Login / Signup

VIPTR: A Vision Permutable Extractor for Fast and Efficient Scene Text Recognition.

Xianfu ChengWeixiao ZhouXiang LiXiaoming ChenJian YangTongliang LiZhoujun Li
Published in: CoRR (2024)
Keyphrases
  • scene text recognition
  • real time
  • computer vision
  • cost effective
  • computationally expensive
  • data sets
  • data mining
  • knowledge base
  • image segmentation
  • high level
  • color images
  • lightweight
  • active vision