Login / Signup

Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold.

Zijie WangAichun ZhuJingyi XueXili WanChao LiuTian WangYifeng Li
Published in: CoRR (2022)
Keyphrases
  • cross modal
  • learning algorithm
  • multi modal
  • learning tasks
  • multimedia retrieval
  • perceptual information
  • multimedia
  • high dimensional
  • visual recognition
  • low dimensional
  • document retrieval