报告时间：2016年12月29日早上9：30
报告地点：计算机学院三楼会议室
联系人：许佳奕(xujiayi@hdu.edu.cn )
报告内容：
1．Facilitating sparse modeling with sophisticated visual ****ysis tools
滕代一成
日本庆应大学
摘要：During FY2013-2018, we have a governmental project under a Grant-in-Aid for Scientific Research on Innovative Areas called “Initiative for High-Dimensional Data-Driven Science through Deepening of Sparse Modeling” (http://sparse-modeling.jp/index_e.html). In this project, I have been heading a planned visualization research project with a primary goal to construct a visualization platform for understanding the behavior of given high-dimensional data in physical space by projecting it onto a designated information space. For this purpose, we transform relatively low-dimensional data obtained through sparse modeling to two, three, or four-dimensional space where we can fully visualize the characteristics of the original high-dimensional data. The idea behind our project is to establish an interactive model called human-in-the-loop by incorporating visual feedback from the users in the ****ysis of high-dimensional data based on sparse modeling. In this talk, I will give an overview of the governmental project and introduce recent research results from the planned research project, including spectral-based contractible parallel coordinate plots, Biclustering multivariate data for correlated subspace mining, and TimeTubes for visualizing polarization variations in blazars.
报告人简介
藤代一成，日本庆应大学科学技术学院的信息计算科学中心教授，博士生导师。主要研究领域包括：科学计算和应用可视化，融合多模态信息的智能环境媒体技术研究。
藤代教授发表250余篇国际学术论文，参与编写37本书籍，并获得29项学术荣誉。担任包括IEEE Transactions on Visualization，Computer Graphics，Elsevier Science Computers & Graphics，Visual Informatics在内的多个国际著名学术期刊的编委；IEEE Scientific Visualization国际会议和Volume Graphics国际研讨会的指导委员会成员。他是IEEE可视化顶级会议PacificVis的创始人之一，并一直担任会议的指导委员会成员。先后主持24个国际会议，其中包括：VG’03/’05, IEEE SMI’06, IEEE PacificVis’08/’14, Cyberworlds’13, ACM VRCAI’14/’15, TopoInVis’17, 和CGI’17。目前，他是日本图像电子工程师协会的会长，日本国际信息科学基金委成员，日本艺术和科学委员会成员，日本计算模拟和可视化委员会成员，和日本图像协会代表。
2．Using Eye-Tracking for Automatic Film Comic Generation
茅晓阳
日本山梨大学
摘要：A film comic refers to the comic generated with the frames of a movie as the panels. Automatic generation of film comic requires the solution to several challenging problems such as selecting important frames well conveying the whole story, creating comic layout with attractive for the general reader, trimming the frames to fit the shape of panels without corrupting the composition of original image and arranging visually-pleasing speech balloons without hiding important objects in the panel. These problems are story and even user dependent and cannot be solved through naive image/video processing. In this talk I will introduce a project on using eye-tracking to solve these problems. Patterns of eye movement are ****yzed for detecting the change of scenes and gaze information is used for automatically finding the location for inserting and directing the word balloons.
报告人简介
茅晓阳，日本山梨大学计算机科学和工程学部教授，博士生导师。主要研究领域包含：情感计算，计算机美学，视觉感知及其在图像合成方面的应用。
茅晓阳教授在各类国际期刊，重要国际会议上发表了100余篇学术论文，担任了包括Cyberworlds 2013，NICOGRAPH International 2016和Computer Graphics International 2017在内的多个知名国际会议的程序委员会联合主席。