# Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey

arXiv: https://arxiv.org/abs/2505.20540 · HTML: https://mlsanity.com/paper/2505.20540/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 48 of its 93 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 30 of 48)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition](https://mlsanity.com/paper/1811.06186/) (2018)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [DIVA: Domain Invariant Variational Autoencoders](https://mlsanity.com/paper/1905.10427/) (2019)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness](https://mlsanity.com/paper/1811.00007/) (2018)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [Appearance-Preserving 3D Convolution for Video-based Person Re-identification](https://mlsanity.com/paper/2007.08434/) (2020)
- [Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification](https://mlsanity.com/paper/1803.09882/) (2018)
- [STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification](https://mlsanity.com/paper/1811.04129/) (2018)
- [Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization](https://mlsanity.com/paper/1910.04562/) (2019)
- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification](https://mlsanity.com/paper/1708.02286/) (2017)
- [Consistent Counterfactuals for Deep Models](https://mlsanity.com/paper/2110.03109/) (2021)
- [Quality Aware Network for Set to Set Recognition](https://mlsanity.com/paper/1704.03373/) (2017)
- [Video-based Person Re-identification with Spatial and Temporal Memory Networks](https://mlsanity.com/paper/2108.09039/) (2021)
- [A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification](https://mlsanity.com/paper/2104.01745/) (2021)
- [Revisiting Temporal Modeling for Video-based Person ReID](https://mlsanity.com/paper/1805.02104/) (2018)
- [Dense Interaction Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.09013/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Resource Aware Person Re-identification across Multiple Resolutions](https://mlsanity.com/paper/1805.08805/) (2018)

## Abstract (arXiv)

Video-based person re-identification (Re-ID) remains brittle in real-world deployments despite impressive benchmark performance. Most existing models rely on superficial correlations such as clothing, background, or lighting that fail to generalize across domains, viewpoints, and temporal variations. This survey examines the emerging role of causal reasoning as a principled alternative to traditional correlation-based approaches in video-based Re-ID. We provide a structured and critical analysis of methods that leverage structural causal models, interventions, and counterfactual reasoning to isolate identity-specific features from confounding factors. The survey is organized around a novel taxonomy of causal Re-ID methods that spans generative disentanglement, domain-invariant modeling, and causal transformers. We review current evaluation metrics and introduce causal-specific robustness measures. In addition, we assess practical challenges of scalability, fairness, interpretability, and privacy that must be addressed for real-world adoption. Finally, we identify open problems and outline future research directions that integrate causal modeling with efficient architectures and self-supervised learning. This survey aims to establish a coherent foundation for causal video-based person Re-ID and to catalyze the next phase of research in this rapidly evolving domain.