Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289293844> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4289293844 abstract "This paper presents a novel approach for synthesizing facial affect; either in terms of the six basic expressions (i.e., anger, disgust, fear, joy, sadness and surprise), or in terms of valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the emotion activation). The proposed approach accepts the following inputs: i) a neutral 2D image of a person; ii) a basic facial expression or a pair of valence-arousal (VA) emotional state descriptors to be generated, or a path of affect in the 2D VA Space to be generated as an image sequence. In order to synthesize affect in terms of VA, for this person, $600,000$ frames from the 4DFAB database were annotated. The affect synthesis is implemented by fitting a 3D Morphable Model on the neutral image, then deforming the reconstructed face and adding the inputted affect, and blending the new face with the given affect into the original image. Qualitative experiments illustrate the generation of realistic images, when the neutral image is sampled from thirteen well known lab-controlled or in-the-wild databases, including Aff-Wild, AffectNet, RAF-DB; comparisons with Generative Adversarial Networks (GANs) show the higher quality achieved by the proposed approach. Then, quantitative experiments are conducted, in which the synthesized images are used for data augmentation in training Deep Neural Networks to perform affect recognition over all databases; greatly improved performances are achieved when compared with state-of-the-art methods, as well as with GAN-based data augmentation, in all cases." @default.
- W4289293844 created "2022-08-02" @default.
- W4289293844 creator A5017072420 @default.
- W4289293844 creator A5029879679 @default.
- W4289293844 creator A5046220058 @default.
- W4289293844 creator A5053692819 @default.
- W4289293844 creator A5080553022 @default.
- W4289293844 date "2018-11-12" @default.
- W4289293844 modified "2023-09-26" @default.
- W4289293844 title "Deep Neural Network Augmentation: Generating Faces for Affect Analysis" @default.
- W4289293844 doi "https://doi.org/10.48550/arxiv.1811.05027" @default.
- W4289293844 hasPublicationYear "2018" @default.
- W4289293844 type Work @default.
- W4289293844 citedByCount "0" @default.
- W4289293844 crossrefType "posted-content" @default.
- W4289293844 hasAuthorship W4289293844A5017072420 @default.
- W4289293844 hasAuthorship W4289293844A5029879679 @default.
- W4289293844 hasAuthorship W4289293844A5046220058 @default.
- W4289293844 hasAuthorship W4289293844A5053692819 @default.
- W4289293844 hasAuthorship W4289293844A5080553022 @default.
- W4289293844 hasBestOaLocation W42892938441 @default.
- W4289293844 hasConcept C121332964 @default.
- W4289293844 hasConcept C153180895 @default.
- W4289293844 hasConcept C154945302 @default.
- W4289293844 hasConcept C15744967 @default.
- W4289293844 hasConcept C168900304 @default.
- W4289293844 hasConcept C195704467 @default.
- W4289293844 hasConcept C2776035688 @default.
- W4289293844 hasConcept C2777375102 @default.
- W4289293844 hasConcept C2779302386 @default.
- W4289293844 hasConcept C2779812673 @default.
- W4289293844 hasConcept C2780343955 @default.
- W4289293844 hasConcept C28490314 @default.
- W4289293844 hasConcept C31972630 @default.
- W4289293844 hasConcept C36951298 @default.
- W4289293844 hasConcept C41008148 @default.
- W4289293844 hasConcept C46312422 @default.
- W4289293844 hasConcept C50644808 @default.
- W4289293844 hasConcept C62520636 @default.
- W4289293844 hasConcept C77805123 @default.
- W4289293844 hasConceptScore W4289293844C121332964 @default.
- W4289293844 hasConceptScore W4289293844C153180895 @default.
- W4289293844 hasConceptScore W4289293844C154945302 @default.
- W4289293844 hasConceptScore W4289293844C15744967 @default.
- W4289293844 hasConceptScore W4289293844C168900304 @default.
- W4289293844 hasConceptScore W4289293844C195704467 @default.
- W4289293844 hasConceptScore W4289293844C2776035688 @default.
- W4289293844 hasConceptScore W4289293844C2777375102 @default.
- W4289293844 hasConceptScore W4289293844C2779302386 @default.
- W4289293844 hasConceptScore W4289293844C2779812673 @default.
- W4289293844 hasConceptScore W4289293844C2780343955 @default.
- W4289293844 hasConceptScore W4289293844C28490314 @default.
- W4289293844 hasConceptScore W4289293844C31972630 @default.
- W4289293844 hasConceptScore W4289293844C36951298 @default.
- W4289293844 hasConceptScore W4289293844C41008148 @default.
- W4289293844 hasConceptScore W4289293844C46312422 @default.
- W4289293844 hasConceptScore W4289293844C50644808 @default.
- W4289293844 hasConceptScore W4289293844C62520636 @default.
- W4289293844 hasConceptScore W4289293844C77805123 @default.
- W4289293844 hasLocation W42892938441 @default.
- W4289293844 hasLocation W42892938442 @default.
- W4289293844 hasLocation W42892938443 @default.
- W4289293844 hasOpenAccess W4289293844 @default.
- W4289293844 hasPrimaryLocation W42892938441 @default.
- W4289293844 hasRelatedWork W1965057385 @default.
- W4289293844 hasRelatedWork W1974787498 @default.
- W4289293844 hasRelatedWork W1987024041 @default.
- W4289293844 hasRelatedWork W2096798980 @default.
- W4289293844 hasRelatedWork W2105112108 @default.
- W4289293844 hasRelatedWork W2246499499 @default.
- W4289293844 hasRelatedWork W2377787444 @default.
- W4289293844 hasRelatedWork W2783434803 @default.
- W4289293844 hasRelatedWork W2959642136 @default.
- W4289293844 hasRelatedWork W96975344 @default.
- W4289293844 isParatext "false" @default.
- W4289293844 isRetracted "false" @default.
- W4289293844 workType "article" @default.