mlsanityData to 14 Oct 2026

GaitPT: Skeletons Are All You Need For Gait Recognition

arXiv 2308.10623 ↗First posted 21 Aug 2023cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting method for automatic person identification at a distance. In this work, we propose a novel gait recognition architecture called Gait Pyramid Transformer (GaitPT) that leverages pose estimation skeletons to capture unique walking patterns, without relying on appearance information. GaitPT adopts a hierarchical transformer architecture that effectively extracts both spatial and temporal features of movement in an anatomically consistent manner, guided by the structure of the human skeleton. Our results show that GaitPT achieves state-of-the-art performance compared to other skeleton-based gait recognition works, in both controlled and in-the-wild scenarios. GaitPT obtains 82.6% average accuracy on CASIA-B, surpassing other works by a margin of 6%. Moreover, it obtains 52.16% Rank-1 accuracy on GREW, outperforming both skeleton-based and appearance-based approaches.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 64 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

37 of 64 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2017Mask R-CNNcited by 7,277
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  9. 2020Supervised Contrastive Learningcited by 2,829
  10. 2018YOLOv3: An Incremental Improvementcited by 2,659
  11. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
25 more
  1. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  2. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  4. 2021Going deeper with Image Transformerscited by 764
  5. 2015Cyclical Learning Rates for Training Neural Networkscited by 629
  6. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  7. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  8. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  9. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  10. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  11. 2018GaitSet: Regarding Gait as a Set for Cross-View Gait Recognitioncited by 138
  12. 2021GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognitioncited by 115
  13. 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 114
  14. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  15. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 77
  16. 2018Horizontal Pyramid Matching for Person Re-identificationcited by 70
  17. 2022Towards a Deeper Understanding of Skeleton-based Gait Recognitioncited by 56
  18. 2021Deep Gait Recognition: A Surveycited by 54
  19. 2022GaitGL: Learning Discriminative Global-Local Feature Representations for Gait Recognitioncited by 26
  20. 2020JointsGait:A model-based Gait Recognition Method based on Gait Graph Convolutional Networks and Joints Relationship Pyramid Mappingcited by 22
  21. 2018Face Recognition in Low Quality Images: A Surveycited by 18
  22. 2021WildGait: Learning Gait Representations from Raw Surveillance Streamscited by 9
  23. 2022RealGait: Gait Recognition for Person Re-Identificationcited by 9
  24. 2021From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patternscited by 6
  25. 2019FingerNet: Pushing The Limits of Fingerprint Recognition Using Convolutional Neural Networkcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 4; 2026: 2.

11 papers.

  1. 2024OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicalitycited by 15
  2. 2024The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Modelscited by 3
  3. 2024Aligning Actions and Walking to LLM-Generated Textual Descriptionscited by 3
  4. 2025On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognitioncited by 2
  5. 2025Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognitioncited by 2
  6. 2026Decoding Children's Gait Behaviorcited by 1
  7. 2023Learning to Simplify Spatial-Temporal Graphs in Gait Analysiscited by 0
  8. 2024Gait Recognition from Highly Compressed Videoscited by 0
  9. 2025Database-Agnostic Gait Enrollment using SetTransformerscited by 0
  10. 2025MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Expertscited by 0
  11. 2026Sketch It Out: Exploring Label-Free Structural Cues for Multimodal Gait Recognitioncited by 0