中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组


您所在的位置 / 新闻动态

新闻动态

【学术报告】意大利特伦托大学Nicu Sebe教授于8月24日来访实验室

发表日期:2018-08-22      点击击数: 79

报告题目:Deep Learning for Analysis and Generation of Facial Attributes

时间:8月24日周五下午13:30-15:00

地点:计算所446会议室


报告摘要:Face analysis is a fundamental and challenging problem in computer vision. For face an-alysis, one of the fundamental techniques is face alignment which is usually employed as the preprocessing step.  For instance, when we do face verification, the faces need to be aligned first. On top of that, face pose and facial expression normalization is also a very important preprocessing step. In addition to the disturbance of the poses and expression,another very important factor that might degrade the performance of face verification is age. Thus , modeling the aging process of human faces is important for cross-age faces verification and recognition. Similar to face verification, a face aging task also needs to normalize the face poses and expressions, and many works have been proposed to nor-malize for facial expressions.  However,  only a few works have studied how to generate faces having various expressions, such as spontaneous or posed smiles. In this presenta-tion, we will present our recent results on face alignment, face aging, and smile videos generation employing recurrent neural networks, such as the Long Short Term Memory(LSTM) and the Gated Recurrent Unit (GRU).


报告人简介:Nicu Sebe is a professor in the University of Trento, Italy, where he is the Director of the Department of Information Engineering and Computer Science.  He is also leading the Research in areas of multimedia information retrieval and human-computer interaction in computer vision applications. He was involved in the organization of the major confer-ences  and workshops addressing the computer vision and human-centered aspects of multimedia information retrieval, among which as a General Co-Chair of IEEE Automatic Face and Gesture Recognition Conference, FG 2008,  ACM International Conference on Image and Video Retrieval (CIVR) 2007 and 2010. He was a general  chair of ACM Multi-media 2013 and ACM ICMR 2017 and program chair of ACM Multimedia 2011 and 2007, ECCV 2016 and ICCV 2017.  He is the program chair of ICPR 2020.  Currently he is the ACM SIGMM vice chair. He is a fellow of IAPR and a Senior member of ACM and IEEE.


视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060