English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Most existing cross-modality person re-identification works rely ondiscriminative modality-shared features for reducing cross-modality variationsand intra-modality variations. Despite some initial success, suchmodality-shared appearance features cannot capture enough modality-invariantdiscriminative information due to a massive discrepancy between RGB andinfrared images. To address this issue, on the top of appearance features, wefurther capture the modality-invariant relations among different person parts(referred to as modality-invariant relation features), which are the complementto those modality-shared appearance features and help to identify persons withsimilar appearances but different body shapes. To this end, a Multi-levelTwo-streamed Modality-shared Feature Extraction (MTMFE) sub-network isdesigned, where the modality-shared appearance features and modality-invariantrelation features are first extracted in a shared 2D feature space and a shared3D feature space, respectively. The two features are then fused into the finalmodality-shared features such that both cross-modality variations andintra-modality variations can be reduced. Besides, a novel cross-modalityquadruplet loss is proposed to further reduce the cross-modality variations.Experimental results on several benchmark datasets demonstrate that ourproposed method exceeds state-of-the-art algorithms by a noticeable margin.

Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification