An End-to-End OCR Text Re-organization Sequence Learning for Rich-Text Detail Image Comprehension.
Liangcheng LiFeiyu GaoJiajun BuYongpan WangZhi YuQi ZhengPublished in: ECCV (25) (2020)
Keyphrases
- end to end
- printed documents
- scanned documents
- multiscale
- image data
- text recognition
- input image
- reinforcement learning
- document analysis
- text lines
- admission control
- congestion control
- wireless ad hoc networks
- optical character recognition
- scanned images
- web services
- ad hoc networks
- video coding
- image retrieval
- image sequences