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

Hand gesture serves as a critical role in sign language. Currentdeep-learning-based sign language recognition (SLR) methods may sufferinsufficient interpretability and overfitting due to limited sign data sources.In this paper, we introduce the first self-supervised pre-trainable SignBERTwith incorporated hand prior for SLR. SignBERT views the hand pose as a visualtoken, which is derived from an off-the-shelf pose extractor. The visual tokensare then embedded with gesture state, temporal and hand chirality information.To take full advantage of available sign data sources, SignBERT first performsself-supervised pre-training by masking and reconstructing visual tokens.Jointly with several mask modeling strategies, we attempt to incorporate handprior in a model-aware method to better model hierarchical context over thehand sequence. Then with the prediction head added, SignBERT is fine-tuned toperform the downstream SLR task. To validate the effectiveness of our method onSLR, we perform extensive experiments on four public benchmark datasets, i.e.,NMFs-CSL, SLR500, MSASL and WLASL. Experiment results demonstrate theeffectiveness of both self-supervised learning and imported hand prior.Furthermore, we achieve state-of-the-art performance on all benchmarks with anotable gain.

SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition