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

arXiv: https://arxiv.org/abs/2009.03671 · HTML: https://mlsanity.com/paper/2009.03671/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2020.

## Built on by (most cited first, 20 of 20)

- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Deep Gait Recognition: A Survey](https://mlsanity.com/paper/2102.09546/) (2021)
- [More than Encoder: Introducing Transformer Decoder to Upsample](https://mlsanity.com/paper/2106.10637/) (2021)
- [Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark](https://mlsanity.com/paper/2206.13964/) (2022)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification](https://mlsanity.com/paper/2303.06819/) (2023)
- [RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction](https://mlsanity.com/paper/2210.09309/) (2022)
- [Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2307.12917/) (2023)
- [SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification](https://mlsanity.com/paper/2107.01903/) (2021)
- [Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch](https://mlsanity.com/paper/2308.11874/) (2023)
- [Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification](https://mlsanity.com/paper/2106.03069/) (2021)
- [SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2204.09826/) (2022)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification](https://mlsanity.com/paper/2405.17790/) (2024)
- [Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning](https://mlsanity.com/paper/2504.14847/) (2025)
- [Skeleton Prototype Contrastive Learning with Multi-Level Graph Relation Modeling for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2208.11814/) (2022)
- [Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer](https://mlsanity.com/paper/2208.01161/) (2022)
- [Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification](https://mlsanity.com/paper/2412.09044/) (2024)
- [A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects](https://mlsanity.com/paper/2401.15296/) (2024)
- [Affinity Contrastive Learning for Skeleton-based Human Activity Understanding](https://mlsanity.com/paper/2601.16694/) (2026)

## Abstract (arXiv)

Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supervised gait representation learning. This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID. Specifically, we first create self-supervision by learning to reconstruct unlabeled skeleton sequences reversely, which involves richer high-level semantics to obtain better gait representations. Other pretext tasks are also explored to further improve self-supervised learning. Second, inspired by the fact that motion's continuity endows adjacent skeletons in one skeleton sequence and temporally consecutive skeleton sequences with higher correlations (referred as locality in 3D skeleton data), we propose a locality-aware attention mechanism and a locality-aware contrastive learning scheme, which aim to preserve locality-awareness on intra-sequence level and inter-sequence level respectively during self-supervised learning. Last, with context vectors learned by our locality-aware attention mechanism and contrastive learning scheme, a novel feature named Constrastive Attention-based Gait Encodings (CAGEs) is designed to represent gait effectively. Empirical evaluations show that our approach significantly outperforms skeleton-based counterparts by 15-40% Rank-1 accuracy, and it even achieves superior performance to numerous multi-modal methods with extra RGB or depth information. Our codes are available at https://github.com/Kali-Hac/Locality-Awareness-SGE.