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

TL;DR

This survey explores the application of causal reasoning in video-based person re-identification to improve robustness and generalization across real-world scenarios, highlighting current methods, challenges, and future directions.

Contribution

It provides a structured taxonomy of causal Re-ID methods, reviews evaluation metrics, and discusses practical challenges and future research directions in the domain.

Findings

Causal methods can improve robustness to domain shifts.

Current evaluation metrics may not fully capture causal robustness.

Identified key challenges for real-world deployment.

Abstract

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.