Matches in SemOpenAlex for { <https://semopenalex.org/work/W3019849343> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3019849343 endingPage "729" @default.
- W3019849343 startingPage "725" @default.
- W3019849343 abstract "An important challenge for facial expression recognition (FER) is that real-world training data are usually imbalanced. Although many deep learning approaches have been proposed to enhance the discriminative power of deep expression features and enable a good predictive effect, few works have focused on the multiclass imbalance problem. When supervised by softmax loss (SL), which is widely used in FER, the classifier is often biased against minority categories (i.e., smaller interclass angular distances). In this letter, we present advanced softmax loss (ASL) to mitigate the bias induced by data imbalance and hence increase accuracy and reliability. The proposed ASL essentially magnifies the interclass diversity in the angular space to enhance discriminative power in every category. The proposed loss can easily be implemented in any deep network. Extensive experiments on the FER2013 and real-world affective faces (RAF) databases demonstrate that ASL is significantly more accurate and reliable than many state-of-the-art approaches and that it can easily be plugged into other methods and improves their performance." @default.
- W3019849343 created "2020-05-01" @default.
- W3019849343 creator A5026243783 @default.
- W3019849343 creator A5050466935 @default.
- W3019849343 creator A5053613875 @default.
- W3019849343 creator A5058637832 @default.
- W3019849343 date "2020-01-01" @default.
- W3019849343 modified "2023-10-18" @default.
- W3019849343 title "Accurate and Reliable Facial Expression Recognition Using Advanced Softmax Loss With Fixed Weights" @default.
- W3019849343 cites W1677182931 @default.
- W3019849343 cites W1983793001 @default.
- W3019849343 cites W2052041602 @default.
- W3019849343 cites W2079678116 @default.
- W3019849343 cites W2095809036 @default.
- W3019849343 cites W2102605133 @default.
- W3019849343 cites W2194775991 @default.
- W3019849343 cites W2474193198 @default.
- W3019849343 cites W2551403050 @default.
- W3019849343 cites W2738672149 @default.
- W3019849343 cites W2744909235 @default.
- W3019849343 cites W2784294927 @default.
- W3019849343 cites W2798553619 @default.
- W3019849343 cites W2805080735 @default.
- W3019849343 cites W2805613995 @default.
- W3019849343 cites W2889978276 @default.
- W3019849343 cites W2902916789 @default.
- W3019849343 cites W2908694412 @default.
- W3019849343 cites W2910883248 @default.
- W3019849343 cites W2961224374 @default.
- W3019849343 cites W2962898354 @default.
- W3019849343 cites W2963466847 @default.
- W3019849343 cites W2963712289 @default.
- W3019849343 cites W2969985801 @default.
- W3019849343 cites W3009883635 @default.
- W3019849343 cites W3035336958 @default.
- W3019849343 doi "https://doi.org/10.1109/lsp.2020.2989670" @default.
- W3019849343 hasPublicationYear "2020" @default.
- W3019849343 type Work @default.
- W3019849343 sameAs 3019849343 @default.
- W3019849343 citedByCount "13" @default.
- W3019849343 countsByYear W30198493432020 @default.
- W3019849343 countsByYear W30198493432021 @default.
- W3019849343 countsByYear W30198493432022 @default.
- W3019849343 countsByYear W30198493432023 @default.
- W3019849343 crossrefType "journal-article" @default.
- W3019849343 hasAuthorship W3019849343A5026243783 @default.
- W3019849343 hasAuthorship W3019849343A5050466935 @default.
- W3019849343 hasAuthorship W3019849343A5053613875 @default.
- W3019849343 hasAuthorship W3019849343A5058637832 @default.
- W3019849343 hasConcept C108583219 @default.
- W3019849343 hasConcept C119857082 @default.
- W3019849343 hasConcept C153180895 @default.
- W3019849343 hasConcept C154945302 @default.
- W3019849343 hasConcept C188441871 @default.
- W3019849343 hasConcept C195704467 @default.
- W3019849343 hasConcept C199360897 @default.
- W3019849343 hasConcept C28490314 @default.
- W3019849343 hasConcept C41008148 @default.
- W3019849343 hasConcept C52622490 @default.
- W3019849343 hasConcept C90559484 @default.
- W3019849343 hasConcept C95623464 @default.
- W3019849343 hasConcept C97931131 @default.
- W3019849343 hasConceptScore W3019849343C108583219 @default.
- W3019849343 hasConceptScore W3019849343C119857082 @default.
- W3019849343 hasConceptScore W3019849343C153180895 @default.
- W3019849343 hasConceptScore W3019849343C154945302 @default.
- W3019849343 hasConceptScore W3019849343C188441871 @default.
- W3019849343 hasConceptScore W3019849343C195704467 @default.
- W3019849343 hasConceptScore W3019849343C199360897 @default.
- W3019849343 hasConceptScore W3019849343C28490314 @default.
- W3019849343 hasConceptScore W3019849343C41008148 @default.
- W3019849343 hasConceptScore W3019849343C52622490 @default.
- W3019849343 hasConceptScore W3019849343C90559484 @default.
- W3019849343 hasConceptScore W3019849343C95623464 @default.
- W3019849343 hasConceptScore W3019849343C97931131 @default.
- W3019849343 hasFunder F4320321001 @default.
- W3019849343 hasLocation W30198493431 @default.
- W3019849343 hasOpenAccess W3019849343 @default.
- W3019849343 hasPrimaryLocation W30198493431 @default.
- W3019849343 hasRelatedWork W2285052147 @default.
- W3019849343 hasRelatedWork W2729514902 @default.
- W3019849343 hasRelatedWork W2739417350 @default.
- W3019849343 hasRelatedWork W2743258233 @default.
- W3019849343 hasRelatedWork W2771515600 @default.
- W3019849343 hasRelatedWork W2806866760 @default.
- W3019849343 hasRelatedWork W2807311372 @default.
- W3019849343 hasRelatedWork W2946016983 @default.
- W3019849343 hasRelatedWork W4214883769 @default.
- W3019849343 hasRelatedWork W4307834408 @default.
- W3019849343 hasVolume "27" @default.
- W3019849343 isParatext "false" @default.
- W3019849343 isRetracted "false" @default.
- W3019849343 magId "3019849343" @default.
- W3019849343 workType "article" @default.