Aesthetics Analysis

My team first contributed to the research on computational aesthetics by studying what makes professional videos and accordingly developing a method to distinguish them from amateur ones. We are also working on subjective photo quality assessment that learns from photographers to rate photo quality. We have made some progress in this project and developed methods to detect rule of thirds and rule of simplicity from a photo.  
Visual Quality Assessment for Projected Content
Hoang Le, Carl Marshall, Thong Dong, Long Mai, and Feng Liu
CRV 2017. PDF
Composition-preserving Deep Photo Aesthetics Assessment
Long Mai, Hailin Jin and Feng Liu
IEEE CVPR 2016. PDF Website
What Makes a Professional Video? A Computational Aesthetics Approach
Yuzhen Niu and Feng Liu
IEEE Transactions on Circuits and Systems for Video Technology. Vol. 22, Issue 7, 2012: 1037 - 1049. PDF  
Aesthetics-based Stereoscopic Photo Cropping for Heterogeneous Displays
Yuzhen Niu, Feng Liu, Wu-chi Feng, and Hailin Jin.  
IEEE Transactions on Multimedia. Vol. 14, Issue 3, 2012: 783-796. PDF
Detecting Rule of Simplicity from Photos
Long Mai, Hoang Le, Yuzhen Niu, Yu-chi Lai, and Feng Liu
ACM Multimedia 2012, Nara, Japan, October 2012. (short paper) 
PDF Website
Rule of Thirds Detection from Photograph
Mai Long, Hoang Le, Yuzhen Niu, and Feng Liu
IEEE ISM 2011. PDF  Website