[4] LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
·
Paper Review/Key Information Extraction
논문 링크: https://arxiv.org/pdf/2104.08836.pdf github: https://github.com/microsoft/unilm GitHub - microsoft/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities - GitHub - microsoft/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities github.com hug..
[3] LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding
·
Paper Review/Key Information Extraction
논문 링크: https://arxiv.org/pdf/2012.14740.pdf Github: https://github.com/microsoft/unilm GitHub - microsoft/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities - GitHub - microsoft/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities github.com hug..
[2] Spatial Dual-Modality Graph Reasoning for Key Information Extraction
·
Paper Review/Key Information Extraction
논문 링크: https://arxiv.org/pdf/2103.14470v1.pdf github: https://github.com/open-mmlab/mmocr GitHub - open-mmlab/mmocr: OpenMMLab Text Detection, Recognition and Understanding Toolbox OpenMMLab Text Detection, Recognition and Understanding Toolbox - GitHub - open-mmlab/mmocr: OpenMMLab Text Detection, Recognition and Understanding Toolbox github.com https://github.com/PaddlePaddle/PaddleOCR GitHub ..
[1] Visual FUDGE: Form Understanding via Dynamic Graph Editing
·
Paper Review/Key Information Extraction
논문 링크: https://arxiv.org/pdf/2105.08194v2.pdf github: https://github.com/herobd/FUDGE