Current image captioning systems perform at a merely descriptive level,
essentially enumerating the objects in the scene and their relations. Humans,
on the contrary, interpret images by integrating several sources of prior
knowledge of the world. In this work, we aim to take a step closer to producing
captions that offer a plausible interpretation of the scene, by integrating
such contextual information into the captioning pipeline. For this we focus on
the captioning of images used to illustrate news articles. We propose a novel
captioning method that is able to leverage contextual information provided by
the text of news articles associated with an image. Our model is able to
selectively draw information from the article guided by visual cues, and to
dynamically extend the output dictionary to out-of-vocabulary named entities
that appear in the context source. Furthermore we introduce `GoodNews', the
largest news image captioning dataset in the literature and demonstrate
state-of-the-art results.

该论文提出了一种新的图像描述方法，利用新闻文章中的上下文信息，动态扩展输出词典，通过可视化线索有选择性地从文章中提取信息，能够生成探究场景的描述，同时发表了最大的新闻图像字幕数据集 “GoodNews”，并展示了最先进的结果。