Login / Signup

Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding.

Yue FanLei DingChing-Chen KuoShan JiangYang ZhaoXinze GuanJie YangYi ZhangXin Eric Wang
Published in: CoRR (2024)
Keyphrases
  • computer screen
  • tree structure
  • user friendly
  • graphical user interface
  • tree construction
  • hierarchically organized
  • real time
  • user interface
  • r tree
  • data sets
  • index structure
  • projector camera
  • depth from focus