通过字体印象共现关系，学习更精准的字体情感向量。
Embedding Font Impression Word Tags Based on Co-occurrence
- 基于印象标签共现构建图结构，用谱嵌入生成向量。
- 相比BERT和CLIP，相似印象标签向量更接近，提升生成效果。
- 适合需要情感化字体生成与检索的应用场景。
不同字体样式（即字形）传达不同印象，表明字形与描述性标签之间存在紧密关联。本文提出一种新型印象标签嵌入方法，利用这种形状-印象关系。例如，该方法使频繁共现的印象标签具有相近向量，而标准词嵌入方法（如BERT、CLIP）则产生差异较大的向量。这一特性在基于印象的字体生成与字体检索中尤为有效。技术上，我们构建一个节点为印象标签、边表示共现关系的图，再通过谱嵌入获得每个标签的向量表示。在定性和定量评估中，我们的方法在印象引导的字体生成任务中表现优于BERT和CLIP。
原文摘要 · Abstract (English)
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, demonstrating that our approach performs better in impression-guided font generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。