特邀报告丨当人工智能（AI）遇上平面设计

Graphic design plays a big role as a communication tool to convey information in modern life, such as posters, slides, websites, and advertisements. However, creating an aesthetically pleasing design while achieving some high-level subjective goals (e.g., theme and personality) to catch audience’s attention is a challenging task. The task requires a lot of expertise and rich design experience, which can often be overwhelming for novices under hundreds of thousands of options on design elements. Since machine learning has shown great potential in many practical areas, can it also ease the burden for graphic design process? In this talk, I will introduce my recent works on data-driven graphic design. I will first talk about the computational model developed for understanding the human perception (i.e., personality) on graphic design and show how it can benefit a broad range of design applications. Then, I will focus on methods designed for different design components. How to use the limited data and supervision signal for guiding the model to achieve good results will also be one of the key ideas of this talk.

嘉宾介绍

赵南轩，香港中文大学MMLab博士后。她在香港城市大学取得博士学位，并在博士期间分别和微软亚洲研究院，哈佛，麻省理工，及Adobe等多个机构合作实习交流。她的主要研究方向为 计算机图形学，计算机视觉和人机交互的交叉方向。致力于研究基于数据驱动的平面设计和无监督学习。曾发表十余篇高质量学术会议和期刊，包括SIGGRAPH, TOG, CHI, CVPR, ICCV, ICLR 等。

提问讨论

14:30 - 15:00