计算机与数字工程2026，Vol.54Issue(3)：601-606,6.DOI:10.3969/j.issn.1672-9722.2026.03.003
基于多层Transformer的细粒度图像-文本检索算法
Fine-grained Image-text Retrieval Algorithm Based on Multi-layer Transformer
摘要
Abstract
Most traditional deep learning-based image-text retrieval algorithms use CNN and RNN networks to encode image and text data.Such methods cannot fully exploit the fine-grained interaction information across modalities.To address this problem,a Transformer-based image-text retrieval network is proposed.It models the fine-grained interactions within and between modalities through two multilayer Transformer modules respectively,while using a CCA-based feature fusion method to obtain a higher quality feature representation.Finally it maximizes the relevance of paired samples through a feature similarity matrix.Comparative experi-ments conducted on two benchmark datasets,Wikipedia and Pascal Sentence,validate the effectiveness of the paper's approach.关键词
图像-文本检索/Transformer/细粒度交互/相似度矩阵Key words
image-text retrieval/Transformer/fine-grained interaction/similarity matrix分类
信息技术与安全科学引用本文复制引用
龚安,李丙寒..基于多层Transformer的细粒度图像-文本检索算法[J].计算机与数字工程,2026,54(3):601-606,6.基金项目
中央高校基本科研业务费专项资金(编号:20CX05019A) （编号:20CX05019A）
中石油重大科技项目(编号:ZD2019-183-004)资助. （编号:ZD2019-183-004）
