发表机构
Luleå University of Technology; Karlsruhe Institute of Technology; LATIS-Laboratory of Advanced Technology and Intelligent Systems, National Engineering School of Sousse (ENISo), University of Sousse（吕勒奥理工大学; 卡尔斯鲁厄理工学院; LATIS先进技术与智能系统实验室，苏斯国家工程学院（ENISo），苏斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对表单字段检测中现有数据集标签噪声大、不一致的问题，提出精选基准 mini-CommonForms，提供高质量标注并评估最先进检测方法，以支持可复现研究。
AI 中文摘要
表单字段检测（FFD）是文档理解系统的基础组件，支撑着从大规模工业数字化到面向无障碍的表单交互自动化分析等各类应用。与常规目标检测任务不同，FFD 具有固有挑战性，因为字段通常由布局结构和空白区域而非可见的前景内容来定义。现有的大规模数据集常常依赖启发式标注流程，导致标签噪声大且不一致，从而妨碍了可靠的评估。在本工作中，我们引入了 mini-CommonForms，一个经过精心策划的 FFD 基准，具有一致且高质量的标注，并对最先进的检测方法进行了详细评估。该基准旨在支持文档自动化和无障碍导向应用中的可复现研究。数据集和代码可在以下 https URL 获取。
英文摘要
Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digitization to accessible form interaction for automated analysis. Unlike conventional object detection tasks, FFD is inherently challenging because fields are often defined by layout structure and whitespace rather than visible foreground content. Existing large-scale datasets frequently rely on heuristic annotation pipelines, resulting in noisy and inconsistent labels that hinder reliable evaluation. In this work, we introduce mini-CommonForms, a carefully curated FFD benchmark with consistent, high-quality annotations, and present a detailed evaluation of state-of-the-art detection approaches. The benchmark is designed to support reproducible research in document automation and accessibility-oriented applications. Dataset and code are available at https://github.com/moured/mini-commonforms
CommentsAccepted at the International Workshop on Document Analysis Systems (DAS) 2026. Dataset: https://huggingface.co/datasets/omoured/minicommonform
Journal refDocument Analysis Systems (DAS 2026), Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, pp. 459-473
DOI：10.1007/978-3-032-36207-0_27
