Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    PDF-VQA: A New Dataset for Real-World VQA on PDF Documents

    Document-based Visual Question Answering examines the document understanding of document images in conditions of natural language questions. We proposed a new document-based VQA dataset, PDF-VQA, to comprehens...

    Yihao Ding, Siwen Luo, Hyunsuk Chung in Machine Learning and Knowledge Discovery i… (2023)