Wang and Xiong receive prestigious 2016 ICPR best paper award

Bo Wang Image of Zixiang XiongBo Wang (left) and Dr. Zixiang Xiong (right), researchers in the Department of Electrical and Computer Engineering at Texas A&M University, received the prestigious 2016 International Conference on Pattern Recognition (ICPR) best paper award. Xiong and Wang won the award for their paper “Adaptive Boosting for Image Denoising: Beyond Low-Rank Representation and Sparse Coding.”

In the past decade, much progress has been made in image denoising due to the use of low-rank representation and sparse coding. In the meanwhile, state-of-the-art algorithms also rely on an iteration step to boost the denoising performance. However, the boosting step is fixed or non-adaptive.

In their work, Xiong and Wang perform rank-1 based fixed-point analysis, then, guided by their analysis, they develop the first adaptive boosting (AB) algorithm, whose convergence is guaranteed. Preliminary results on the same image dataset show that AB uniformly outperforms existing denoising algorithms on every image and at each noise level, with more gains at higher noise levels.

Xiong, an IEEE Fellow, joined the department in 1999. His research focuses on information signal processing over networks. Other honors he has received include the TEES Fellow Award, the TEES Select Young Faculty Award, the Young Investigator Awards from the Office of Naval Research and the U.S. Army Research Office, the CAREER Award from the National Science Foundation, the 2006 IEEE Signal Processing Magazine best paper award, and top 10 percent paper awards at the 2011 and 2015 IEEE Multimedia Signal Processing Workshops.

He received his Ph.D. from the University of Illinois at Urbana-Champaign in 1996.

Wang received his bachelor’s degree from the Special Class of Gifted Young Department, University of Science and Technology of China, Hefei, China in 2007, and his master’s degree in computer engineering from Santa Clara University in 2009. He is a Ph.D. candidate in the department under the guidance of Xiong. His research interests include image/video denoising, computer vision and deep learning.

ICPR is an international forum for discussions on recent advances in the fields of pattern recognition, machine learning and computer vision, and on applications of these technologies in various fields.