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) achieved promising performance inskeleton-based human action recognition by modeling a sequence of skeletons asa spatio-temporal graph. Most of the recently proposed GCN-based methodsimprove the performance by learning the graph structure at each layer of thenetwork using a spatial attention applied on a predefined graph Adjacencymatrix that is optimized jointly with model's parameters in an end-to-endmanner. In this paper, we analyze the spatial attention used in spatio-temporalGCN layers and propose a symmetric spatial attention for better reflecting thesymmetric property of the relative positions of the human body joints whenexecuting actions. We also highlight the connection of spatio-temporal GCNlayers employing additive spatial attention to bilinear layers, and we proposethe spatio-temporal bilinear network (ST-BLN) which does not require the use ofpredefined Adjacency matrices and allows for more flexible design of the model.Experimental results show that the three models lead to effectively the sameperformance. Moreover, by exploiting the flexibility provided by the proposedST-BLN, one can increase the efficiency of the model.

On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition