# Hierarchical Co-Embedding of Font Shapes and Impression Tags

arXiv: https://arxiv.org/abs/2604.04158 · HTML: https://mlsanity.com/paper/2604.04158/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry](https://mlsanity.com/paper/1806.03417/) (2018)
- [Representation Tradeoffs for Hyperbolic Embeddings](https://mlsanity.com/paper/1804.03329/) (2018)
- [Hyperbolic Image-Text Representations](https://mlsanity.com/paper/2304.09172/) (2023)
- [Compositional Entailment Learning for Hyperbolic Vision-Language Models](https://mlsanity.com/paper/2410.06912/) (2024)
- [Hyperbolic Contrastive Learning for Visual Representations beyond Objects](https://mlsanity.com/paper/2212.00653/) (2022)
- [Large-scale Tag-based Font Retrieval with Generative Feature Learning](https://mlsanity.com/paper/1909.02072/) (2019)
- [HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning](https://mlsanity.com/paper/2507.17402/) (2025)
- [Impressions2Font: Generating Fonts by Specifying Impressions](https://mlsanity.com/paper/2103.10036/) (2021)
- [FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications](https://mlsanity.com/paper/2403.06453/) (2024)
- [Shared Latent Space of Font Shapes and Their Noisy Impressions](https://mlsanity.com/paper/2103.12347/) (2021)
- [Font Generation with Missing Impression Labels](https://mlsanity.com/paper/2203.10348/) (2022)
- [Is Hyperbolic Space All You Need for Medical Anomaly Detection?](https://mlsanity.com/paper/2505.21228/) (2025)
- [GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models](https://mlsanity.com/paper/2408.07259/) (2024)
- [Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts](https://mlsanity.com/paper/2402.16350/) (2024)
- [Exploring the Effects of Japanese Font Designs on Impression Formation and Decision-Making in Text-Based Communication](https://mlsanity.com/paper/2309.06743/) (2023)
- [Embedding Font Impression Word Tags Based on Co-occurrence](https://mlsanity.com/paper/2508.18825/) (2025)

## Abstract (arXiv)

Font shapes can evoke a wide range of impressions, but the correspondence between fonts and impression descriptions is not one-to-one: some impressions are broadly compatible with diverse styles, whereas others strongly constrain the set of plausible fonts. We refer to this graded constraint strength as style specificity. In this paper, we propose a hyperbolic co-embedding framework that models font--impression correspondence through entailment rather than simple paired alignment. Font images and impression descriptions, represented as single tags or tag sets, are embedded in a shared hyperbolic space with two complementary entailment constraints: impression-to-font entailment and low-to-high style-specificity entailment among impressions. This formulation induces a radial structure in which low style-specificity impressions lie near the origin and high style-specificity impressions lie farther away, yielding an interpretable geometric measure of how strongly an impression constrains font style. Experiments on the MyFonts dataset demonstrate improved bidirectional retrieval over strong one-to-one baselines. In addition, traversal and tag-level analyses show that the learned space captures a coherent progression from ambiguous to more style-specific impressions and provides a meaningful, data-driven quantification of style specificity.