学术报告:群体智慧在多媒体计算中的应用

撰写时间:2017-12-20来源:bt365在线投注

报告人:魏骁勇教授,四川大学
时间:2017年12月21日下午4点
地点:数学与信息学院201报告厅


摘要:Due to the explosive growth of images and videos nowadays, multimedia computing, which focuses on techniques for organizing and searching large-scale multimedia data, has attracted intensive attentions from both researchers and industrial practitioners in the last decade. The “Wisdom of Crowds” refers to the collaborative utilization of multiple modalities or sources instead of relying on a single one alone for decision making, which has been successfully practiced in multimedia computing due to the multi-sourcing nature of multimedia data. In this talk, we introduce the recent research carried out by the Multimedia Computing Group of Sichuan University by using this philosophy, including 1) coached active learning, the first framework for modeling the user’s query intention in interactive video search; 2) in-class social network mining, the first automatic method for mining social interactions in classrooms based on a social network-augmented face recognition scheme; and 3) collocative near-duplicate retrieval, the first domain-specific method for near-duplicate image search that is specifically designed for merchandize image retrieval.


报告人简介:

    Xiao-Yong Wei is a Professor with the College of Computer Science, Chengdu, Sichuan University of China. He received his Ph.D. degree in Computer Science from City University of Hong Kong and has worked as a postdoctoral fellow in University of California, Berkeley. He has been serving the technical program committees of numerous multimedia and information retrieval conferences including ACM Multimedia (MM), ACM SIGIR, International Conf. on Multimedia Retrieval (ICMR) and International Conf. on Multimedia and Expo (ICME). He is one of the founding members of the VIREO multimedia retrieval group, City University of Hong Kong. His research interests include multimedia retrieval, data mining, and machine learning. His research has been widely reported by BBC, Telegraph, Now This, Digital Trends, and other international media.


欢迎广大师生莅临参加!



0