活动通知：GAMES Webinar344期-智能图表生成与风格化（10月17日）

报告题目

Reviving Static Charts into Live Charts

报告嘉宾

应璐

浙江大学

报告时间

2024年10月17号 晚上8:00-8:30（北京时间）

报告方式

GAMES直播间: https://live.bilibili.com/h5/24617282

报告摘要

Data charts are prevalent across various fields due to their efficacy in conveying complex data relationships. However, static charts may sometimes struggle to engage readers and efficiently present intricate information, potentially resulting in limited understanding. We introduce “Live Charts,” a new format of presentation that decomposes complex information within a chart and explains the information pieces sequentially through rich animations and accompanying audio narration. We propose an automated approach to revive static charts into Live Charts. Our method integrates GNN-based techniques to analyze the chart components and extract data from charts. Then we adopt large natural language models to generate appropriate animated visuals along with a voice-over to produce Live Charts from static ones. We conducted a thorough evaluation of our approach, which involved the model performance, use cases, a crowd-sourced user study, and expert interviews. The results demonstrate Live Charts offer a multi-sensory experience where readers can follow the information and understand the data insights better. We analyze the benefits and drawbacks of Live Charts over static charts as a new information consumption experience.

Lu Ying (应璐) is a fifth-year PhD student in the School of Computer Science and Technology at Zhejiang University, under the supervision of Prof. Yingcai Wu. Her research primarily focuses on data storytelling and glyph-based visualization. She is dedicated to integrating AI techniques into visualization to simplify the creation process. Additionally, she conducts foundational and advanced research in visual analytics, with significant achievements in intelligent visualization generation and information visualization storytelling. She has published four first-author papers in top-tier journals and conferences, including IEEE TVCG, IEEE VIS, and ACM CHI.

https://yiyinyinguu.github.io/

报告题目

Bridging Data and Semantics: Innovative Approaches to Infographics and Typography Design

报告嘉宾

肖诗诗

Brown University

报告时间

2024年10月17号 晚上8:30-9:00（北京时间）

报告方式

GAMES直播间: https://live.bilibili.com/h5/24617282

报告摘要

We introduce two systems that seamlessly integrate data and semantic context into visual representations, advancing both infographic and typography design. Unlike conventional approaches that rely on retrieval and predefined visual elements, ChartSpark generates visualizations conditioned on both textual semantic inputs and numerical data from charts, accommodating a wide range of design needs for both foreground and background elements. To extend this method to more generalized data formats, we developed TypeDance, which focuses on semantic typographic logos by blending typefaces and imagery to convey meaning while preserving legibility. TypeDance utilizes AI-assisted design, integrating user input and personalized design rationales to create logos that harmonize typeface and imagery at various structural levels. This tool offers flexible control over the design process—enabling ideation, generation, evaluation, and iteration— with user evaluations confirming its effectiveness across diverse design tasks.

嘉宾简介

Shishi Xiao (肖诗诗) graduated from The Hong Kong University of Science and Technology (Guangzhou), where she was supervised by Professor Wei Zeng during her master’s program. She is currently a first-year PhD student in Computer Science at Brown University. Her research focuses on human-computer interaction and data visualization, particularly in developing creative tools for effective communication. Her work has been published in leading conferences such as IEEE VIS and ACM CHI.

个人主页

主持人简介

李晨辉

华东师范大学

华东师范大学计算机科学与技术学院副教授，CCF计算机辅助设计与图形学专委会执行委员，CSIG可视化与可视分析专委会委员。博士毕业于香港理工大学，专注数据可视化、空间大数据智能分析、计算机图形学研究，主持国家及校企合作科研项目10余项，在IEEE VIS、IEEE TVCG、ACM CHI、IEEE VR等国际会议及期刊上发表学术论文50余篇，曾担任ChinaVis2018会议组织委员，VINCI2019国际会议本地主席，CAD/CG 2023及CAD/Graphics 2023会议组织主席，ChinaVis2024会议论文主席。长期担任VIS、TVCG、CHI等国际期刊及会议的审稿人。曾获2020年度上海市科技进步特等奖，2022年度上海市高等教育教学成果二等奖。更多信息见：

http://chenhui.li

陆旻

深圳大学

深圳大学助理教授，研究方向为数据可视化和人机交互，近年来在可视化、人机交互国际会议IEEE VIS，ACM CHI等发表论文多篇，获ChinaVis 2016最佳海报奖、ICUI 2017最佳论文奖、IEEE PacificVis 2018最佳海报奖、Computational Visual Media 2020最佳论文提名、IEEE PacificVis 2024最佳论文提名等奖项，担任IEEE PacificVis、ChinaVis等会议程序委员，长期担任IEEE VIS，IEEE TVCG, ACM TIST等审稿人，更多信息请访问个人主页：https://deardeer.github.io/。

GAMES网站: http://games-cn.org