【摘要】 图像描述是计算机视觉应用于视觉理解的一项基础任务,主要任务是将一幅图片翻译为一段描述性文字,其也是一个融合计算机视觉和自然语言处理的综合问题。近些年神经网络技术的发展和大数据的兴起为视觉和语言之间搭建一座桥梁,引发图像描述的研究热潮。对近些年应用于图像描述任务中的神经网络方法进行回顾与总结,并介绍图像描述任务常用的数据集。更多还原

【Abstract】 Image caption is similar to translating a picture into a descriptive text. It is a basic task of computer vision applied to visual understanding,and a comprehensive problem that combines computer vision and natural language processing. In recent years, the development of neural network technology and the rise of big data have established a bridge between vision and language, which has triggered a wave of research on image caption. This paper reviews and summarizes the neural network methods used in image caption tasks in recent years, and introduces commonly used image caption data sets.更多还原