Skip to content

Spatio-Spectral Consistent Learning and Hybrid Local-Global Integration for Visible-Infrared Person Re-identification

Sep 2026 · Journal of Supercomputing · Vol 82 · 0 citations · 38 references
Computer Science

TL;DR

A Spatio-Spectral Consistent Learning Network (SSCL-Net) built upon a lightweight backbone is proposed, which leverages directional pooling to precisely capture robust body structures while employing frequency-domain gating to explicitly suppress modality-specific textural interference.

View source

Similar papers

Open access Sep 2026

CMIA-Net: early cross-modal interaction for visible-infrared person re-identification

It is argued that VI-ReID should be treated as an early cross-modal correspondence learning problem rather than only a late embedding alignment problem, and CMIA-Net is proposed, a framework that establishes bidirectional visible-infrared interaction at shallow backbone stages and introduces Spectral-Invariant Augmenta...

Dao-Li Zhang, Qi-Cheng Liu · 0 citations
Aug 2026

Decoupled information-guided cross-modal alignment for visible-infrared person re-identification.

Experiments show that DIGCA achieves competitive overall performance compared with recent VI-ReID methods, providing empirical support for the effectiveness of the proposed decoupling-guided alignment strategy in cross-modal identity matching.

Qing-Song Deng, Guangqian Kong, Xun Duan et al. · 0 citations
Oct 2026

MDGRN: multi-scale deformable embedding and dual-guided relation network for visible-infrared person re-identification

The Multi-Scale Deformable Embedding and Dual-Guided Relation Network (MDGRN) combines fixed multi-scale perception with factorized deformable sampling to capture complementary local representations and further models channel compatibility and spatial reliability between adjacent feature stages.

Xiang-Jie Liu, Cheng-Fang Zhang, Zi-Liang Feng · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.