Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183147992> ?p ?o ?g. }
- W3183147992 abstract "Faces generated using generative adversarial networks (GANs) have reached unprecedented realism. These faces, also known as Deep Fakes, appear as realistic photographs with very little pixel-level distortions. While some work has enabled the training of models that lead to the generation of specific properties of the subject, generating a facial image based on a natural language description has not been fully explored. For security and criminal identification, the ability to provide a GAN-based system that works like a sketch artist would be incredibly useful. In this paper, we present a novel approach to generate facial images from semantic text descriptions. The learned model is provided with a text description and an outline of the type of face, which the model uses to sketch the features. Our models are trained using an Affine Combination Module (ACM) mechanism to combine the text embedding from BERT and the GAN latent space using a self-attention matrix. This avoids the loss of features due to inadequate attention, which may happen if text embedding and latent vector are simply concatenated. Our approach is capable of generating images that are very accurately aligned to the exhaustive textual descriptions of faces with many fine detail features of the face and helps in generating better images. The proposed method is also capable of making incremental changes to a previously generated image if it is provided with additional textual descriptions or sentences." @default.
- W3183147992 created "2021-08-02" @default.
- W3183147992 creator A5003875781 @default.
- W3183147992 creator A5013521988 @default.
- W3183147992 creator A5031639663 @default.
- W3183147992 date "2021-07-22" @default.
- W3183147992 modified "2023-09-27" @default.
- W3183147992 title "Semantic Text-to-Face GAN -ST^2FG." @default.
- W3183147992 cites W1782590233 @default.
- W3183147992 cites W1797268635 @default.
- W3183147992 cites W1834627138 @default.
- W3183147992 cites W1861492603 @default.
- W3183147992 cites W1916445035 @default.
- W3183147992 cites W2112912048 @default.
- W3183147992 cites W2183341477 @default.
- W3183147992 cites W2185175083 @default.
- W3183147992 cites W2194775991 @default.
- W3183147992 cites W2250539671 @default.
- W3183147992 cites W2405756170 @default.
- W3183147992 cites W2481240925 @default.
- W3183147992 cites W2545656684 @default.
- W3183147992 cites W2546696630 @default.
- W3183147992 cites W2568262903 @default.
- W3183147992 cites W2687693326 @default.
- W3183147992 cites W2783879794 @default.
- W3183147992 cites W2784121710 @default.
- W3183147992 cites W2787560479 @default.
- W3183147992 cites W2891417743 @default.
- W3183147992 cites W2949433733 @default.
- W3183147992 cites W2951697117 @default.
- W3183147992 cites W2952729433 @default.
- W3183147992 cites W2953276893 @default.
- W3183147992 cites W2956018683 @default.
- W3183147992 cites W2962706528 @default.
- W3183147992 cites W2962770929 @default.
- W3183147992 cites W2962964995 @default.
- W3183147992 cites W2963245493 @default.
- W3183147992 cites W2963341956 @default.
- W3183147992 cites W2963626105 @default.
- W3183147992 cites W2963671154 @default.
- W3183147992 cites W2963966654 @default.
- W3183147992 cites W2964024144 @default.
- W3183147992 cites W2970127127 @default.
- W3183147992 cites W2994303421 @default.
- W3183147992 cites W3005755659 @default.
- W3183147992 cites W3023902827 @default.
- W3183147992 cites W3035316078 @default.
- W3183147992 cites W3035574324 @default.
- W3183147992 cites W3094325913 @default.
- W3183147992 cites W3129576130 @default.
- W3183147992 cites W3174194560 @default.
- W3183147992 hasPublicationYear "2021" @default.
- W3183147992 type Work @default.
- W3183147992 sameAs 3183147992 @default.
- W3183147992 citedByCount "0" @default.
- W3183147992 crossrefType "posted-content" @default.
- W3183147992 hasAuthorship W3183147992A5003875781 @default.
- W3183147992 hasAuthorship W3183147992A5013521988 @default.
- W3183147992 hasAuthorship W3183147992A5031639663 @default.
- W3183147992 hasConcept C11413529 @default.
- W3183147992 hasConcept C115961682 @default.
- W3183147992 hasConcept C138885662 @default.
- W3183147992 hasConcept C153180895 @default.
- W3183147992 hasConcept C154945302 @default.
- W3183147992 hasConcept C204321447 @default.
- W3183147992 hasConcept C2779231336 @default.
- W3183147992 hasConcept C2779304628 @default.
- W3183147992 hasConcept C39890363 @default.
- W3183147992 hasConcept C41008148 @default.
- W3183147992 hasConcept C41608201 @default.
- W3183147992 hasConcept C41895202 @default.
- W3183147992 hasConceptScore W3183147992C11413529 @default.
- W3183147992 hasConceptScore W3183147992C115961682 @default.
- W3183147992 hasConceptScore W3183147992C138885662 @default.
- W3183147992 hasConceptScore W3183147992C153180895 @default.
- W3183147992 hasConceptScore W3183147992C154945302 @default.
- W3183147992 hasConceptScore W3183147992C204321447 @default.
- W3183147992 hasConceptScore W3183147992C2779231336 @default.
- W3183147992 hasConceptScore W3183147992C2779304628 @default.
- W3183147992 hasConceptScore W3183147992C39890363 @default.
- W3183147992 hasConceptScore W3183147992C41008148 @default.
- W3183147992 hasConceptScore W3183147992C41608201 @default.
- W3183147992 hasConceptScore W3183147992C41895202 @default.
- W3183147992 hasLocation W31831479921 @default.
- W3183147992 hasOpenAccess W3183147992 @default.
- W3183147992 hasPrimaryLocation W31831479921 @default.
- W3183147992 hasRelatedWork W1994142342 @default.
- W3183147992 hasRelatedWork W2185524415 @default.
- W3183147992 hasRelatedWork W2405756170 @default.
- W3183147992 hasRelatedWork W2896134062 @default.
- W3183147992 hasRelatedWork W2900085483 @default.
- W3183147992 hasRelatedWork W2913299240 @default.
- W3183147992 hasRelatedWork W2922909102 @default.
- W3183147992 hasRelatedWork W2946453420 @default.
- W3183147992 hasRelatedWork W3023902827 @default.
- W3183147992 hasRelatedWork W3034178211 @default.
- W3183147992 hasRelatedWork W3047180765 @default.
- W3183147992 hasRelatedWork W3048077125 @default.
- W3183147992 hasRelatedWork W3061398139 @default.
- W3183147992 hasRelatedWork W3105974621 @default.