视觉输入中指代目标对象的多语言表达式理解
Comprehension of Multilingual Expressions Referring to Target Objects in Visual Inputs
AI总结：
本研究针对多语言指代表达式理解问题，构建了含10种语言的统一多语言数据集，提出基于多语言SigLIP2编码器的注意力锚定高效架构，验证了该模型在多语言视觉定位任务上的竞争力与稳定性。
摘要：
指代表达式理解（REC）要求模型基于不同类型的自然语言描述定位图像中的对象。尽管该领域已取得显著进展，但研究仍以英语为中心，无法满足日益增长的全球部署需求。本研究针对多语言REC开展，主要贡献有两点：一是通过机器翻译和基于上下文的翻译增强，系统扩展12个现有英语REC基准，构建涵盖10种语言的统一多语言数据集；二是引入采用多语言SigLIP2编码器的注意力锚定高效神经架构，该方法从注意力分布生成粗略空间锚点，再通过学习到的残差对其进行优化。实验评估表明，即便使用相对较小的模型，在标准基准上仍表现出有竞争力的性能；多语言评估显示其在各语言间具备稳定能力，为高效多语言视觉 grounding 系统的实际可行性提供了支撑。
英文摘要：
Referring Expression Comprehension (REC) requires models to localize objects in images based on different types of natural language descriptions. Even with significant progress, research on the area remains predominantly English-centric, despite increasing global deployment demands. This work addresses multilingual REC through two main contributions. First, we construct a unified multilingual dataset spanning 10 languages, by systematically expanding 12 existing English REC benchmarks through machine translation and context-based translation enhancement. Second, we introduce an attention-anchored efficient neural architecture that uses a multilingual SigLIP2 encoder. Our attention-based approach generates coarse spatial anchors from attention distributions, which are subsequently refined through learned residuals. Experimental evaluation demonstrates competitive performance on standard benchmarks despite the use of a relatively small model. Multilingual evaluation shows consistent capabilities across languages, establishing the practical feasibility of efficient multilingual visual grounding systems.
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。
