学在北邮

/ Study in BUPT

首页 · 学在北邮 · 学术活动 · 正文

Deep models for face processing with “big” or “small” data

主讲人 :山世光研究员(中国科学院计算技术研究所,中科院智能信息处理重点实验室常务副主任) 地点 :教三楼811会议室 开始时间 : 2015-06-18 09:00 结束时间 : 2015-06-18 11:00

学术讲座通知

   

讲座题目: Deep models for face processing with “big” or “small” data

主讲人:山世光研究员中国科学院计算技术研究所,中科院智能信息处理重点实验室常务副主任

时间:2015618日(周四)上午9:00-11:00

地点:教三楼811会议室

主持人:马占宇副教授(北邮模式识别实验室)

内容摘要:

   Deep learning models,especially CNN, has been successfully applied to face recognition, especially under the evaluation protocol of Labeled Faces in the Wild (LFW), when big face data is available. In this talk, except showing some recent results of CNN feature for video-based face processing (our FG’15 paper), I will also show that alternative deep models such as Auto-Encoder can also benefit face recognition impressively, especially for face alignment (our ECCV14 paper) and pose normalization (our CVPR14 paper) purpose. Both works might imply in caseof “small” data, elaborate deep models can also work well for many computerv ision tasks.

               

该讲座为北京邮电大学60周年校庆系列讲座之一,欢迎全校师生踊跃参加。

           

校学术委员会

信息与通信工程学院

2015年6月9日

分享到