Skip links

  • Skip to primary navigation
  • Skip to content
  • Skip to footer
Douglas M. Souza
  • Research
  • Teaching
  • CV
    Douglas M. Souza

    Douglas M. Souza

    I am a PhD student at the School of Technology of PUCRS. My research is focused on deep generative models that generate images from text descriptions.

    • GitHub
    • LinkedIn
    • ORCID
    • Google Scholar
    • Lattes

    Posts by Tag

    • Deep Neural Networks 3
    • GANs 2
    • Face Pose Synthesis 1
    • Face Frontalization 1
    • Bidirectional Retrieval 1
    • Multimodal learning 1
    • Text-to-Image Generation 1

    Deep Neural Networks

    Efficient Neural Architecturefor Text-to-Image Synthesis

    less than 1 minute read

    Language-Agnostic Visual-Semantic Embeddings

    less than 1 minute read

    Towards High-Resolution Face Pose Synthesis

    less than 1 minute read

    Back to Top ↑

    GANs

    Efficient Neural Architecturefor Text-to-Image Synthesis

    less than 1 minute read

    Towards High-Resolution Face Pose Synthesis

    less than 1 minute read

    Back to Top ↑

    Face Pose Synthesis

    Towards High-Resolution Face Pose Synthesis

    less than 1 minute read

    Back to Top ↑

    Face Frontalization

    Towards High-Resolution Face Pose Synthesis

    less than 1 minute read

    Back to Top ↑

    Bidirectional Retrieval

    Language-Agnostic Visual-Semantic Embeddings

    less than 1 minute read

    Back to Top ↑

    Multimodal learning

    Language-Agnostic Visual-Semantic Embeddings

    less than 1 minute read

    Back to Top ↑

    Text-to-Image Generation

    Efficient Neural Architecturefor Text-to-Image Synthesis

    less than 1 minute read

    Back to Top ↑
    • GitHub
    • LinkedIn
    • ORCID
    • Google Scholar
    • Lattes
    • Feed
    © 2021 Douglas M. Souza. Powered by Jekyll & Minimal Mistakes.