visual-information-extraction

There are 4 repositories under visual-information-extraction topic.

  • SCUT-DLVCLab/Document-AI-Recommendations

    Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.

    2001019

  • ZeningLin/ViBERTgrid-PyTorch

    An unofficial PyTorch implementation of "Lin et al. ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents. ICDAR, 2021"

    Language:Python534115

  • ZeningLin/PEneo

    [MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.

    Language:Python37487

  • SCUT-DLVCLab/RFUND

    [MM'2024] Official release of RFUND introduced in the MM'2024 paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction"

    20100