# A Multi-Stage Adaptive Feature Fusion Neural Network for Multimodal Gait Recognition

arXiv: https://arxiv.org/abs/2312.14410 · HTML: https://mlsanity.com/paper/2312.14410/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [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)
- [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)
- [Gait Recognition via Disentangled Representation Learning](https://mlsanity.com/paper/1904.04925/) (2019)
- [Multimodal feature fusion for CNN-based gait recognition: an empirical comparison](https://mlsanity.com/paper/1806.07753/) (2018)
- [Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition](https://mlsanity.com/paper/2002.09674/) (2020)

## Built on by (most cited first, 12 of 12)

- [BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models](https://mlsanity.com/paper/2505.18132/) (2025)
- [OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality](https://mlsanity.com/paper/2405.09138/) (2024)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Exploring More from Multiple Gait Modalities for Human Identification](https://mlsanity.com/paper/2412.11495/) (2024)
- [DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition](https://mlsanity.com/paper/2503.18830/) (2025)
- [The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models](https://mlsanity.com/paper/2402.08320/) (2024)
- [Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classification](https://mlsanity.com/paper/2508.03277/) (2025)
- [SpheriGait: Enriching Spatial Representation via Spherical Projection for LiDAR-based Gait Recognition](https://mlsanity.com/paper/2409.11869/) (2024)
- [CVVNet: A Cross-Vertical-View Network for Gait Recognition](https://mlsanity.com/paper/2505.01837/) (2025)
- [Text-guided Feature Disentanglement for Cross-modal Gait Recognition](https://mlsanity.com/paper/2605.30784/) (2026)
- [HorGait: A Hybrid Model for Accurate Gait Recognition in LiDAR Point Cloud Planar Projections](https://mlsanity.com/paper/2410.08454/) (2024)
- [Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary Information](https://mlsanity.com/paper/2507.05544/) (2025)

## Abstract (arXiv)

Gait recognition is a biometric technology that has received extensive attention. Most existing gait recognition algorithms are unimodal, and a few multimodal gait recognition algorithms perform multimodal fusion only once. None of these algorithms may fully exploit the complementary advantages of the multiple modalities. In this paper, by considering the temporal and spatial characteristics of gait data, we propose a multi-stage feature fusion strategy (MSFFS), which performs multimodal fusions at different stages in the feature extraction process. Also, we propose an adaptive feature fusion module (AFFM) that considers the semantic association between silhouettes and skeletons. The fusion process fuses different silhouette areas with their more related skeleton joints. Since visual appearance changes and time passage co-occur in a gait period, we propose a multiscale spatial-temporal feature extractor (MSSTFE) to learn the spatial-temporal linkage features thoroughly. Specifically, MSSTFE extracts and aggregates spatial-temporal linkages information at different spatial scales. Combining the strategy and modules mentioned above, we propose a multi-stage adaptive feature fusion (MSAFF) neural network, which shows state-of-the-art performance in many experiments on three datasets. Besides, MSAFF is equipped with feature dimensional pooling (FD Pooling), which can significantly reduce the dimension of the gait representations without hindering the accuracy. https://github.com/ShinanZou/MSAFF