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 detection has achieved great improvements in recent years, whilecomplex occlusion handling is still one of the most important problems. To takeadvantage of the body parts and context information for pedestrian detection,we propose the part and context network (PCN) in this work. PCN speciallyutilizes two branches which detect the pedestrians through body parts semanticand context information, respectively. In the Part Branch, the semanticinformation of body parts can communicate with each other via recurrent neuralnetworks. In the Context Branch, we adopt a local competition mechanism foradaptive context scale selection. By combining the outputs of all branches, wedevelop a strong complementary pedestrian detector with a lower miss rate andbetter localization accuracy, especially for occlusion pedestrian.Comprehensive evaluations on two challenging pedestrian detection datasets(i.e. Caltech and INRIA) well demonstrated the effectiveness of the proposedPCN.

PCN: Part and Context Information for Pedestrian Detection with CNNs