Impression-CLIP：面向字体的对比式形状-印象嵌入
Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts
AI总结：
本文提出基于 CLIP 的 Impression-CLIP 模型，通过对比学习实现字体形状与主观印象的联合嵌入，在跨模态检索中优于现有方法，并对噪声和缺失标签具有鲁棒性。
摘要：
字体向读者传达不同的印象，这些印象通常来源于字体形状。然而，字体与其印象之间的相关性较弱且不稳定，因为印象具有主观性。为了捕捉字体形状与其印象之间这种弱且不稳定的跨模态相关性，我们提出了 Impression-CLIP，这是一种基于 CLIP（对比语言-图像预训练）的新型机器学习模型。通过使用基于 CLIP 的模型，字体图像特征与其印象特征被拉近，而字体图像特征与不相关的印象特征被推远。该过程实现了字体图像与其印象之间的联合嵌入。在实验中，我们通过联合嵌入在字体与印象之间进行跨模态检索。结果表明，Impression-CLIP 取得了优于最先进方法的检索准确率。此外，我们的模型表现出对噪声和缺失标签的鲁棒性。
英文摘要：
Fonts convey different impressions to readers. These impressions often come from the font shapes. However, the correlation between fonts and their impression is weak and unstable because impressions are subjective. To capture such weak and unstable cross-modal correlation between font shapes and their impressions, we propose Impression-CLIP, which is a novel machine-learning model based on CLIP (Contrastive Language-Image Pre-training). By using the CLIP-based model, font image features and their impression features are pulled closer, and font image features and unrelated impression features are pushed apart. This procedure realizes co-embedding between font image and their impressions. In our experiment, we perform cross-modal retrieval between fonts and impressions through co-embedding. The results indicate that Impression-CLIP achieves better retrieval accuracy than the state-of-the-art method. Additionally, our model shows the robustness to noise and missing tags.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
