RGB-based and skeleton-based pipelines for estimating the LMA elements
(A) The RGB-based pipeline extracts frames from the input clip, crops the target human, and feeds the resultant frames into a neural network.
(B) The Skeleton-based pipeline leverages the 2D/3D human pose extracted from the frames as the input for a neural network.
This figure incorporates frames from the film “Wagner” (1983, directed by Tony Palmer).