Font Shape-to-Impression Translation
Masaya Ueda, Akisato Kimura, Seiichi Uchida

TL;DR
This paper introduces a Transformer-based method for analyzing and translating font shapes into impressions, effectively capturing local part correlations to understand how font features influence perceived impressions.
Contribution
It presents a novel Transformer architecture for part-based font impression analysis and translation, outperforming existing methods in accuracy.
Findings
Transformer-based approaches estimate font impressions more accurately.
The method reveals key local parts responsible for specific impressions.
Approach works for both classification and translation tasks.
Abstract
Different fonts have different impressions, such as elegant, scary, and cool. This paper tackles part-based shape-impression analysis based on the Transformer architecture, which is able to handle the correlation among local parts by its self-attention mechanism. This ability will reveal how combinations of local parts realize a specific impression of a font. The versatility of Transformer allows us to realize two very different approaches for the analysis, i.e., multi-label classification and translation. A quantitative evaluation shows that our Transformer-based approaches estimate the font impressions from a set of local parts more accurately than other approaches. A qualitative evaluation then indicates the important local parts for a specific impression.
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.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Advanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Dropout · Dense Connections · Residual Connection · Layer Normalization · Absolute Position Encodings · Adam · Label Smoothing
