# Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification

arXiv: https://arxiv.org/abs/2412.09044 · HTML: https://mlsanity.com/paper/2412.09044/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 64 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [3D Human Pose Estimation = 2D Pose Estimation + Matching](https://mlsanity.com/paper/1612.06524/) (2016)
- [Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction](https://mlsanity.com/paper/1910.02212/) (2019)
- [You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos](https://mlsanity.com/paper/2303.07863/) (2023)
- [Space-Time Representation of People Based on 3D Skeletal Data: A Review](https://mlsanity.com/paper/1601.01006/) (2016)
- [A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification](https://mlsanity.com/paper/2009.03671/) (2020)
- [Robust Depth-based Person Re-identification](https://mlsanity.com/paper/1703.09474/) (2017)
- [Person Re-Identification by Discriminative Selection in Video Ranking](https://mlsanity.com/paper/1601.06260/) (2016)
- [Learnable Bernoulli Dropout for Bayesian Deep Learning](https://mlsanity.com/paper/2002.05155/) (2020)
- [Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification](https://mlsanity.com/paper/2008.09435/) (2020)
- [Motif-based Convolutional Neural Network on Graphs](https://mlsanity.com/paper/1711.05697/) (2017)
- [A Survey of Artificial Intelligence in Gait-Based Neurodegenerative Disease Diagnosis](https://mlsanity.com/paper/2405.13082/) (2024)

## Built on by (most cited first, 1 of 1)

- [Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders](https://mlsanity.com/paper/2504.09530/) (2025)

## Abstract (arXiv)

Person re-identification (re-ID) via 3D skeleton data is a challenging task with significant value in many scenarios. Existing skeleton-based methods typically assume virtual motion relations between all joints, and adopt average joint or sequence representations for learning. However, they rarely explore key body structure and motion such as gait to focus on more important body joints or limbs, while lacking the ability to fully mine valuable spatial-temporal sub-patterns of skeletons to enhance model learning. This paper presents a generic Motif guided graph transformer with Combinatorial skeleton prototype learning (MoCos) that exploits structure-specific and gait-related body relations as well as combinatorial features of skeleton graphs to learn effective skeleton representations for person re-ID. In particular, motivated by the locality within joints' structure and the body-component collaboration in gait, we first propose the motif guided graph transformer (MGT) that incorporates hierarchical structural motifs and gait collaborative motifs, which simultaneously focuses on multi-order local joint correlations and key cooperative body parts to enhance skeleton relation learning. Then, we devise the combinatorial skeleton prototype learning (CSP) that leverages random spatial-temporal combinations of joint nodes and skeleton graphs to generate diverse sub-skeleton and sub-tracklet representations, which are contrasted with the most representative features (prototypes) of each identity to learn class-related semantics and discriminative skeleton representations. Extensive experiments validate the superior performance of MoCos over existing state-of-the-art models. We further show its generality under RGB-estimated skeletons, different graph modeling, and unsupervised scenarios.