内容

讲座信息:Attention module for spatial and temporal relations

阅读数:25    发布:2019-10-22 14:39    

Time9:30-11:30 AM, 25 Oct, 2019

Location理工楼L6 801


Abstract:

In this report, I will talk about our recent works on attention based spatial and temporal analysis for human reconstruction and face action unit analysis. To be specific, we investigated how to efficiently learn skeleton information from point clouds as well as to incorporate spatial relations and temporal relations for facial action unit analysis. 

 

Bio:

Haiyong Jiang earned his Ph.D. degree in computer graphics from the National Laboratory of Pattern Recognition of the Institute of Automation, Chinese Academy of Sciences (CASIA) in 2017. In the present, he works as a postdoc at Nanyang Technological University (NTU). His research interests revolve around 3D vision, 3D scene understanding, and 3D scene modeling.


深圳大学计算机与软件学院 2009-2016