Visual Rhythm Prediction with Feature-Aligning Network
MVA, 2019.
EI
Abstract:
In this paper, we propose a data-driven visual rhythm prediction method, which overcomes the previous worksu0027 deficiency that predictions are made primarily by human-crafted hard rules. In our approach, we first extract features including original frames and their residuals, optical flow, scene change, and body pose. These visual featu...More
Code:
Data:
Tags
Comments