The Pose Knows: Video Forecasting by Generating Pose Futures on ShortScience.org

arxiv.org
scholar.google.com

The Pose Knows: Video Forecasting by Generating Pose Futures
Walker, Jacob and Marino, Kenneth and Gupta, Abhinav and Hebert, Martial
arXiv e-Print archive - 2017 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Kirill Pevzner 7 years ago

Problem
---------
Video prediction with human objects


Contribution
--------------
Instead of the common approach of predicting directly in pixel-space, use explicit knowledge of human motion space to predict the future of the video.

Approach
--------------
1. VAE to model the possible future movements of humans in the pose space
2. Conditional GAN - use pose information for to predict video in pixel space.



https://image.ibb.co/b1omVF/The_pose_knows.png

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private