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.
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· Engineering Research Express· 0 citations
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.
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.
It is shown that modality-unified prototypical contrast facilitates better modality invariance by jointly and simultaneously optimizing similarity relation within and across-modality.
This study proposes a novel dual-path convolution based multi-scale feature alignment (DCMFA) network that significantly outperforms existing mainstream methods in terms of recognition accuracy.
Bai-Liang Huang, Bin Chen, Tian-Ran Sun et al.· 電腦學刊· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.