Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

2026-07-16

AI Summary

Current single-modality person re-identification faces performance bottlenecks under challenging conditions such as low illumination and occlusion. This work systematically reviews the evolution of multimodal person re-identification, encompassing cross-modal tasks including visible-infrared, text-to-image, sketch-based, and non-line-of-sight scenarios. It further introduces, for the first time, a Transformer-based baseline framework for visible-infrared re-identification, which achieves effective matching through cross-modal alignment and modality-invariant feature learning. The proposed comprehensive survey framework and baseline model not only substantially enhance cross-modal retrieval performance but also establish a unified reference benchmark and offer forward-looking directions for future research in the field.

Abstract

Person re-identification (ReID) serves as a critical component in intelligent surveillance systems, aiming to match identities across disjoint camera networks. While traditional methods primarily rely on single-modal RGB imagery, they are often constrained by environmental challenges such as low illumination and occlusion. To overcome these limitations, the field is rapidly evolving toward cross-modal and multi-modal paradigms. This survey presents a comprehensive overview of this transition, systematically reviewing key cross-modal tasks including visible-infrared (VI-ReID), text-image (TI-ReID), sketch-based (Sketch-ReID), and the emerging Non-Line-of-Sight (NLOS) ReID, which extends perception beyond direct visibility. Furthermore, we examine tri-spectral and multi-modal fusion ReID, discussing how complementary information from diverse sensors enhances robustness. Beyond summarizing datasets, challenges, and methodologies, we propose a Transformer-based baseline framework for visible-infrared ReID, designed to effectively capture modality-invariant features. Finally, based on the current landscape, we outline several promising directions for future research.

Problem

• Person Re-identification
• Single-modal
• Environmental challenges
• Low illumination
• Occlusion

Innovation

• multi-modal person re-identification
• cross-modal ReID
• Transformer-based baseline
• modality-invariant features
• Non-Line-of-Sight ReID