基于对抗学习的跨模态检索方法研究进展

摘要

随着移动设备的普及,互联网上的多媒体数据呈现爆炸性的增长.人们对于能够方便快捷地检索多模态数据的需求日益增强,因此跨模态检索成为一个热门的研究领域.近年来,基于对抗学习的跨模态检索方法在检索精度上的显著提高引起学者们的广泛关注.通过对对抗学习应用到跨模态检索上的方式进行分析归纳,为基于对抗学习的跨模态检索方法的进一步研究提供理论基础.%With the popularity of mobile devices, multimedia data on the Internet has exploded. There is an increasing demand for convenient and fast retrieval of multi-modal data, so cross-modal retrieval has become a hot research topic. In recent years, the cross-modal retrieval method based on adversarial learning has attracted much attention because of its remarkable improvement in retrieval accuracy. Analyzes and sum? marizes the application of adversarial learning to cross-modal retrieval, which provides a theoretical basis for the further study of crossmodal retrieval methods based on adversarial learning.