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

Graph convolutional networks (GCNs) have been very successful in modelingnon-Euclidean data structures, like sequences of body skeletons forming actionsmodeled as spatio-temporal graphs. Most GCN-based action recognition methodsuse deep feed-forward networks with high computational complexity to processall skeletons in an action. This leads to a high number of floating pointoperations (ranging from 16G to 100G FLOPs) to process a single sample, makingtheir adoption in restricted computation application scenarios infeasible. Inthis paper, we propose a temporal attention module (TAM) for increasing theefficiency in skeleton-based action recognition by selecting the mostinformative skeletons of an action at the early layers of the network. Weincorporate the TAM in a light-weight GCN topology to further reduce theoverall number of computations. Experimental results on two benchmark datasetsshow that the proposed method outperforms with a large margin the baselineGCN-based method while having 2.9 times less number of computations. Moreover,it performs on par with the state-of-the-art with up to 9.6 times less numberof computations.

Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition