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

Pose based hand gesture recognition has been widely studied in the recentyears. Compared with full body action recognition, hand gesture involves jointsthat are more spatially closely distributed with stronger collaboration. Thisnature requires a different approach from action recognition to capturing thecomplex spatial features. Many gesture categories, such as "Grab" and "Pinch",have very similar motion or temporal patterns posing a challenge on temporalprocessing. To address these challenges, this paper proposes a two-streamneural network with one stream being a self-attention based graph convolutionalnetwork (SAGCN) extracting the short-term temporal information and hierarchicalspatial information, and the other being a residual-connection enhancedbidirectional Independently Recurrent Neural Network (RBi-IndRNN) forextracting long-term temporal information. The self-attention based graphconvolutional network has a dynamic self-attention mechanism to adaptivelyexploit the relationships of all hand joints in addition to the fixed topologyand local feature extraction in the GCN. On the other hand, theresidual-connection enhanced Bi-IndRNN extends an IndRNN with the capability ofbidirectional processing for temporal modelling. The two streams are fusedtogether for recognition. The Dynamic Hand Gesture dataset and First-PersonHand Action dataset are used to validate its effectiveness, and our methodachieves state-of-the-art performance.

A Two-stream Neural Network for Pose-based Hand Gesture Recognition