27 February 2024 in IEEE Signal Processing Letters
We propose a new benchmark for vehicle re-identification in mixed visible and infrared domains. Unlike cross-modal vehicle re-identification, we focus on a more realistic scenario, namely, mixed-modal vehicle re-identification, in which both probe and gallery sets contain visible and infrared images. We provide auto-cropped visible and infrared images, simulating data from actual surveillance systems. We design a mixed triplet loss function for model training. We report both mixed-modal and cross-modal retrieval performance. Our mixed method performs well in cross-modal retrieval, e.g., the Rank-1 identification rate is 79.19% in the visible-to-infrared retrieval mode.
27 May 2026 in IEEE Transactions on Intelligent Transportation Systems
Day-night cross-domain object re-identification presents significant challenges due to severe illumination-induced domain gaps. Unlike conventional attention mechanisms that suffer from limited dimensional coverage and rely on single-type normalization strategies, we propose a structural feature modulation (SFM) approach that operates from a modulation perspective. Our SFM approach incorporates a gated batch-layer normalization strategy within the modulation architecture, resulting in the construction of a gated normalization-based modulation (GNM) module. This module effectively leverages the complementary advantages of both batch normalization and layer normalization to balance intra-domain discriminability and cross-domain generalization. Furthermore, we develop a multi-granularity modulation (MGM) module that recalibrates features across both edge-granularity and area-granularity pathways, enabling comprehensive structural modulation. Extensive experiments on the DN-348 and LLCM benchmark datasets demonstrate that our SFM approach consistently outperforms state-of-the-art approaches, achieving notable improvements including a 2.51% mAP increase on the DN-348 dataset. Our codes are available at https://github.com/SimiiZ/SFM