# GaitFormer: Revisiting Intrinsic Periodicity for Gait Recognition

arXiv: https://arxiv.org/abs/2307.13259 · HTML: https://mlsanity.com/paper/2307.13259/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 25 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Conditional Positional Encodings for Vision Transformers](https://mlsanity.com/paper/2102.10882/) (2021)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition](https://mlsanity.com/paper/1811.06186/) (2018)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [OpenGait: Revisiting Gait Recognition Toward Better Practicality](https://mlsanity.com/paper/2211.06597/) (2022)
- [Deep Gait Recognition: A Survey](https://mlsanity.com/paper/2102.09546/) (2021)
- [GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality](https://mlsanity.com/paper/2203.03972/) (2022)
- [A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges](https://mlsanity.com/paper/2206.13732/) (2022)
- [MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition](https://mlsanity.com/paper/2306.03445/) (2023)
- [Gait Recognition with Mask-based Regularization](https://mlsanity.com/paper/2203.04038/) (2022)
- [Skeleton-based Gait Index Estimation with LSTMs](https://mlsanity.com/paper/1908.07416/) (2019)

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

- [QAGait: Revisit Gait Recognition from a Quality Perspective](https://mlsanity.com/paper/2401.13531/) (2024)
- [Free Lunch for Gait Recognition: A Novel Relation Descriptor](https://mlsanity.com/paper/2308.11487/) (2023)

## Abstract (arXiv)

Gait recognition aims to distinguish different walking patterns by analyzing video-level human silhouettes, rather than relying on appearance information. Previous research on gait recognition has primarily focused on extracting local or global spatial-temporal representations, while overlooking the intrinsic periodic features of gait sequences, which, when fully utilized, can significantly enhance performance. In this work, we propose a plug-and-play strategy, called Temporal Periodic Alignment (TPA), which leverages the periodic nature and fine-grained temporal dependencies of gait patterns. The TPA strategy comprises two key components. The first component is Adaptive Fourier-transform Position Encoding (AFPE), which adaptively converts features and discrete-time signals into embeddings that are sensitive to periodic walking patterns. The second component is the Temporal Aggregation Module (TAM), which separates embeddings into trend and seasonal components, and extracts meaningful temporal correlations to identify primary components, while filtering out random noise. We present a simple and effective baseline method for gait recognition, based on the TPA strategy. Extensive experiments conducted on three popular public datasets (CASIA-B, OU-MVLP, and GREW) demonstrate that our proposed method achieves state-of-the-art performance on multiple benchmark tests.