Search papers, labs, and topics across Lattice.
This survey critically examines the evolution of person re-identification (ReID) from traditional single-modal approaches to advanced cross-modal and multi-modal techniques, addressing the limitations posed by environmental challenges. It systematically reviews key tasks such as visible-infrared, text-image, sketch-based, and Non-Line-of-Sight ReID, highlighting how multi-modal fusion can enhance robustness through complementary sensor information. The authors propose a Transformer-based baseline framework for visible-infrared ReID that effectively captures modality-invariant features, paving the way for future research directions in this rapidly advancing field.
Multi-modal person re-identification can significantly enhance identity matching in challenging environments, with a new Transformer-based framework setting the stage for future breakthroughs.
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.
