Human pose forecasting is the task of detecting and predicting future human poses.
( Image credit: EgoPose )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.
SOTA for Human Pose Forecasting on Human3.6M
We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos.
The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
#4 best model for Skeleton Based Action Recognition on CAD-120