Show simple item record

dc.contributor.authorTatsukawa, Yukien_US
dc.contributor.authorShen, I-Chaoen_US
dc.contributor.authorQi, Anranen_US
dc.contributor.authorKoyama, Yukien_US
dc.contributor.authorIgarashi, Takeoen_US
dc.contributor.authorShamir, Arielen_US
dc.contributor.editorBermano, Amit H.en_US
dc.contributor.editorKalogerakis, Evangelosen_US
dc.date.accessioned2024-04-16T14:42:15Z
dc.date.available2024-04-16T14:42:15Z
dc.date.issued2024
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.15043
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf15043
dc.description.abstractAcquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works have alleviated some of these difficulties, they often lack support for multiple languages and semantic attributes beyond the training data domains. To solve this problem, we present FontCLIP – a model that connects the semantic understanding of a large vision-language model with typographical knowledge. We integrate typographyspecific knowledge into the comprehensive vision-language knowledge of a pretrained CLIP model through a novel finetuning approach. We propose to use a compound descriptive prompt that encapsulates adaptively sampled attributes from a font attribute dataset focusing on Roman alphabet characters. FontCLIP's semantic typographic latent space demonstrates two unprecedented generalization abilities. First, FontCLIP generalizes to different languages including Chinese, Japanese, and Korean (CJK), capturing the typographical features of fonts across different languages, even though it was only finetuned using fonts of Roman characters. Second, FontCLIP can recognize the semantic attributes that are not presented in the training data. FontCLIP's dual-modality and generalization abilities enable multilingual and cross-lingual font retrieval and letter shape optimization, reducing the burden of obtaining desired fonts.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleFontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applicationsen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersVector Art and Line Drawings
dc.description.volume43
dc.description.number2
dc.identifier.doi10.1111/cgf.15043
dc.identifier.pages11 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License