学术讲座

首页 > 通知动态  > 学术讲座
2019年7月5日学术报告(刘俊 博士,新加坡南洋理工大学)
2019年07月03日16时 人评论

报告题目:Context Modeling for Human Action Recognition

报告时间:201975日(周)上午10:00

报告地点:计算机学院B404会议室

报告人:刘俊

报告人单位:新加坡南洋理工大学

 

报告人简介:

Jun Liu is completing his PhD work at the Rapid-Rich Object Search Lab, Nanyang Technological University, Singapore. He obtained the M.Sc degree in Computer Science from Fudan University, China in 2014, and the B.Eng degree in Software Engineering from Central South University, China in 2011. He published 4 TPAMI, 1 TIP, 2 CVPR, and 1 ECCV papers as the first author during his PhD study. His Google Scholar citations reach 1200. His research interests include computer vision and deep learning. 

报告摘要

Human action understanding is an important and hot research problem due to its wide applications in security surveillance, self-driving vehicles, robotics, and human-machine interaction. Spatio-temporal context modeling and learning is crucial for this task. In this talk, several deep learning architectures for human action recognition will be introduced, which include networks on modeling the spatio-temporal context dependencies in action video sequences, frameworks on selecting the most important and proper context for action analysis, and mechanisms on improving robustness of deep networks by taking advantage of the spatio-temporal context information.   

 

邀请人:杜博 教授


版权所有 ©武汉大学计算机学院 | copyright © 2008-2019 School of Computer Science, Wuhan University. All Rights Reserved.