Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308386320> ?p ?o ?g. }
- W4308386320 endingPage "109157" @default.
- W4308386320 startingPage "109157" @default.
- W4308386320 abstract "Considering most deep learning-based methods heavily depend on huge labels, it is still a challenging issue for facial expression recognition to extract discriminative features of training samples with limited labels. Given above, we propose a discriminatively deep fusion (DDF) approach based on an improved conditional generative adversarial network (im-cGAN) to learn abstract representation of facial expressions. First, we employ facial images with action units (AUs) to train the im-cGAN to generate more labeled expression samples. Subsequently, we utilize global features learned by the global-based module and the local features learned by the region-based module to obtain the fused feature representation. Finally, we design the discriminative loss function (D-loss) that expands the inter-class variations while minimizing the intra-class distances to enhance the discrimination of fused features. Experimental results on JAFFE, CK+, Oulu-CASIA, and KDEF datasets demonstrate the proposed approach is superior to some state-of-the-art methods." @default.
- W4308386320 created "2022-11-11" @default.
- W4308386320 creator A5007660110 @default.
- W4308386320 creator A5029988326 @default.
- W4308386320 creator A5049529533 @default.
- W4308386320 creator A5070990928 @default.
- W4308386320 creator A5077972623 @default.
- W4308386320 date "2023-03-01" @default.
- W4308386320 modified "2023-10-04" @default.
- W4308386320 title "A discriminatively deep fusion approach with improved conditional GAN (im-cGAN) for facial expression recognition" @default.
- W4308386320 cites W2016163491 @default.
- W4308386320 cites W2035372623 @default.
- W4308386320 cites W2096044434 @default.
- W4308386320 cites W2139916508 @default.
- W4308386320 cites W2562637781 @default.
- W4308386320 cites W2737559518 @default.
- W4308386320 cites W2938665958 @default.
- W4308386320 cites W2940314039 @default.
- W4308386320 cites W2963626105 @default.
- W4308386320 cites W2969222682 @default.
- W4308386320 cites W2995396423 @default.
- W4308386320 cites W3000164979 @default.
- W4308386320 cites W3000577085 @default.
- W4308386320 cites W3003720578 @default.
- W4308386320 cites W3035437068 @default.
- W4308386320 cites W3083995153 @default.
- W4308386320 cites W3092695513 @default.
- W4308386320 cites W3098677746 @default.
- W4308386320 cites W3167258964 @default.
- W4308386320 cites W3178473334 @default.
- W4308386320 cites W3189654580 @default.
- W4308386320 cites W3211081651 @default.
- W4308386320 cites W4225323075 @default.
- W4308386320 doi "https://doi.org/10.1016/j.patcog.2022.109157" @default.
- W4308386320 hasPublicationYear "2023" @default.
- W4308386320 type Work @default.
- W4308386320 citedByCount "9" @default.
- W4308386320 countsByYear W43083863202023 @default.
- W4308386320 crossrefType "journal-article" @default.
- W4308386320 hasAuthorship W4308386320A5007660110 @default.
- W4308386320 hasAuthorship W4308386320A5029988326 @default.
- W4308386320 hasAuthorship W4308386320A5049529533 @default.
- W4308386320 hasAuthorship W4308386320A5070990928 @default.
- W4308386320 hasAuthorship W4308386320A5077972623 @default.
- W4308386320 hasConcept C108583219 @default.
- W4308386320 hasConcept C138885662 @default.
- W4308386320 hasConcept C153180895 @default.
- W4308386320 hasConcept C154945302 @default.
- W4308386320 hasConcept C158525013 @default.
- W4308386320 hasConcept C167966045 @default.
- W4308386320 hasConcept C17744445 @default.
- W4308386320 hasConcept C195704467 @default.
- W4308386320 hasConcept C199360897 @default.
- W4308386320 hasConcept C199539241 @default.
- W4308386320 hasConcept C2776359362 @default.
- W4308386320 hasConcept C2776401178 @default.
- W4308386320 hasConcept C2777212361 @default.
- W4308386320 hasConcept C2987714656 @default.
- W4308386320 hasConcept C2988773926 @default.
- W4308386320 hasConcept C31510193 @default.
- W4308386320 hasConcept C39890363 @default.
- W4308386320 hasConcept C41008148 @default.
- W4308386320 hasConcept C41895202 @default.
- W4308386320 hasConcept C90559484 @default.
- W4308386320 hasConcept C94625758 @default.
- W4308386320 hasConcept C97931131 @default.
- W4308386320 hasConceptScore W4308386320C108583219 @default.
- W4308386320 hasConceptScore W4308386320C138885662 @default.
- W4308386320 hasConceptScore W4308386320C153180895 @default.
- W4308386320 hasConceptScore W4308386320C154945302 @default.
- W4308386320 hasConceptScore W4308386320C158525013 @default.
- W4308386320 hasConceptScore W4308386320C167966045 @default.
- W4308386320 hasConceptScore W4308386320C17744445 @default.
- W4308386320 hasConceptScore W4308386320C195704467 @default.
- W4308386320 hasConceptScore W4308386320C199360897 @default.
- W4308386320 hasConceptScore W4308386320C199539241 @default.
- W4308386320 hasConceptScore W4308386320C2776359362 @default.
- W4308386320 hasConceptScore W4308386320C2776401178 @default.
- W4308386320 hasConceptScore W4308386320C2777212361 @default.
- W4308386320 hasConceptScore W4308386320C2987714656 @default.
- W4308386320 hasConceptScore W4308386320C2988773926 @default.
- W4308386320 hasConceptScore W4308386320C31510193 @default.
- W4308386320 hasConceptScore W4308386320C39890363 @default.
- W4308386320 hasConceptScore W4308386320C41008148 @default.
- W4308386320 hasConceptScore W4308386320C41895202 @default.
- W4308386320 hasConceptScore W4308386320C90559484 @default.
- W4308386320 hasConceptScore W4308386320C94625758 @default.
- W4308386320 hasConceptScore W4308386320C97931131 @default.
- W4308386320 hasLocation W43083863201 @default.
- W4308386320 hasOpenAccess W4308386320 @default.
- W4308386320 hasPrimaryLocation W43083863201 @default.
- W4308386320 hasRelatedWork W1497005071 @default.
- W4308386320 hasRelatedWork W2088575594 @default.
- W4308386320 hasRelatedWork W2970216048 @default.
- W4308386320 hasRelatedWork W2984154060 @default.
- W4308386320 hasRelatedWork W3120135729 @default.
- W4308386320 hasRelatedWork W3164441579 @default.
- W4308386320 hasRelatedWork W3195543922 @default.