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

We address the task of American Sign Language fingerspelling translationusing videos in the wild. We exploit advances in more accurate hand poseestimation and propose a novel architecture that leverages the transformerbased encoder-decoder model enabling seamless contextual word translation. Thetranslation model is augmented by a novel loss term that accurately predictsthe length of the finger-spelled word, benefiting both training and inference.We also propose a novel two-stage inference approach that re-ranks thehypotheses using the language model capabilities of the decoder. Throughextensive experiments, we demonstrate that our proposed method outperforms thestate-of-the-art models on ChicagoFSWild and ChicagoFSWild+ achieving more than10% relative improvement in performance. Our findings highlight theeffectiveness of our approach and its potential to advance fingerspellingrecognition in sign language translation. Code is also available athttps://github.com/pooyafayyaz/Fingerspelling-PoseNet.

Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models