PAPER

PAPER

2017.08.08

グラフィックデザインにおける各要素の重要性を可視化 – Learning Visual Importance for Graphic Designs and Data Visualizations

  • design
  • FCN

PAPER

2017.07.26

音楽⇄動画のクロスモーダルな検索技術 – Deep Learning for Content-Based, Cross-Modal Retrieval of Videos and Music

  • audio
  • cross-modal
  • video

PAPER

2017.07.25

料理の写真 ↔︎ 材料とレシピ – Learning Cross-modal Embeddings for Cooking Recipes and Food Images

  • cooking
  • food

PAPER

2017.07.09

GANで音楽生成 – MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation using 1D and 2D Conditions

  • cnn
  • GAN
  • midi
  • music

PAPER

2017.06.29

過去の作品を学習することで本当に新しい作品が作れるのか?? – CAN: Creative Adversarial Networks Generating “Art” by Learning About Styles and Deviating from Style Norms

  • creativity
  • GAN
  • psychology

DEMO

PAPER

2017.06.25

人工知能の力を借り、3Dモデルを共作する – Interactive 3D Modeling with a Generative Adversarial Network –

  • 3D
  • 3D modeling
  • GAN
  • image

PAPER

2017.06.07

連想の学習 – See, Hear, and Read: Deep Aligned Representations

  • audio
  • cnn
  • cross-modal
  • image
  • text

PAPER

2017.05.31

服を着ている人の画像を生成 – A Generative Model of People in Clothing

  • fashion
  • pix2pix
  • vae

PAPER

2017.05.15

GANを応用したSANによるSaliency Map(顕著性マップ)の生成 – Supervised Adversarial Networks for Image Saliency Detection –

  • cnn
  • CVPR
  • GAN
  • generative
  • Generative Adversarial Network