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

The results obtained from state of the art human pose estimation (HPE) modelsdegrade rapidly when evaluating people of a low resolution, but can superresolution (SR) be used to help mitigate this effect? By using various SRapproaches we enhanced two low resolution datasets and evaluated the change inperformance of both an object and keypoint detector as well as end-to-end HPEresults. We remark the following observations. First we find that for peoplewho were originally depicted at a low resolution (segmentation area in pixels),their keypoint detection performance would improve once SR was applied. Second,the keypoint detection performance gained is dependent on that persons pixelcount in the original image prior to any application of SR; keypoint detectionperformance was improved when SR was applied to people with a small initialsegmentation area, but degrades as this becomes larger. To address this weintroduced a novel Mask-RCNN approach, utilising a segmentation area thresholdto decide when to use SR during the keypoint detection step. This approachachieved the best results on our low resolution datasets for each HPEperformance metrics.

Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?