Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification

06/06/2021
by   Haocong Rao, et al.
6

Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of body joints, while they rarely explore valuable relation information contained in body structure or motion. To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID. Specifically, considering that structurally-connected body components are highly correlated in a skeleton, we first propose a multi-head structural relation layer to learn different relations of neighbor body-component nodes in graphs, which helps aggregate key correlative features for effective node representations. Second, inspired by the fact that body-component collaboration in walking usually carries recognizable patterns, we propose a cross-level collaborative relation layer to infer collaboration between different level components, so as to capture more discriminative skeleton graph features. Finally, to enhance graph dynamics encoding, we propose a novel self-supervised sparse sequential prediction task for model pre-training, which facilitates encoding high-level graph semantics for person Re-ID. MG-SCR outperforms state-of-the-art skeleton-based methods, and it achieves superior performance to many multi-modal methods that utilize extra RGB or depth features. Our codes are available at https://github.com/Kali-Hac/MG-SCR.

READ FULL TEXT
research
07/05/2021

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

Person re-identification via 3D skeletons is an emerging topic with grea...
research
08/25/2022

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 emergi...
research
08/21/2020

Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification

Gait-based person re-identification (Re-ID) is valuable for safety-criti...
research
09/05/2020

A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification

Person re-identification (Re-ID) via gait features within 3D skeleton se...
research
07/24/2023

Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification

With rapid advancements in depth sensors and deep learning, skeleton-bas...
research
08/07/2022

Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour

Automated social behaviour analysis of mice has become an increasingly p...

Please sign up or login with your details

Forgot password? Click here to reset