SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification

Haocong Rao, Xiping Hu*, Jun Cheng, Bin Hu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

10 引用 (Scopus)

摘要

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.

源语言英语
主期刊名MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
出版商Association for Computing Machinery, Inc
1812-1820
页数9
ISBN(电子版)9781450386517
DOI
出版状态已出版 - 17 10月 2021
活动29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, 中国
期限: 20 10月 202124 10月 2021

出版系列

姓名MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

会议

会议29th ACM International Conference on Multimedia, MM 2021
国家/地区中国
Virtual, Online
时期20/10/2124/10/21

指纹

探究 'SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification' 的科研主题。它们共同构成独一无二的指纹。

引用此