DocVQA: A Dataset for VQA on Document Images.
Minesh MathewDimosthenis KaratzasR. ManmathaC. V. JawaharPublished in: CoRR (2020)
Keyphrases
- document images
- image database
- document image analysis
- printed documents
- document analysis
- optical character recognition
- document image understanding
- document processing
- video database
- page segmentation
- mathematical formulas
- page layout
- language identification
- scanned documents
- scanned images
- historical documents
- binary images
- multimedia
- line extraction
- image binarization
- document image retrieval