Natural Language Model for Image Caption

Chunjie Guo, Weiwei Yang, Huan Xin Peng · 2020

Image caption is a technology that combines the knowledge of computer vision with natural language processing. In this paper, we offer some natural language models by human beings in picture description in hope that they might shed light on relevant research on image caption. The paper concludes that picture descriptions by human beings are rules governed as well as experience oriented. Picture descriptions by human beings are characterized with background knowledge about the world which is lacking in present-day image caption systems.

Read the paper · More papers on PaperTik