无提案查询引导网络用于 grounded 多模态命名实体识别
A Proposal-Free Query-Guided Network for Grounded Multimodal Named Entity Recognition
AI总结：
本文提出无提案查询引导网络，通过文本引导和跨模态交互统一多模态推理与解码，提升开放域场景下的命名实体识别精度与鲁棒性。
摘要：
Grounded Multimodal Named Entity Recognition (GMNER) 识别自然语言文本中的命名实体，包括其跨度和类型，并将其与关联图像中的相应区域关联起来。现有方法将此任务分为两步：首先使用预训练的通用检测器检测对象，然后将命名实体匹配到检测到的对象上。然而，这些方法面临主要限制：由于预训练的通用对象检测器与文本实体独立，它们倾向于检测常见对象并经常忽略命名实体所需的特定细粒度区域。这种对象检测器与实体之间的不匹配引入了不精确性，并可能损害整体系统性能。在本文中，我们提出了一种无提案查询引导网络（QGN），通过文本引导和跨模态交互统一多模态推理与解码。QGN 在开放域场景中实现了准确的关联和稳健的性能。广泛的实验表明，QGN 在广泛使用的基准上实现了优于其他 GMNER 模型的顶级性能。
英文摘要：
Grounded Multimodal Named Entity Recognition (GMNER) identifies named entities, including their spans and types, in natural language text and grounds them to the corresponding regions in associated images. Most existing approaches split this task into two steps: they first detect objects using a pre-trained general-purpose detector and then match named entities to the detected objects. However, these methods face a major limitation. Because pre-trained general-purpose object detectors operate independently of textual entities, they tend to detect common objects and frequently overlook specific fine-grained regions required by named entities. This misalignment between object detectors and entities introduces imprecision and can impair overall system performance. In this paper, we propose a proposal-free Query-Guided Network (QGN) that unifies multimodal reasoning and decoding through text guidance and cross- modal interaction. QGN enables accurate grounding and robust performance in open-domain scenarios. Extensive experiments demonstrate that QGN achieves top performance among compared GMNER models on widely used benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
