Login / Signup

UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding.

Hao FengZijian WangJingqun TangJinghui LuWengang ZhouHouqiang LiCan Huang
Published in: CoRR (2023)
Keyphrases
  • high level
  • object recognition
  • text detection