<kbd id="yen5jhfd"></kbd><address id="yen5jhfd"><style id="yen5jhfd"></style></address><button id="yen5jhfd"></button>

              <kbd id="i4g3pn2i"></kbd><address id="i4g3pn2i"><style id="i4g3pn2i"></style></address><button id="i4g3pn2i"></button>

                      <kbd id="l72bbmxp"></kbd><address id="l72bbmxp"><style id="l72bbmxp"></style></address><button id="l72bbmxp"></button>

                              <kbd id="ryqehu8z"></kbd><address id="ryqehu8z"><style id="ryqehu8z"></style></address><button id="ryqehu8z"></button>

                                      <kbd id="bkrhb7p7"></kbd><address id="bkrhb7p7"><style id="bkrhb7p7"></style></address><button id="bkrhb7p7"></button>

                                              <kbd id="ckv39iwy"></kbd><address id="ckv39iwy"><style id="ckv39iwy"></style></address><button id="ckv39iwy"></button>

                                                      <kbd id="e77npiao"></kbd><address id="e77npiao"><style id="e77npiao"></style></address><button id="e77npiao"></button>


                                                          首页 > 讲座 > 正文



                                                          报告内容:Low-resolution face recognition

                                                          报告人:熊子祥 教授 美国德克萨斯A&M大学

                                                          报告时间:2018125 上午 0930



                                                          It has been well publicized that computers can outperform humans in face  recognition provided that the face images have high resolution and quality.  In practical scenarios (e.g., video surveillance), the available face images are often very noisy with low resolution. In this talk, I will give an overview of my group's work on low-resolution face recognition, namely, denoising, super-resolution, and machine learning based face recognition.

                                                          I will also highlight our latest work on virtual/augmented reality,  3D point scene completion from a single depth Image, and 2D pose estimation.


                                                          Zixiang Xiong received the Ph.D. degree in Electrical Engineering in 1996 from the University of Illinois at Urbana-Champaign. From 1995 to 1997, he was with Princeton University, first as a visiting student, then as a research associate. From 1997 to 1999, he was with the University of Hawaii. Since 1999, he has been with the Department of Electrical and Computer Engineering at Texas A&M University, where he is a professor. He spent his sabbatical leaves at Stanford University in spring 2010 and at Monash Univeristy, Australia during the 2017-2018 academic year.
                                                             He received an NSF Career Award in 1999, an ARO Young Investigator Award in 2000, and an ONR Young Investigator Award in 2001. He is co-recipient of the 2006 IEEE Signal Processing Magazine best paper award, top 10% paper awards at the 2011 and 2015 IEEE Multimedia Signal Processing Workshops, an IBM best student paper award at the 2016 IEEE International Conference on Pattern Recognition, and the best demo paper award at the 2018 IEEE International Conference on Multimedia and Expo. He served as associate editor for the IEEE Trans. on Circuits and Systems for Video Technology (1999-2005), the IEEE Trans. on Image Processing (2002-2005), the IEEE Trans. on Signal Processing (2002-2006), the IEEE Trans. on Systems, Man, and Cybernetics (part B) (2005-2009), and the IEEE Trans. on Communications (2008-2013). He is currently an associate editor for the IEEE Trans. on Multimedia. He is a fellow of the IEEE.

                                                          Copyright © 2016 Wuhan,China.All Rights Reserved.

                                                          华中科技大学 新濠天地赌场app 电话: 027-87543235