Fonts Like This but Happier

Kulahcioglu, Tugba; Melo, Gerard de

doi:10.1145/3394171.3413534

Cited by 7 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multilingual Font Retrieval First, we demonstrate FontCLIP's unprecedented generalization capability by showing multilingual font retrieval results using a combination of attributes and image inputs. Our goal aligns with [KdM20], where we aim to retrieve results that preserve the style of input font image while incorporating the desired attributes. Specifically, given a query font image I query and a set of desired attributes A = { a 1 , a 2 ,…, a N }, we obtain the embedding vector of the desired font e desired using the following formulation:

…”

Section: Dual‐modal Multilingual Font Retrievalmentioning

confidence: 99%

“…[OLAH14]. Specifically, we render an image of each font using the text “ The quick brown fox jumps over the lazy dog ”, which is widely used for displaying font samples due to its inclusion of a diverse range of letters [OLAH14, KdM20]. To enhance the robustness of our finetuned model, we apply standard data augmentation techniques such as rotation, cropping, and scaling to the font image (refer to Figure 3).…”

Section: Fontclipmentioning

confidence: 99%

See 1 more Smart Citation

FontCLIP: A Semantic Typography Visual‐Language Model for Multilingual Font Applications

Tatsukawa,

Shen,

et al. 2024

Computer Graphics Forum

View full text Add to dashboard Cite

Acquiring 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 typography‐specific 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.

show abstract

…”

Section: Dual‐modal Multilingual Font Retrievalmentioning

confidence: 99%