时间：5.23（周三）14:00

地点：博识楼434

题目：Computer Vision Computing Models in Social Media Analysis

主讲人介绍：付彦伟，复旦大学大数据学院青年研究员，目前主要研究领域包括零样本、小样本识别、终生学习算法，人脸识别及行人再识别，及视频情感分析等。2014年获得伦敦大学玛丽皇后学院博士学位，2014年12月至2016年7月，在美国Disney Research博士后研究员。先后入选上海市扬帆计划、上海高校特聘教授(东方学者)等。有IEEE TPAMI, CVPR等顶级期刊会议论文30篇，15项中国、2项美国专利等。论文被美国多家科技媒体报道，如Science 2.0, PhyORG, Science Newsline Technology, Science 2.0, Communications of ACM, Business Standard, Science Newsline Technology, PhyORG, EurekAlert! AAAS等。他是多个国际期刊、学术会议长期审稿人及程序委员会委员（如IEEE TPAMI, IJCV, ACM MM, NIPS, ICCV等）等。

摘要：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 vision computing architecture to transfer the information of old tasks to new tasks. In this talk, we will summarize the key challenges and limitations of vision computing models in social media analysis. We show the benefits of solving these challenges and limitations in our approach which thus achieves better performance than previous methods.