154945302 @default.
- W3119120717 hasConceptScore W3119120717C15744967 @default.
- W3119120717 hasConceptScore W3119120717C180747234 @default.