Sign in

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Image Manipulation.

Chenliang ZhouFangcheng ZhongA. Cengiz Öztireli
Published in: CoRR (2022)
Keyphrases
  • image manipulation
  • video clips
  • feature vectors
  • feature space
  • co occurrence
  • object detection
  • key frames
  • digital image processing