Deep Generative Multimedia Children's Literature
This work addresses the problem of generating integrated multimedia content for children's literature, which is incremental as it combines existing models in a new application domain.
The authors tackled the challenge of creating multimedia children's literature using machine learning by designing a system that leverages publicly available pretrained deep neural network models, resulting in multiple generated examples and an exploration of associated problems in creative work.
Artistic work leveraging Machine Learning techniques is an increasingly popular endeavour for those with a creative lean. However, most work is done in a single domain: text, images, music, etc. In this work, I design a system for a machine learning created multimedia experience, specifically in the genre of children's literature. We detail the process for exclusively using publicly available pretrained deep neural network based models, I present multiple examples of the work my system creates, and I explore the problems associated in this area of creative work.