# The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models

arXiv: https://arxiv.org/abs/2402.08320 · HTML: https://mlsanity.com/paper/2402.08320/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition](https://mlsanity.com/paper/2101.11228/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [A Survey on Instance Segmentation: State of the art](https://mlsanity.com/paper/2007.00047/) (2020)
- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [Towards a Deeper Understanding of Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.07855/) (2022)
- [Deep Gait Recognition: A Survey](https://mlsanity.com/paper/2102.09546/) (2021)
- [On Learning Disentangled Representations for Gait Recognition](https://mlsanity.com/paper/1909.03051/) (2019)
- [GPGait: Generalized Pose-based Gait Recognition](https://mlsanity.com/paper/2303.05234/) (2023)
- [COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification](https://mlsanity.com/paper/2005.07862/) (2020)
- [Spatial Transformer Network on Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.03873/) (2022)
- [GaitGL: Learning Discriminative Global-Local Feature Representations for Gait Recognition](https://mlsanity.com/paper/2208.01380/) (2022)
- [JointsGait:A model-based Gait Recognition Method based on Gait Graph Convolutional Networks and Joints Relationship Pyramid Mapping](https://mlsanity.com/paper/2005.08625/) (2020)
- [A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition](https://mlsanity.com/paper/2312.14410/) (2023)
- [GaitPT: Skeletons Are All You Need For Gait Recognition](https://mlsanity.com/paper/2308.10623/) (2023)
- [PsyMo: A Dataset for Estimating Self-Reported Psychological Traits from Gait](https://mlsanity.com/paper/2308.10631/) (2023)
- [Recognizing People by Body Shape Using Deep Networks of Images and Words](https://mlsanity.com/paper/2305.19160/) (2023)
- [GaitFormer: Learning Gait Representations with Noisy Multi-Task Learning](https://mlsanity.com/paper/2310.19418/) (2023)
- [Whole-body Detection, Recognition and Identification at Altitude and Range](https://mlsanity.com/paper/2311.05725/) (2023)

## Built on by (most cited first, 3 of 3)

- [Aligning Actions and Walking to LLM-Generated Textual Descriptions](https://mlsanity.com/paper/2404.12192/) (2024)
- [On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition](https://mlsanity.com/paper/2504.07598/) (2025)
- [Gait Recognition from Highly Compressed Videos](https://mlsanity.com/paper/2404.12183/) (2024)

## Abstract (arXiv)

Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, in particular skeleton-based gait recognition, relies primarily on motion patterns, revealing a significant role of the implicit anthropometric information encoded in the walking sequence. We show through a comparative analysis that removing height information leads to notable performance degradation across three models and two benchmarks (CASIA-B and GREW). Furthermore, we propose a spatial transformer model processing individual poses, disregarding any temporal information, which achieves unreasonably good accuracy, emphasizing the bias towards appearance information and indicating spurious correlations in existing benchmarks. These findings underscore the need for a nuanced understanding of the interplay between motion and appearance in vision-based gait recognition, prompting a reevaluation of the methodological assumptions in this field. Our experiments indicate that "in-the-wild" datasets are less prone to spurious correlations, prompting the need for more diverse and large scale datasets for advancing the field.