CVMar 19, 2019

Trick or TReAT: Thematic Reinforcement for Artistic Typography

arXiv:1903.07820v116 citations
Originality Incremental advance
AI Analysis

This addresses the need for automated artistic typography in design and communication, though it is incremental as it builds on existing semantic reinforcement concepts.

The paper tackles the problem of making text visually appealing and memorable by developing TReAT, a computational approach for semantic reinforcement that replaces letters in a word with theme-relevant cliparts. Human studies show participants reliably recognize the word and theme in the outputs, finding them more creative than baselines.

An approach to make text visually appealing and memorable is semantic reinforcement - the use of visual cues alluding to the context or theme in which the word is being used to reinforce the message (e.g., Google Doodles). We present a computational approach for semantic reinforcement called TReAT - Thematic Reinforcement for Artistic Typography. Given an input word (e.g. exam) and a theme (e.g. education), the individual letters of the input word are replaced by cliparts relevant to the theme which visually resemble the letters - adding creative context to the potentially boring input word. We use an unsupervised approach to learn a latent space to represent letters and cliparts and compute similarities between the two. Human studies show that participants can reliably recognize the word as well as the theme in our outputs (TReATs) and find them more creative compared to meaningful baselines.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes