Scene retrieval from input descriptions has been one of the most important applications with the increasing number of videos on the Web. However, this is still a challenging task since semantic gaps between features of texts and videos exist. In this paper, we try to solve this problem by utilizing a textto-image Generative Adversarial Network (GAN), which has become one of the most attractive research topics in recent years. The text-to-image GAN is a deep learning model that can generate

more »

... s from their corresponding descriptions. We propose a new retrieval framework, "Query is GAN", based on the textto-image GAN that drastically improves scene retrieval performance by simple procedures. Our novel idea makes use of images generated by the text-to-image GAN as queries for the scene retrieval task. In addition, unlike many studies on text-to-image GANs that mainly focused on the generation of high-quality images, we reveal that the generated images have reasonable visual features suitable for the queries even though they are not visually pleasant. We show the effectiveness of the proposed framework through experimental evaluation in which scene retrieval is performed from real video datasets. INDEX TERMS Scene retrieval, deep learning, generative adversarial network, text-to-image translation.