TY - GEN
T1 - SM-SGE
T2 - 29th ACM International Conference on Multimedia, MM 2021
AU - Rao, Haocong
AU - Hu, Xiping
AU - Cheng, Jun
AU - Hu, Bin
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/10/17
Y1 - 2021/10/17
N2 - 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.
AB - 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.
KW - multi-scale skeleton graph encoding
KW - self-supervised representation learning
KW - skeleton-based person re-identification
UR - http://www.scopus.com/inward/record.url?scp=85119381442&partnerID=8YFLogxK
U2 - 10.1145/3474085.3475330
DO - 10.1145/3474085.3475330
M3 - Conference contribution
AN - SCOPUS:85119381442
T3 - MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
SP - 1812
EP - 1820
BT - MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
PB - Association for Computing Machinery, Inc
Y2 - 20 October 2021 through 24 October 2021
ER -