TY - CONF AU - Andrea Gemelli AU - Sanket Biswas AU - Enrico Civitelli AU - Josep Llados AU - Simone Marinai A2 - ECCV-TiE PY - 2022// TI - Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks T2 - LNCS BT - 17th European Conference on Computer Vision Workshops SP - 329–344 VL - 13804 N2 - Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection. SN - 978-3-031-25068-2 UR - https://link.springer.com/chapter/10.1007/978-3-031-25069-9_22 L1 - http://refbase.cvc.uab.es/files/GBC2022.pdf UR - http://dx.doi.org/10.1007/978-3-031-25069-9_22 N1 - DAG; 600.162; 600.140; 110.312 ID - Andrea Gemelli2022 ER -