Shared Latent Space of Font Shapes and Their Noisy Impressions
This addresses the challenge of subjective and noisy font-impression data for designers and researchers, but it is incremental as it builds on existing latent space and DeepSets techniques.
The paper tackled the problem of noisy impression words for fonts by creating a shared latent space where fonts and their impressions are embedded nearby, using DeepSets to enhance shape-relevant words and suppress irrelevant ones. Experimental results on a large-scale dataset showed that the method appropriately describes correlations, especially for shape-relevant impression words.
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.