PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition. (arXiv:2208.05775v1 [cs.CV])

Pose-based action recognition is predominantly tackled by approaches which
treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree
are processed as a whole. However, such approaches ignore the fact that action
categories are often characterized by localized action dynamics involving only
small subsets of part joint groups involving hands (e.g. `Thumbs up') or legs
(e.g. `Kicking'). Although part-grouping based approaches exist, each part
group is not considered within the global pose frame, causing such methods …

arxiv cv part