ECE PhD student wins WACV Best Algorithms Paper Award
Zhihao Duan, a graduate student in the Purdue University Elmore Family School of Electrical and Computer engineering won the Best Algorithms Paper Award at the Winter Conference on Applications of Computer Vision (WACV) 2023. The paper is titled “Lossy Image Compression with Quantized Hierarchical VAEs,” which proposed a novel method for lossy image compression using machine learning techniques. The method not only achieves better compression efficiency than previous methods but also draws a deeper connection between data compression and generative models in machine learning.
WACV is a premier international computer vision conference. This year, the conference received 1,577 valid submissions, out of which 1,265 were submitted to the Algorithms Track. The Best Algorithms Paper Award is awarded to the single best paper in the Algorithm Track. Last month, Zhihao’s other paper was also among the five best paper finalists at the Picture Coding Symposium (PCS) 2022, one of the most prestigious video coding focused international conferences.
Zhihao received B.E. in Electrical Engineering from Shanghai Jiao Tong University, China in 2018, and M.S. in Electrical and Computer Engineering from Boston University, USA in 2020. He is currently pursuing his Ph.D. at Purdue University under the direction of Fengqing Maggie Zhu, Associate Professor of Electrical and Computer Engineering. Zhihao’s research focuses on the intersection of image compression, computer vision, and machine learning.