Skeleton Prototype Contrastive Learning with Multi-level Graph Relation Modeling for Unsupervised Person Re-Identification

Person re-identification (re-ID) via 3D skeletons is an important emerging topic with many merits. Existing solutions rarely explore valuable body-component relations in skeletal structure or motion, and they typically lack the ability to learn general representations with unlabeled skeleton data for person re-ID. This paper proposes a genericunsupervisedSkeleton Prototype Contrastive learning paradigm with Multi-level Graph Relation learning (SPC-MGR) to learn effective representations fromunlabeledskeletons to perform person re-ID. Specifically, we first constructunified multi-level skeleton graphsto fully model body structure within skeletons. Then we propose amulti-head structural relation layerto comprehensively capture relations of physically-connected body-component nodes in graphs. Afull-level collaborative relation layeris exploited to infer collaboration between motion-related body parts at various levels, so as to capture rich body features and recognizable walking patterns. Lastly, we propose askeleton prototype contrastive learning schemethat clusters feature-correlative instances of unlabeled graph representations and contrasts their inherent similarity with representative skeleton features (“skeleton prototypes”) to learn discriminative skeleton representations for person re-ID. Empirical evaluations show that SPC-MGR significantly outperforms several state-of-the-art skeleton-based methods under different scenarios.