學(xué)術(shù)講座通知
講座題目: Deep models for face processing with “big” or “small” data
主講人：山世光研究員（中國科學(xué)院計(jì)算技術(shù)研究所，中科院智能信息處理重點(diǎn)實(shí)驗(yàn)室常務(wù)副主任）
時(shí)間：2015年6月18日（周四）上午9:00-11:00
地點(diǎn)：教三樓811會議室
主持人：馬占宇副教授(北郵模式識別實(shí)驗(yàn)室)
內(nèi)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.
該講座為北京郵電大學(xué)60周年校慶系列講座之一，歡迎全校師生踴躍參加。
校學(xué)術(shù)委員會
信息與通信工程學(xué)院
2015年6月9日
