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

arXiv: https://arxiv.org/abs/2307.12917 · HTML: https://mlsanity.com/paper/2307.12917/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 99 references that are in the map.
- First posted on arXiv 24 Jul 2023.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [3D Human Pose Estimation = 2D Pose Estimation + Matching](https://mlsanity.com/paper/1612.06524/) (2016)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries](https://mlsanity.com/paper/2011.08435/) (2020)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [Towards Domain-Agnostic Contrastive Learning](https://mlsanity.com/paper/2011.04419/) (2020)
- [Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer](https://mlsanity.com/paper/2112.02466/) (2021)
- [Densely Semantically Aligned Person Re-Identification](https://mlsanity.com/paper/1812.08967/) (2018)
- [Unsupervised Tracklet Person Re-Identification](https://mlsanity.com/paper/1903.00535/) (2019)
- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)

## Built on by (most cited first, 9 of 9)

- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond](https://mlsanity.com/paper/2406.02978/) (2024)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [I2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation](https://mlsanity.com/paper/2310.15568/) (2023)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/2509.11526/) (2025)
- [A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects](https://mlsanity.com/paper/2401.15296/) (2024)
- [Find Them All: Unveiling MLLMs for Versatile Person Re-identification](https://mlsanity.com/paper/2508.06908/) (2025)
- [ICPR 2026 Competition on Privacy-Preserving Person Re-Identification from Top-View RGB-Depth Camera (TVRID)](https://mlsanity.com/paper/2605.04977/) (2026)
- [Privacy-Preserving Person Re-Identification from Temporal Sequences with Transformer and Hungarian Optimization](https://mlsanity.com/paper/2606.23230/) (2026)

## Abstract (arXiv)

With rapid advancements in depth sensors and deep learning, skeleton-based person re-identification (re-ID) models have recently achieved remarkable progress with many advantages. Most existing solutions learn single-level skeleton features from body joints with the assumption of equal skeleton importance, while they typically lack the ability to exploit more informative skeleton features from various levels such as limb level with more global body patterns. The label dependency of these methods also limits their flexibility in learning more general skeleton representations. This paper proposes a generic unsupervised Hierarchical skeleton Meta-Prototype Contrastive learning (Hi-MPC) approach with Hard Skeleton Mining (HSM) for person re-ID with unlabeled 3D skeletons. Firstly, we construct hierarchical representations of skeletons to model coarse-to-fine body and motion features from the levels of body joints, components, and limbs. Then a hierarchical meta-prototype contrastive learning model is proposed to cluster and contrast the most typical skeleton features ("prototypes") from different-level skeletons. By converting original prototypes into meta-prototypes with multiple homogeneous transformations, we induce the model to learn the inherent consistency of prototypes to capture more effective skeleton features for person re-ID. Furthermore, we devise a hard skeleton mining mechanism to adaptively infer the informative importance of each skeleton, so as to focus on harder skeletons to learn more discriminative skeleton representations. Extensive evaluations on five datasets demonstrate that our approach outperforms a wide variety of state-of-the-art skeleton-based methods. We further show the general applicability of our method to cross-view person re-ID and RGB-based scenarios with estimated skeletons.