Embedding Font Impression Word Tags Based on Co-occurrence
Yugo Kubota, Seiichi Uchida

TL;DR
This paper introduces a spectral embedding method for impression tags based on co-occurrence data, improving impression-guided font generation and retrieval over standard models like BERT and CLIP.
Contribution
A novel spectral embedding approach for impression tags that captures co-occurrence relationships, enhancing font generation and retrieval tasks.
Findings
Our method produces more coherent impression vectors than BERT and CLIP.
Improved performance in impression-guided font generation tasks.
Spectral embedding effectively captures co-occurrence relationships among impression tags.
Abstract
Different font styles (i.e., font shapes) convey distinct impressions, indicating a close relationship between font shapes and word tags describing those impressions. This paper proposes a novel embedding method for impression tags that leverages these shape-impression relationships. For instance, our method assigns similar vectors to impression tags that frequently co-occur in order to represent impressions of fonts, whereas standard word embedding methods (e.g., BERT and CLIP) yield very different vectors. This property is particularly useful for impression-based font generation and font retrieval. Technically, we construct a graph whose nodes represent impression tags and whose edges encode co-occurrence relationships. Then, we apply spectral embedding to obtain the impression vectors for each tag. We compare our method with BERT and CLIP in qualitative and quantitative evaluations,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
