G3D

2000년 도입 · 논문 2편에서 사용

G3D is a unified spatial-temporal graph convolutional operator that directly models cross-spacetime joint dependencies. It leverages dense cross-spacetime edges as skip connections for direct information propagation across the 3D spatial-temporal graph.

출처: Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition

소개 논문: Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition