.png){kind=icon}
返回
Boosting Entity-Aware Image Captioning With Multi-Modal Knowledge Graph
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2023.3301279.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between named entities and visual cues due to the long-tail distribution of named entities. Furthermore, the complexity of the article brings difficulty in extracting fine-grained relationships between entities to generate informative event descriptions about the image. To tackle these challenges, we propose a novel approach that constructs a multi-modal knowledge graph (MMKG) to associate the visual objects with named entities and capture the relationship between entities simultaneously with the help of external knowledge collected from the web. Specifically, we build a text sub-graph by extracting named entities and their relationships from the article, and build an image sub-graph by detecting the objects in the image. To connect these two sub-graphs, we propose a cross-modal entity matching module trained using a knowledge base that contains Wikipedia entries and the corresponding images. Finally, the MMKG is integrated into the captioning model via a graph attention mechanism. Extensive experiments on both GoodNews and NYTimes800 k datasets demonstrate the effectiveness of our method.
Keyword:
Image captioning
named entity
knowledge graph
期刊
IF:
9.7
论文数:
4.7K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容