Visually Rich Documents (VRDs) are essential in academia, finance, medical fields, and marketing due to their multimodal information content. Traditional methods for extracting information from VRDs depend on expert knowledge and manual labor, making them costly and inefficient. The advent of deep learning has revolutionized this process, introducing models that leverage multimodal information vision, text, and layout along with pretraining tasks to develop comprehensive document representations. These models have achieved state-of-the-art performance across various downstream tasks, significantly enhancing the efficiency and accuracy of information extraction from VRDs. In response to the growing demands and rapid developments in Visually Rich Document Understanding (VRDU), this paper provides a comprehensive review of deep learning-based VRDU frameworks. We systematically survey and analyze existing methods and benchmark datasets, categorizing them based on adopted strategies and downstream tasks. Furthermore, we compare different techniques used in VRDU models, focusing on feature representation and fusion, model architecture, and pretraining methods, while highlighting their strengths, limitations, and appropriate scenarios. Finally, we identify emerging trends and challenges in VRDU, offering insights into future research directions and practical applications. This survey aims to provide a thorough understanding of VRDU advancements, benefiting both academic and industrial sectors.

翻译：视觉丰富文档（VRDs）因其多模态信息内容，在学术、金融、医疗和营销领域至关重要。传统从VRDs中提取信息的方法依赖于专家知识和人工劳动，成本高昂且效率低下。深度学习的出现彻底改变了这一过程，引入了利用多模态信息（视觉、文本和布局）以及预训练任务来开发全面文档表示的模型。这些模型在各种下游任务中实现了最先进的性能，显著提高了从VRDs中提取信息的效率和准确性。针对视觉丰富文档理解（VRDU）日益增长的需求和快速发展，本文对基于深度学习的VRDU框架进行了全面综述。我们系统性地调研和分析了现有方法和基准数据集，并根据采用的策略和下游任务对其进行了分类。此外，我们比较了VRDU模型中使用的不同技术，重点关注特征表示与融合、模型架构和预训练方法，同时强调其优势、局限性和适用场景。最后，我们指出了VRDU领域的新兴趋势和挑战，并对未来研究方向和实际应用提出了见解。本综述旨在提供对VRDU进展的深入理解，以惠及学术界和工业界。