模式识别系列讲座
lecture series in pattern recognition
题 目(title): deep understanding of users for socio-mobile recommendation
讲 座 人(speaker):梅涛研究员;微软亚洲研究院
主 持 人 (chair): 桑基韬博士
时 间 (time): 3月15日(friday), 上午10:30
地 点 (venue):十三层第二会议室,自动化大厦
报告摘要(abstract):
people are contributing massive social media contents for knowledge sharing anytime and anywhere. deep understanding users from heterogeneous, complex, and dynamic social media therefore becomes important for socio-mobile applications. there are four elements in the loop of understanding a user: user profile, context, multi-modal input, and interactivity. this talk will introduce recent advances for understanding these key elements by leveraging machine intelligence and natural user interaction. specifically, we will introduce: 1) how to predict user attributes from the heterogeneous forms of data by machine learning techniques, 2) how to leverage context information for personalized recommendation, and 3) how to analyze multi-modal user input for cross-media recommendation. we will also showcase recently developed applications of this kind.
报告人简介(biography):
梅涛,微软亚洲研究院多媒体计算组研究员,ieee/acm高级会员,中国科学技术大学兼职教授、博士生导师,西安电子科技大学客座教授。1996年考入中国科学技术大学自动化系,分别于2001年和2006年获工学学士和博士学位,2006年加入微软亚洲研究院。主要研究方向为多媒体分析、检索,以及其在互联网和移动应用的研究。已主持撰写了3本学术专著,在国际学术期刊和会议上发表论文140余篇,并拥有5项美国专利及30余项申请。担任多个国际学术期刊的副主编(neurocomputing, journal of multimedia)和客座编委(ieee trans. on multimedia, acm/springer multimedia systems, ieee multimedia magazine)。
承办单位:模式识别国家重点实验室
|