Center for Research in Comptuer Vision
Center for Research in Comptuer Vision


2nd Place Award for NHK Where is beauty? Grand Challenge

Towards a Comprehensive Computational Model for Aesthetic Assessment of Videos by Subhabrata Bhattacharya, Behnaz Nojavanasghari, Tao Chen, Dong Liu, Shih-Fu Chang, and, Mubarak Shah, received the 2nd place award for the NHK Where is beauty? Grand Challenge at the ACM Multimedia 2013 conference that was held in Barcelona, Spain in November 2013.

Participants were provided with approximately 1,000 clips of raw broadcast video footage, containing various categories such as creatures, landscape, and CGI. These video clips lasted about 1 minute. Participants had to evaluate the beautifulness of these videos automatically, and rank them in terms of beauty.

The proposed method was evaluated on the basis of its originality and accuracy. Participants were expected to consider a diverse range of beauty, not only the balance of color, but also composition, motion, audio, and other brand new features. The reliability and the diversity of the extracted beauty was scored by using manually annotated data.