Visit ShanghaiTech University | 中文 | How to find us
HOME > News and Events > Events
Life-long Learning in Social Media Analysis
Date: 2017/4/27             Browse: 427
Speaker:  Yanwei Fu
Time:        Apr 27, 4:00 pm – 5:00pm.
Location:  Auditorium, SIST Building
Inviter:    Prof.Shenghua Gao
Abstract:

For the past decade computer vision research has achieved increasing success in visual recognition including object detection and video classification. Nevertheless, these achievements still cannot meet the urgent needs of image and video understanding. The recently rapid development of social media sharing has created a huge demand for automatic media classification and annotation techniques. One promising solution is to employ  life-long learning to transfer the  information to tasks for which no data have been observed so far. In this talk, we will summarize the key challenges and limitations of life-long learning in image/video understanding. We show the benefits of solving these challenges and limitations in our approach which thus achieves better performance than previous methods.

Bio:

付彦伟博士现任复旦大学大数据学院青年副研究员。他于20119-201411月在英国伦敦大学玛丽皇后学院的计算机科学系攻读并获得博士学位。201412月至20167月,在美国匹兹堡卡内基梅隆大学迪士尼研究院从事博士后研究工作。20167月,他加入复旦大学大数据学院,主要研究领域包括图像处理与模式识别、机器学习。他已在国际期刊及会议发表论文共17篇;11篇第一作者论文,2篇通讯作者论文。其中包括3篇以第一作者身份发表的IEEE TPAMI长篇论文(该杂志2015年的影响因子高达6.077)。他是IEEE TPAMI, IEEE TMM, IEEE TCSVTAAAI 等国际顶级期刊、会议的长期审稿人。其相关研究成果他引数超过400次:其中,关于多视点视频内容分析与摘要的论文被IEEE通信学会MMTC-Letters专文评论推荐;关于半监督词汇学习(semi-supervised vocabulary-informed learning)的论文被选为CVPR2016口头报告,并被美国多家科技媒体报道。


SIST-Seminar 17014