Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements 事件

Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements arXiv:2604.28173v2 Announce Type: replace Abstract: Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overa