mlsanityData to 14 Oct 2026

Skeleton Prototype Contrastive Learning with Multi-Level Graph Relation Modeling for Unsupervised Person Re-Identification

arXiv 2208.11814 ↗First posted 25 Aug 2022cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Person re-identification (re-ID) via 3D skeletons is an important emerging topic with many merits. Existing solutions rarely explore valuable body-component relations in skeletal structure or motion, and they typically lack the ability to learn general representations with unlabeled skeleton data for person re-ID. This paper proposes a generic unsupervised Skeleton Prototype Contrastive learning paradigm with Multi-level Graph Relation learning (SPC-MGR) to learn effective representations from unlabeled skeletons to perform person re-ID. Specifically, we first construct unified multi-level skeleton graphs to fully model body structure within skeletons. Then we propose a multi-head structural relation layer to comprehensively capture relations of physically-connected body-component nodes in graphs. A full-level collaborative relation layer is exploited to infer collaboration between motion-related body parts at various levels, so as to capture rich body features and recognizable walking patterns. Lastly, we propose a skeleton prototype contrastive learning scheme that clusters feature-correlative instances of unlabeled graph representations and contrasts their inherent similarity with representative skeleton features ("skeleton prototypes") to learn discriminative skeleton representations for person re-ID. Empirical evaluations show that SPC-MGR significantly outperforms several state-of-the-art skeleton-based methods, and it also achieves highly competitive person re-ID performance for more general scenarios.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 60 references that are in the map. First posted on arXiv 25 Aug 2022.

Builds on

29 of 60 references.

References · 29

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Graph Attention Networkscited by 8,923
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  7. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  8. 2019Contrastive Multiview Codingcited by 1,301
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  10. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  11. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  12. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
17 more
  1. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  2. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  3. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 232
  4. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  5. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  6. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  7. 2018Densely Semantically Aligned Person Re-Identificationcited by 58
  8. 2019Unsupervised Tracklet Person Re-Identificationcited by 55
  9. 2017Person Re-Identification by Camera Correlation Aware Feature Augmentationcited by 35
  10. 2016Space-Time Representation of People Based on 3D Skeletal Data: A Reviewcited by 24
  11. 2019Unsupervised Person Re-identification by Deep Asymmetric Metric Embeddingcited by 22
  12. 2014Person Re-identification by Saliency Learningcited by 20
  13. 2020A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identificationcited by 20
  14. 2016Person Re-Identification by Discriminative Selection in Video Rankingcited by 16
  15. 2020Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identificationcited by 12
  16. 2021SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identificationcited by 8
  17. 2021Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identificationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identificationcited by 14
  2. 2023Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identificationcited by 9