Abstract
Handwritten word retrieval is vital for digital archives but remains challenging due to large handwriting variability and cross-lingual semantic gaps. While large vision-language models offer potential solutions, their prohibitive computational costs hinder practical edge deployment. To address this, we propose a lightweight asymmetric dual-encoder framework that learns unified, style-invariant visual embeddings. By jointly optimizing instance-level alignment and class-level semantic consistency, our approach anchors visual embeddings to language-agnostic semantic prototypes, enforcing invariance across scripts and writing styles. Experiments show that our method outperforms 28 baselines and achieves state-of-the-art accuracy on within-language retrieval benchmarks. We further conduct explicit cross-lingual retrieval, where the query language differs from the target language, to validate the effectiveness of the learned cross-lingual representations. Achieving strong performance with only a fraction of the parameters required by existing models, our framework enables accurate and resource-efficient cross-script handwriting retrieval.
Abstract (translated)
手写词检索对于数字档案至关重要，但由于书写风格的多样性以及跨语言语义差距的存在，这一任务依然具有挑战性。虽然大型视觉-语言模型提供了潜在解决方案，但其高昂的计算成本阻碍了在实际边缘设备上的部署。为了解决这个问题，我们提出了一种轻量级的不对称双编码器框架，该框架能够学习统一且风格不变的视觉嵌入。通过同时优化实例级别的对齐和类级别语义一致性，我们的方法将视觉嵌入固定到语言无关的语义原型上，并确保跨书写体系和风格的一致性。实验表明，与28个基准模型相比，我们提出的方法在同语言检索基准测试中实现了最先进的准确率。此外，我们在查询语言不同于目标语言的情况下进行了显式的跨语言检索，以验证学习得到的跨语言表示的有效性。通过使用现有模型所需参数的极小部分就能实现强大的性能，我们的框架能够实现在资源有限条件下的精确和高效的多书写体系手写检索。
URL
https://arxiv.org/abs/2601.11248
