{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/trick-or-treat-thematic-reinforcement-for","title":"Trick or TReAT: Thematic Reinforcement for Artistic Typography","arxiv_id":"1903.07820","date":"2019-03-19","proceeding":null,"authors":["Purva Tendulkar","Kalpesh Krishna","Ramprasaath R. Selvaraju","Devi Parikh"],"abstract":"An approach to make text visually appealing and memorable is semantic\nreinforcement - the use of visual cues alluding to the context or theme in\nwhich the word is being used to reinforce the message (e.g., Google Doodles).\nWe present a computational approach for semantic reinforcement called TReAT -\nThematic Reinforcement for Artistic Typography. Given an input word (e.g. exam)\nand a theme (e.g. education), the individual letters of the input word are\nreplaced by cliparts relevant to the theme which visually resemble the letters\n- adding creative context to the potentially boring input word. We use an\nunsupervised approach to learn a latent space to represent letters and cliparts\nand compute similarities between the two. Human studies show that participants\ncan reliably recognize the word as well as the theme in our outputs (TReATs)\nand find them more creative compared to meaningful baselines.","url_abs":"http://arxiv.org/abs/1903.07820v1","url_pdf":"http://arxiv.org/pdf/1903.07820v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"trick-or-treat-thematic-reinforcement-for","repo_url":"https://github.com/purvaten/treat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.07820","atlas_url":"https://app.syntology.ai/?focus=1903.07820","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}