Saliency Detection via Divergence Analysis: A Unified Perspective
- LecturerMr. Jia-Bin Huang (UIUC)
Host: Chu-song Chen - Time2012-05-29 (Tue.) 10:30 ~ 12:00
- LocationAuditorium 106 at new IIS Building
Abstract
We present a unified view that frames various bottom-up saliency detection algorithms. As these methods were proposed from intuition and principles inspired from psychophysical studies of human vision, the theoretical relations among them are unclear. In this talk, we propose such a bridge. The saliency is defined in terms of divergence between feature distributions estimated using samples from center and surround, respectively. We explicitly show that these seemly different algorithms are in fact closely related. We also discuss some commonly-used center-surround selection strategies. Comparative experiments on two publicly available datasets are presented to further provide insights on relative advantages of these algorithms.
BIO
Jia-Bin Huang received the B.S. degree from the Department of Electronics Engineerings, National Chiao-Tung University, Hsinchu in 2006. He is currently pursuing the Ph.D degree at the University of Illinois, Urbana-Champaign under the supervision of Prof. Narendra Ahuja. He works in the field of computer vision, signal and image processing, specializing particularly in visual recognition. Personal
page: https://netfiles.uiuc.edu/jbhuang1/www/