A Novel Approach to Artistic Textual Visualization via GAN
This addresses the challenge of artistic textual visualization for fields like art and information science, but it appears incremental as it builds on existing GAN and NLP techniques.
The paper tackles the problem of visualizing artistic text by proposing GAN-ATV, a method that creates paintings from poems using a cross-modal approach, and reports experimental results on a new dataset called Cross-Art.
While the visualization of statistical data tends to a mature technology, the visualization of textual data is still in its infancy, especially for the artistic text. Due to the fact that visualization of artistic text is valuable and attractive in both art and information science, we attempt to realize this tentative idea in this article. We propose the Generative Adversarial Network based Artistic Textual Visualization (GAN-ATV) which can create paintings after analyzing the semantic content of existing poems. Our GAN-ATV consists of two main sections: natural language analysis section and visual information synthesis section. In natural language analysis section, we use Bag-of-Word (BoW) feature descriptors and a two-layer network to mine and analyze the high-level semantic information from poems. In visual information synthesis section, we design a cross-modal semantic understanding module and integrate it with Generative Adversarial Network (GAN) to create paintings, whose content are corresponding to the original poems. Moreover, in order to train our GAN-ATV and verify its performance, we establish a cross-modal artistic dataset named "Cross-Art". In the Cross-Art dataset, there are six topics and each topic has their corresponding paintings and poems. The experimental results on Cross-Art dataset are shown in this article.