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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep part-based methods in recent literature have revealed the greatpotential of learning local part-level representation for pedestrian image inthe task of person re-identification. However, global features that capturediscriminative holistic information of human body are usually ignored or notwell exploited. This motivates us to investigate joint learning global andlocal features from pedestrian images. Specifically, in this work, we propose anovel framework termed tree branch network (TBN) for person re-identification.Given a pedestrain image, the feature maps generated by the backbone CNN, arepartitioned recursively into several pieces, each of which is followed by abottleneck structure that learns finer-grained features for each level in thehierarchical tree-like framework. In this way, representations are learned in acoarse-to-fine manner and finally assembled to produce more discriminativeimage descriptions. Experimental results demonstrate the effectiveness of theglobal and local feature learning method in the proposed TBN framework. We alsoshow significant improvement in performance over state-of-the-art methods onthree public benchmarks: Market-1501, CUHK-03 and DukeMTMC.

Pedestrian re-identification based on Tree branch network with local and global learning