Deformable Locality-Coordination Graph Motifs for 3D Skeleton Based Person Re-Identification

Existing 3D skeleton based person re-identification (re-ID) approaches typically model skeletons as graphs to capture body relations and motion. However, they often rely on fixed joint’s connections such as adjacency for relation modeling, while lacking a flexible and specific focus on key body joints or parts of different levels to capture various local relations (“locality”) and limb relations (“coordination”). In this letter, we propose Deformable Locality-Coordination graph Motifs (DL-CM) that can guide the body relation learning to particularly capture multi-order locality and coordination of key gait-specific body parts to enhance person re-ID performance. Specifically, we first devise Deformable Locality Motifs (DLM), which are applicable to deformed skeleton graphs at different levels, to simultaneously focus on different-order neighbors’ relations for body structure and pattern learning. Then, we propose Deformable Coordination Motifs (DCM) to concurrently capture local and global coordination of different-level limbs in deformed graphs, so as to facilitate learning discriminative gait patterns for person re-ID. Extensive experiments on four public benchmarks demonstrate the effectiveness of DL-CM on state-of-the-art models and different-level graph representations to improve person re-ID performance.