Sign in

Show, Deconfound and Tell: Image Captioning with Causal Inference.

Bing LiuDong WangXu YangYong ZhouRui YaoZhiwen ShaoJiaqi Zhao
Published in: CVPR (2022)
Keyphrases
  • causal inference
  • additive noise
  • input image
  • multiscale
  • edge detection
  • feature extraction
  • prior knowledge
  • test images