StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training.
Yuechen YuYulin LiChengquan ZhangXiaoqiang ZhangZengyuan GuoXiameng QinKun YaoJunyu HanErrui DingJingdong WangPublished in: ICLR (2023)
Keyphrases
- document images
- document image analysis
- document analysis
- document image understanding
- optical character recognition
- language identification
- scanned documents
- page segmentation
- visual features
- line extraction
- page layout
- visual information
- document processing
- natural language
- document layout
- historical documents
- printed documents
- multimedia
- camera captured document