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

Sign language recognition (SLR) plays a crucial role in bridging thecommunication gap between the hearing and vocally impaired community and therest of the society. Word-level sign language recognition (WSLR) is the firstimportant step towards understanding and interpreting sign language. However,recognizing signs from videos is a challenging task as the meaning of a worddepends on a combination of subtle body motions, hand configurations, and othermovements. Recent pose-based architectures for WSLR either model both thespatial and temporal dependencies among the poses in different framessimultaneously or only model the temporal information without fully utilizingthe spatial information.  We tackle the problem of WSLR using a novel pose-based approach, whichcaptures spatial and temporal information separately and performs late fusion.Our proposed architecture explicitly captures the spatial interactions in thevideo using a Graph Convolutional Network (GCN). The temporal dependenciesbetween the frames are captured using Bidirectional Encoder Representationsfrom Transformers (BERT). Experimental results on WLASL, a standard word-levelsign language recognition dataset show that our model significantly outperformsthe state-of-the-art on pose-based methods by achieving an improvement in theprediction accuracy by up to 5%.

Pose-based Sign Language Recognition using GCN and BERT