# GaitGCI: Generative Counterfactual Intervention for Gait Recognition

arXiv: https://arxiv.org/abs/2306.03428 · HTML: https://mlsanity.com/paper/2306.03428/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 79 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 37)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition](https://mlsanity.com/paper/1811.06186/) (2018)
- [Pixel-Adaptive Convolutional Neural Networks](https://mlsanity.com/paper/1904.05373/) (2019)
- [ABD-Net: Attentive but Diverse Person Re-Identification](https://mlsanity.com/paper/1908.01114/) (2019)
- [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)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning](https://mlsanity.com/paper/1811.02307/) (2018)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality](https://mlsanity.com/paper/2203.03972/) (2022)
- [Dynamic Region-Aware Convolution](https://mlsanity.com/paper/2003.12243/) (2020)
- [On Learning Disentangled Representations for Gait Recognition](https://mlsanity.com/paper/1909.03051/) (2019)
- [Revisiting Dynamic Convolution via Matrix Decomposition](https://mlsanity.com/paper/2103.08756/) (2021)

## Built on by (most cited first, 30 of 31)

- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [QAGait: Revisit Gait Recognition from a Quality Perspective](https://mlsanity.com/paper/2401.13531/) (2024)
- [OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality](https://mlsanity.com/paper/2405.09138/) (2024)
- [Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition](https://mlsanity.com/paper/2407.12519/) (2024)
- [Open-Set Biometrics: Beyond Good Closed-Set Models](https://mlsanity.com/paper/2407.16133/) (2024)
- [It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment](https://mlsanity.com/paper/2411.10742/) (2024)
- [HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID](https://mlsanity.com/paper/2508.05038/) (2025)
- [Free Lunch for Gait Recognition: A Novel Relation Descriptor](https://mlsanity.com/paper/2308.11487/) (2023)
- [HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations](https://mlsanity.com/paper/2401.00271/) (2023)
- [Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room](https://mlsanity.com/paper/2503.13028/) (2025)
- [GaitSnippet: Gait Recognition Beyond Unordered Sets and Ordered Sequences](https://mlsanity.com/paper/2508.07782/) (2025)
- [HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition](https://mlsanity.com/paper/2311.11210/) (2023)
- [CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition](https://mlsanity.com/paper/2407.03632/) (2024)
- [CarGait: Cross-Attention based Re-ranking for Gait recognition](https://mlsanity.com/paper/2503.03501/) (2025)
- [TrackletGait: A Robust Framework for Gait Recognition in the Wild](https://mlsanity.com/paper/2508.02143/) (2025)
- [Silhouette-based Gait Foundation Model](https://mlsanity.com/paper/2512.00691/) (2025)
- [EventGait: Towards Robust Gait Recognition with Event Streams](https://mlsanity.com/paper/2605.22139/) (2026)
- [GaitSTR: Gait Recognition with Sequential Two-stream Refinement](https://mlsanity.com/paper/2404.02345/) (2024)
- [GenHPE: Generative Counterfactuals for 3D Human Pose Estimation with Radio Frequency Signals](https://mlsanity.com/paper/2503.09537/) (2025)
- [CVVNet: A Cross-Vertical-View Network for Gait Recognition](https://mlsanity.com/paper/2505.01837/) (2025)
- [Gait Recognition via Collaborating Discriminative and Generative Diffusion Models](https://mlsanity.com/paper/2511.06245/) (2025)
- [Vocabulary-Guided Gait Recognition](https://mlsanity.com/paper/2609.18413/) (2026)
- [Identity-aware Dual-constraint Network for Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2403.08270/) (2024)
- [ZipGait: Bridging Skeleton and Silhouette with Diffusion Model for Advancing Gait Recognition](https://mlsanity.com/paper/2408.12111/) (2024)
- [Learning Geometric Invariance for Gait Recognition](https://mlsanity.com/paper/2601.05604/) (2026)
- [TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation](https://mlsanity.com/paper/2602.08462/) (2026)
- [SilLang: Improving Gait Recognition with Silhouette Language Encoding](https://mlsanity.com/paper/2603.23976/) (2026)
- [Gait Recognition with Temporal Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2604.09990/) (2026)
- [Gait Recognition via Deep Residual Networks and Multi-Branch Feature Fusion](https://mlsanity.com/paper/2604.27353/) (2026)
- [Learning A Unified Template for Gait Recognition](https://mlsanity.com/paper/2609.18490/) (2026)

## Abstract (arXiv)

Gait is one of the most promising biometrics that aims to identify pedestrians from their walking patterns. However, prevailing methods are susceptible to confounders, resulting in the networks hardly focusing on the regions that reflect effective walking patterns. To address this fundamental problem in gait recognition, we propose a Generative Counterfactual Intervention framework, dubbed GaitGCI, consisting of Counterfactual Intervention Learning (CIL) and Diversity-Constrained Dynamic Convolution (DCDC). CIL eliminates the impacts of confounders by maximizing the likelihood difference between factual/counterfactual attention while DCDC adaptively generates sample-wise factual/counterfactual attention to efficiently perceive the sample-wise properties. With matrix decomposition and diversity constraint, DCDC guarantees the model to be efficient and effective. Extensive experiments indicate that proposed GaitGCI: 1) could effectively focus on the discriminative and interpretable regions that reflect gait pattern; 2) is model-agnostic and could be plugged into existing models to improve performance with nearly no extra cost; 3) efficiently achieves state-of-the-art performance on arbitrary scenarios (in-the-lab and in-the-wild).