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
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

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...
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...
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...
04/29/2021

Learning Multi-Attention Context Graph for Group-Based Re-Identification

Learning to re-identify or retrieve a group of people across non-overlap...
06/16/2021

Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight

This paper addresses unsupervised person re-identification (Re-ID) using...
11/14/2020

Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition

In this paper, we focus on unsupervised representation learning for skel...
02/02/2021

Graph Classification Based on Skeleton and Component Features

Most existing popular methods for learning graph embedding only consider...

Code Repositories

MG-SCR

[IJCAI 2021] Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.