# On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition

arXiv: https://arxiv.org/abs/2504.07598 · HTML: https://mlsanity.com/paper/2504.07598/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 30 of 40)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer](https://mlsanity.com/paper/2203.03466/) (2022)
- [Scaling Laws for Transfer](https://mlsanity.com/paper/2102.01293/) (2021)
- [A Constructive Prediction of the Generalization Error Across Scales](https://mlsanity.com/paper/1909.12673/) (2019)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Spreading vectors for similarity search](https://mlsanity.com/paper/1806.03198/) (2018)
- [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)
- [Broken Neural Scaling Laws](https://mlsanity.com/paper/2210.14891/) (2022)
- [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://mlsanity.com/paper/2305.13035/) (2023)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [Data Scaling Laws in NMT: The Effect of Noise and Architecture](https://mlsanity.com/paper/2202.01994/) (2022)
- [On Data Scaling in Masked Image Modeling](https://mlsanity.com/paper/2206.04664/) (2022)
- [On Learning Disentangled Representations for Gait Recognition](https://mlsanity.com/paper/1909.03051/) (2019)
- [SkeletonGait: Gait Recognition Using Skeleton Maps](https://mlsanity.com/paper/2311.13444/) (2023)
- [GPGait: Generalized Pose-based Gait Recognition](https://mlsanity.com/paper/2303.05234/) (2023)
- [Scaling Law for Recommendation Models: Towards General-purpose User Representations](https://mlsanity.com/paper/2111.11294/) (2021)

## Built on by (most cited first, 2 of 2)

- [MMGait: Towards Multi-Modal Gait Recognition](https://mlsanity.com/paper/2604.15979/) (2026)
- [MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts](https://mlsanity.com/paper/2510.04654/) (2025)

## Abstract (arXiv)

Gait recognition from video streams is a challenging problem in computer vision biometrics due to the subtle differences between gaits and numerous confounding factors. Recent advancements in self-supervised pretraining have led to the development of robust gait recognition models that are invariant to walking covariates. While neural scaling laws have transformed model development in other domains by linking performance to data, model size, and compute, their applicability to gait remains unexplored. In this work, we conduct the first empirical study scaling on skeleton-based self-supervised gait recognition to quantify the effect of data quantity, model size and compute on downstream gait recognition performance. We pretrain multiple variants of GaitPT - a transformer-based architecture - on a dataset of 2.7 million walking sequences collected in the wild. We evaluate zero-shot performance across four benchmark datasets to derive scaling laws for data, model size, and compute. Our findings demonstrate predictable power-law improvements in performance with increased scale and confirm that data and compute scaling significantly influence downstream accuracy. We further isolate architectural contributions by comparing GaitPT with GaitFormer under controlled compute budgets. These results provide practical insights into resource allocation and performance estimation for real-world gait recognition systems.