# Multi-scale Context-aware Network with Transformer for Gait Recognition

arXiv: https://arxiv.org/abs/2204.03270 · HTML: https://mlsanity.com/paper/2204.03270/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 58 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Conditional Positional Encodings for Vision Transformers](https://mlsanity.com/paper/2102.10882/) (2021)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [SMART Frame Selection for Action Recognition](https://mlsanity.com/paper/2012.10671/) (2020)
- [Appearance-Preserving 3D Convolution for Video-based Person Re-identification](https://mlsanity.com/paper/2007.08434/) (2020)
- [You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization](https://mlsanity.com/paper/1911.06644/) (2019)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [On Learning Disentangled Representations for Gait Recognition](https://mlsanity.com/paper/1909.03051/) (2019)

## Built on by (most cited first, 6 of 6)

- [OpenGait: Revisiting Gait Recognition Toward Better Practicality](https://mlsanity.com/paper/2211.06597/) (2022)
- [LidarGait: Benchmarking 3D Gait Recognition with Point Clouds](https://mlsanity.com/paper/2211.10598/) (2022)
- [Spatial Transformer Network on Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.03873/) (2022)
- [A Brief Survey on Person Recognition at a Distance](https://mlsanity.com/paper/2212.08969/) (2022)
- [Towards Complete-View and High-Level Pose-based Gait Recognition](https://mlsanity.com/paper/2209.11577/) (2022)
- [Gait Recognition with Temporal Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2604.09990/) (2026)

## Abstract (arXiv)

Although gait recognition has drawn increasing research attention recently, since the silhouette differences are quite subtle in spatial domain, temporal feature representation is crucial for gait recognition. Inspired by the observation that humans can distinguish gaits of different subjects by adaptively focusing on clips of varying time scales, we propose a multi-scale context-aware network with transformer (MCAT) for gait recognition. MCAT generates temporal features across three scales, and adaptively aggregates them using contextual information from both local and global perspectives. Specifically, MCAT contains an adaptive temporal aggregation (ATA) module that performs local relation modeling followed by global relation modeling to fuse the multi-scale features. Besides, in order to remedy the spatial feature corruption resulting from temporal operations, MCAT incorporates a salient spatial feature learning (SSFL) module to select groups of discriminative spatial features. Extensive experiments conducted on three datasets demonstrate the state-of-the-art performance. Concretely, we achieve rank-1 accuracies of 98.7%, 96.2% and 88.7% under normal walking, bag-carrying and coat-wearing conditions on CASIA-B, 97.5% on OU-MVLP and 50.6% on GREW. The source code will be available at https://github.com/zhuduowang/MCAT.git.