Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification

2026-04-16

AI Summary

This work addresses the challenges of unreliable pseudo-labels and cross-modal misalignment in unsupervised video-based visible-infrared person re-identification, which stem from modality bias and identity confusion. To tackle these issues, the authors propose a Causal Bootstrapping Alignment (CBA) framework that uniquely integrates causal intervention with prototype-guided uncertainty refinement. Specifically, Causal Intervention Warm-up (CIW) suppresses spurious cross-modal correlations, while Prototype-Guided Uncertainty Refinement (PGUR) enables coarse-to-fine cross-modal alignment, effectively mitigating imbalanced clustering granularity. Extensive experiments on the HITSZ-VCM and BUPTCampus benchmarks demonstrate that the proposed method significantly outperforms existing unsupervised approaches, validating its effectiveness for all-weather video-based cross-modal person re-identification.

Technology Category

• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Causality
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images. However, existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability. To address this issue, we investigate Unsupervised Learning for VVI-ReID (USL-VVI-ReID), which learns identity-discriminative representations directly from unlabeled video tracklets. Directly extending image-based USL-VI-ReID methods to this setting with generic pretrained encoders leads to suboptimal performance. Such encoders suffer from weak identity discrimination and strong modality bias, resulting in severe intra-modality identity confusion and pronounced clustering granularity imbalance between visible and infrared modalities. These issues jointly degrade pseudo-label reliability and hinder effective cross-modality alignment. To address these challenges, we propose a Causal Bootstrapped Alignment (CBA) framework that explicitly exploits inherent video priors. First, we introduce Causal Intervention Warm-up (CIW), which performs sequence-level causal interventions by leveraging temporal identity consistency and cross-modality identity consistency to suppress modality- and motion-induced spurious correlations while preserving identity-relevant semantics, yielding cleaner representations for unsupervised clustering. Second, we propose Prototype-Guided Uncertainty Refinement (PGUR), which employs a coarse-to-fine alignment strategy to resolve cross-modality granularity mismatch, reorganizing under-clustered infrared representations under the guidance of reliable visible prototypes with uncertainty-aware supervision. Extensive experiments on the HITSZ-VCM and BUPTCampus benchmarks demonstrate that CBA significantly outperforms existing USL-VI-ReID methods when extended to the USL-VVI-ReID setting.

Problem

• Visible-Infrared Person Re-Identification
• Unsupervised Learning
• Modality Bias
• Pseudo-label Reliability
• Cross-modality Alignment

Innovation

• Causal Intervention
• Unsupervised Video ReID
• Cross-Modality Alignment
• Prototype Guidance
• Temporal Consistency