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

For the visible-infrared person re-identification (VIReID) task, one of themajor challenges is the modality gaps between visible (VIS) and infrared (IR)images. However, the training samples are usually limited, while the modalitygaps are too large, which leads that the existing methods cannot effectivelymine diverse cross-modality clues. To handle this limitation, we propose anovel augmentation network in the embedding space, called diverse embeddingexpansion network (DEEN). The proposed DEEN can effectively generate diverseembeddings to learn the informative feature representations and reduce themodality discrepancy between the VIS and IR images. Moreover, the VIReID modelmay be seriously affected by drastic illumination changes, while all theexisting VIReID datasets are captured under sufficient illumination withoutsignificant light changes. Thus, we provide a low-light cross-modality (LLCM)dataset, which contains 46,767 bounding boxes of 1,064 identities captured by 9RGB/IR cameras. Extensive experiments on the SYSU-MM01, RegDB and LLCM datasetsshow the superiority of the proposed DEEN over several other state-of-the-artmethods. The code and dataset are released at: https://github.com/ZYK100/LLCM

Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification