Cross-modal Image Retrieval Considering Semantic Relationships with Object Information
Cross-modal Image Retrieval Considering Semantic Relationships with Object Information
复制标题
DOI：
10.1109/gcce56475.2022.10014358
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Huaying Zhang;Rintaro Yanagi;Ren Togo;Takahiro Ogawa;M. Haseyama
中科院分区：
文献类型：
--
作者：
Huaying Zhang;Rintaro Yanagi;Ren Togo;Takahiro Ogawa;M. Haseyama
跨模态图像检索方法使用户能够通过嵌入空间从文本查询中找到所需的图像。然而，大多数现有的方法没有考虑语义相似的文本和图像的嵌入空间。在本文中，我们提出了一种新的跨模态图像检索方法，可以考虑语义相似的文本和图像之间的关系。该方法利用图像中的目标信息构造了一个与语义相似度相一致的嵌入空间。实验结果表明，与现有方法相比，该方法能有效地保持文本和图像在嵌入空间中的语义相似性。
Cross-modal image retrieval methods enable users to find desired images from a text query via the embedding space. However, most existing methods do not consider the semantically similar texts and images in the embedding space. In this paper, we propose a novel cross-modal image retrieval method that can consider the relationships between semantically similar texts and images. Our method constructs an embedding space consistent with the semantic similarity by using the object information in images. Experimental results verify that our method is effective for keeping the semantically similar texts and images close in the embedding space compared to the existing methods.