Why Can’t I Dance in a Mall?
          Learning to Mitigate Scene Bias
            in Action Recognition

    Jinwoo Choi      Chen Gao       Joseph C. E. Messou     Jia-Bin Huang
   Virginia Tech     Virginia Tech       Virginia Tech       Virginia Tech
  jinchoi@vt.edu     chengao@vt.edu      mejc2014@vt.edu      jbhuang@vt.edu


Figure 1: Quiz time! Can you guess what action the (blocked) person is doing in the four videos?
Even though we cannot see a human actor, we can easily predict the ac ...