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

Existing 3D skeleton-based action recognition approaches reach impressiveperformance by encoding handcrafted action features to image format anddecoding by CNNs. However, such methods are limited in two ways: a) thehandcrafted action features are difficult to handle challenging actions, and b)they generally require complex CNN models to improve action recognitionaccuracy, which usually occur heavy computational burden. To overcome theselimitations, we introduce a novel AFE-CNN, which devotes to enhance thefeatures of 3D skeleton-based actions to adapt to challenging actions. Wepropose feature enhance modules from key joint, bone vector, key frame andtemporal perspectives, thus the AFE-CNN is more robust to camera views and bodysizes variation, and significantly improve the recognition accuracy onchallenging actions. Moreover, our AFE-CNN adopts a light-weight CNN model todecode images with action feature enhanced, which ensures a much lowercomputational burden than the state-of-the-art methods. We evaluate the AFE-CNNon three benchmark skeleton-based action datasets: NTU RGB+D, NTU RGB+D 120,and UTKinect-Action3D, with extensive experimental results demonstrate ouroutstanding performance of AFE-CNN.

AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement