This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. In contrast to existing approaches, our model can understand rich text, whether it is a single word, a phrase, or a sentence, and generate multiple possible palettes from it. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT). Our proposed model called Text2Colors consists of two conditional generative adversarial networks: the text-topalette generation networks and the palette-based colorization networks. The former captures the semantics of the text input and produce relevant color palettes. The latter colorizes a grayscale image using the generated color palette. Our evaluation results show that people preferred our generated palettes over ground truth palettes and that our model can effectively reflect the given palette when colorizing an image.

If it is the author's pre-published version, changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published version.

Having moved through the eras of steam and hydropower, electricity and assembly lines, and then computerization, the world has now entered a new era, dubbed the Fourth Industrial Revolution, with the adoption of cyber-physical systems, the Internet of Things and the Internet of Systems implemented as intelligent machines. The implications of this new era for the education of current and future generations are now a focus of discussion. As artificial intelligence (AI), branching from computer science (CS), becomes ubiquitous and seamless behind the scenes of our daily lives, many countries are dedicating significant resources to fueling research on this continually developing technology. The renewed interest in AI has sparked discussion of the importance of teaching AI knowledge, concepts, and computational skills to young people, including whether we should begin considering how to introduce AI at K-12 level through CS education. This article aims to reshape the concepts of AI with reference to the historical development of the computing industry and CS education, and uncover a new direction for AI education in K-12 around the globe. The Beginning of Computer ScienceThe history of computer science (CS) as a discipline can be traced back to the early 19th century, when Charles Babbage, who is considered a pioneer in the field of computing, designed a computational device: a calculator that was able to compute digits with up to eight decimal points. Working closely with him was Augusta Ada King, Countess of Lovelace, who is acknowledged as a pioneer in computer programming [21]. Although Babbage's invention was able to make mechanical calculations, Lovelace pushed its potential even further by designing an algorithm that could be executed by such a machine. This marks the beginning of what we know as "the computer," and the development of computing technology has shown no signs of waning since.