Person re-identification via 3D skeletons is an emerging topic with great potential in security-critical applications. Existing methods typically learn body and motion features from the body-joint trajectory, whereas they lack a systematic way to model body structure and underlying relations of body components beyond the scale of body joints. In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID. Specifically, we first devise multi-scale skeleton graphs with coarse-to-fine human body partitions, which enables us to model body structure and skeleton dynamics at multiple levels. Second, to mine inherent correlations between body components in skeletal motion, we propose a multi-scale graph relation network to learn structural relations between adjacent body-component nodes and collaborative relations among nodes of different scales, so as to capture more discriminative skeleton graph features. Last, we propose a novel multi-scale skeleton reconstruction mechanism to enable our framework to encode skeleton dynamics and high-level semantics from unlabeled skeleton graphs, which encourages learning a discriminative skeleton representation for person Re-ID. Extensive experiments show that SM-SGE outperforms most state-of-the-art skeleton-based methods. We further demonstrate its effectiveness on 3D skeleton data estimated from large-scale RGB videos. Our codes are open at https://github.com/Kali-Hac/SM-SGE.
翻译:通过 3D 骨架重新确定人的身份是一个新兴主题,具有巨大的安全关键应用潜力。 现有方法通常从身体- 联合轨迹中学习身体和运动特征, 而它们缺乏一个系统的方法来模拟身体结构, 以及超越身体联合规模的人体组成部分的内在关系。 在本文中,我们首次提出一个自我监督的多级 Skeleton 图形编码框架( SM-SGE), 全面模拟人体身体、 组成部分关系和骨架动态, 从各种规模的未贴标签的骨架图中全面模拟人体、 组成部分关系和骨架动态, 以学习个人重新识别的有效骨架特征。 具体地说, 我们首先设计一个具有全方位至全方位的骨架骨架结构图, 使我们的骨架结构结构结构结构结构结构结构得以建模结构结构结构结构结构结构结构, 并且用高层次的骨架- 智能SD 来显示我们骨架- 的骨架- 数据- 数据库- 数据库- 数据库- 数据库- 展示一个高层次的骨架- 数据- 基础- 模型- 模型- 模型- 模型- 演示- 演示- 展示- 展示- 演示- 演示- 模型- 模型- 展示- 模型- 模型- 学习- 模型- 模型- 模型- 模型- 模型- 模型- 模型- 模型- 展示- 模型- 模型- 模型- 模型- 模型- 模型- 模型- 模型- 展示- 模型- 模型- 模型- 智能- 智能- 智能- 智能- 学习- 模型- 智能- 智能- 模型- 模型- 学习- 学习- 智能- 智能- 智能- 校对- 智能- 3- 校对- 智能- 校对- 校对- 校对- 性- 校对- 智能- 智能- 校程- 性- 性- 性- 校程- 校程- 3- 校程- 校程- 校程- 校程- 校程- 校程- 校程- 校程- 校程- 校程- 校