发表机构
Accessful GmbH（阿克塞斯富尔有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对交互式PDF表单字段缺失问题，提出AcroMELD检测器，结合视觉Transformer与PDF基元，在内部测试中F₁值达0.9344，超过历史参考值，同时也暴露了领域与稀有类别性能限制。
AI 中文摘要
在视觉上类似表单的文档中，交互式PDF表单字段往往缺失，导致用户无法输入数据，只能打印或使用外部编辑工具。检测缺失的部件（widget）十分困难，原因包括一个字段可能由多个重叠线索指示、原生数字PDF虽暴露有用信息但绘图结构不完整，以及密集页面可能包含数百个字段。我们提出AcroMELD（AcroForm多源证据链接解码器），这是一个拥有3940万参数的检测器，结合了高分辨率视觉Transformer与无标签PDF基元。其896个查询集合包含384个视觉候选、384个结构种子候选和128个学习型恢复查询。四个图集层在几何偏置的稀疏邻域上交换信息，并交叉关注PDF结构。学习到的同字段关系链接共指候选，而定位质量头则使用下游恢复决策所用的包含感知重叠进行训练。我们定义了一种哈希绑定评估协议，包含互斥的开发、校准、内部测试和隔离的外部保留角色。密封的单种子候选在内部测试中达到原生包含微F₁值0.9344，在一次性外部保留集上达到0.8477（95% PDF聚类自举区间为[0.8339, 0.8605]），比注册的历史FFGBT-v8参考值绝对F₁高出0.0186。然而，在更严格的外部适配器下，性能为0.7786 IoU-0.5 F₁和0.2900 COCO mAP，低于本地评估的CommonForms-L参考；在所选阈值下，签名类未得到任何预测。因此，该结果支持注册的操作门，同时暴露了显著的领域和稀有类别限制。
英文摘要
Interactive PDF form fields are often absent from documents that visually resemble forms, leaving users unable to enter data without printing or external editing tools. Detecting the missing widgets is difficult because a field may be indicated by several overlapping cues, born-digital PDFs expose useful but incomplete drawing structure, and dense pages can contain hundreds of fields. We introduce AcroMELD (AcroForm Multi-source Evidence Linking Decoder), a 39.4M-parameter detector that combines a high-resolution visual transformer with label-free PDF primitives. Its 896-query set comprises 384 visual proposals, 384 structure-seeded proposals, and 128 learned recovery queries. Four graph-set layers exchange information over geometry-biased sparse neighborhoods and cross-attend to PDF structure. A learned same-field relation links co-referent candidates, while a localization-quality head is trained on the containment-aware overlap used by the downstream recovery decision. We define a hash-bound evaluation protocol with disjoint development, calibration, internal-test, and quarantined external-holdout roles. The sealed, single-seed candidate reaches native containment micro-$F_1$ 0.9344 on the internal test and 0.8477 on the one-shot external holdout (95% PDF-cluster bootstrap interval [0.8339, 0.8605]). This passes the registered historical FFGBT-v8 reference by 0.0186 absolute $F_1$. Under the stricter external adapter, however, performance is 0.7786 IoU-$0.5$ $F_1$ and 0.2900 COCO mAP, below a locally evaluated CommonForms-L reference; the signature class receives no prediction at the selected threshold. Thus the result supports the registered operational gate while exposing substantial domain and rare-class limitations.
Comments13 pages, 2 figures, 7 tables. Source compiles to a tagged PDF 2.0 document with MathML embedded as associated files
