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 vital role in facilitatingcommunication for the hearing-impaired community. SLR is a weakly supervisedtask where entire videos are annotated with glosses, making it challenging toidentify the corresponding gloss within a video segment. Recent studiesindicate that the main bottleneck in SLR is the insufficient training caused bythe limited availability of large-scale datasets. To address this challenge, wepresent SignVTCL, a multi-modal continuous sign language recognition frameworkenhanced by visual-textual contrastive learning, which leverages the fullpotential of multi-modal data and the generalization ability of language model.SignVTCL integrates multi-modal data (video, keypoints, and optical flow)simultaneously to train a unified visual backbone, thereby yielding more robustvisual representations. Furthermore, SignVTCL contains a visual-textualalignment approach incorporating gloss-level and sentence-level alignment toensure precise correspondence between visual features and glosses at the levelof individual glosses and sentence. Experimental results conducted on threedatasets, Phoenix-2014, Phoenix-2014T, and CSL-Daily, demonstrate that SignVTCLachieves state-of-the-art results compared with previous methods.

SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning