# Shared Latent Space of Font Shapes and Their Noisy Impressions

arXiv: https://arxiv.org/abs/2103.12347 · HTML: https://mlsanity.com/paper/2103.12347/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [From Captions to Visual Concepts and Back](https://mlsanity.com/paper/1411.4952/) (2014)
- [Large-scale Tag-based Font Retrieval with Generative Feature Learning](https://mlsanity.com/paper/1909.02072/) (2019)
- [Impressions2Font: Generating Fonts by Specifying Impressions](https://mlsanity.com/paper/2103.10036/) (2021)
- [Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders](https://mlsanity.com/paper/1906.06142/) (2019)
- [Let Me Choose: From Verbal Context to Font Selection](https://mlsanity.com/paper/2005.01151/) (2020)
- [Serif or Sans: Visual Font Analytics on Book Covers and Online Advertisements](https://mlsanity.com/paper/1906.10269/) (2019)
- [Effect of Text Color on Word Embeddings](https://mlsanity.com/paper/2004.08526/) (2020)

## Built on by (most cited first, 7 of 7)

- [Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts](https://mlsanity.com/paper/2402.16350/) (2024)
- [VecGlypher: Unified Vector Glyph Generation with Language Models](https://mlsanity.com/paper/2602.21461/) (2026)
- [Embedding Font Impression Word Tags Based on Co-occurrence](https://mlsanity.com/paper/2508.18825/) (2025)
- [Local Style Awareness of Font Images](https://mlsanity.com/paper/2310.06337/) (2023)
- [Font Impression Estimation in the Wild](https://mlsanity.com/paper/2402.15236/) (2024)
- [Total Disentanglement of Font Images into Style and Character Class Features](https://mlsanity.com/paper/2403.12784/) (2024)
- [Hierarchical Co-Embedding of Font Shapes and Impression Tags](https://mlsanity.com/paper/2604.04158/) (2026)

## Abstract (arXiv)

Styles of typefaces or fonts are often associated with specific impressions, such as heavy, contemporary, or elegant. This indicates that there are certain correlations between font shapes and their impressions. To understand the correlations, this paper realizes a shared latent space where a font and its impressions are embedded nearby. The difficulty is that the impression words attached to a font are often very noisy. This is because impression words are very subjective and diverse. More importantly, some impression words have no direct relevance to the font shapes and will disturb the realization of the shared latent space. We, therefore, use DeepSets for enhancing shape-relevant words and suppressing shape irrelevant words automatically while training the shared latent space. Quantitative and qualitative experimental results with a large-scale font-impression dataset demonstrate that the shared latent space by the proposed method describes the correlation appropriately, especially for the shape-relevant impression words.