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

RGB-infrared person re-identification is a challenging task due to theintra-class variations and cross-modality discrepancy. Existing works mainlyfocus on learning modality-shared global representations by aligning imagestyles or feature distributions across modalities, while local feature frombody part and relationships between person images are largely neglected. Inthis paper, we propose a Dual-level (i.e., local and global) Feature Fusion(DF^2) module by learning attention for discriminative feature from local toglobal manner. In particular, the attention for a local feature is determinedlocally, i.e., applying a learned transformation function on itself. Meanwhile,to further mining the relationships between global features from person images,we propose an Affinities Modeling (AM) module to obtain the optimal intra- andinter-modality image matching. Specifically, AM employes intra-classcompactness and inter-class separability in the sample similarities assupervised information to model the affinities between intra- andinter-modality samples. Experimental results show that our proposed methodoutperforms state-of-the-arts by large margins on two widely usedcross-modality re-ID datasets SYSU-MM01 and RegDB, respectively.

DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification