3260 papers • 126 benchmarks • 313 datasets
Sign Language Production (SLP) is the automatically translation from spoken language sentences into sign language sequences. Whilst Sign language Translation translates from sign to text, SLP is the opposite task from text to sign.
(Image credit: Papersgraph)
These leaderboards are used to track progress in sign-language-production-3
No benchmarks available.
Use these libraries to find sign-language-production-3 models and implementations
No subtasks available.
A back translation evaluation mechanism for SLP is proposed, presenting benchmark quantitative results on the challenging RWTH-PHoENIX-Weather-2014T(PHOENIX14T) dataset and setting baselines for future research.
A study with ASL signers is conducted and it is shown that synthesized videos using the How2Sign dataset can indeed be understood and gives insights on challenges that computer vision should address in order to make progress in this field.
This work proposes a novel Frame Selection Network (FS-NET) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences, and proposes SIGNGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose.
This paper introduces an innovative solution by transforming the continuous pose generation problem into a discrete sequence generation problem, overcoming the need for costly annotation and presents a sign stitching method to effectively join tokens together.
This paper uses the SignGAN model to map the output to a photo-realistic signer and presents a complete Text-to-Sign (T2S) SLP pipeline, showcasing state-of-the-art performance across all datasets.
Adding a benchmark result helps the community track progress.