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

Pedestrian attribute recognition aims to assign multiple attributes to onepedestrian image captured by a video surveillance camera. Although numerousmethods are proposed and make tremendous progress, we argue that it is time tostep back and analyze the status quo of the area. We review and rethink therecent progress from three perspectives. First, given that there is no explicitand complete definition of pedestrian attribute recognition, we formally defineand distinguish pedestrian attribute recognition from other similar tasks.Second, based on the proposed definition, we expose the limitations of theexisting datasets, which violate the academic norm and are inconsistent withthe essential requirement of practical industry application. Thus, we proposetwo datasets, PETA\textsubscript{$ZS$} and RAP\textsubscript{$ZS$}, constructedfollowing the zero-shot settings on pedestrian identity. In addition, we alsointroduce several realistic criteria for future pedestrian attribute datasetconstruction. Finally, we reimplement existing state-of-the-art methods andintroduce a strong baseline method to give reliable evaluations and faircomparisons. Experiments are conducted on four existing datasets and twoproposed datasets to measure progress on pedestrian attribute recognition.

Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting