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 generic unsupervised Skeleton Prototype Contrastive learning paradigm with Multi-level Graph Relation learning (SPC-MGR) to learn effective representations from unlabeled skeletons to perform person re-ID. Specifically, we first construct unified multi-level skeleton graphs to fully model body structure within skeletons. Then we propose a multi-head structural relation layer to comprehensively capture relations of physically-connected body-component nodes in graphs. A full-level collaborative relation layer is 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 a skeleton prototype contrastive learning scheme that 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, and it also achieves highly competitive person re-ID performance for more general scenarios.
翻译:通过 3D 骨骼重新定位( re-ID) 是一个重要的新兴主题,有许多优点。 现有的解决方案很少探索骨骼结构或运动中有价值的身体构成关系,它们通常缺乏学习无标签的骨骼数据为人再识别的能力。 本文提出一个通用的、不受监督的Skeleton 原型对比学习模式,与多层次图表关系学习( SPC- MGR) 一起学习从未贴标签的骨骼中有效表达来进行人再识别。 具体地说, 我们首先建立统一的多层次骨骼图, 以完全的骨骼结构结构结构结构结构为模型中全面捕捉与身体相连的人体构成节点之间的关系。 一个完整的协作关系层被用来推断不同层次的运动相关身体部分之间的协作, 以便捕捉到丰富的身体特征和可识别的行走模式。 最后, 我们提出一个骨架原型的典型对比学习模式, 将未贴标签的图形表达的特征实例与骨骼结构结构结构结构结构对比, 将其与具有代表性的骨架结构特征对比( “ eleast-stimal” ex- ex ex ex eximprestial ex impeal impeal impeal ex dal researal researal deal deal deal ex ex exal exings) (“s) ex exal ex exalutututututututus ex ex ex ex expututus expal exal exal exal impeutututusal exal exal imational exputusal expal exs” expeuts) ( “ “ “ “ “ “ “ “ “ “ ” peral peral peral peral peral ” per per peral peral peral peral peral peral peral peral impeuts” peuts” perpal peral ” ” perpal perpal impeuts” exal exal perfal ” ” impeal exal exal peral