1 code implementation • 17 Oct 2024 • Amit Moryossef, Gerard Sant, Zifan Jiang
We introduce a method for transferring the signer's appearance in sign language skeletal poses while preserving the sign content.
1 code implementation • 1 Jul 2024 • Zifan Jiang, Gerard Sant, Amit Moryossef, Mathias Müller, Rico Sennrich, Sarah Ebling
We present SignCLIP, which re-purposes CLIP (Contrastive Language-Image Pretraining) to project spoken language text and sign language videos, two classes of natural languages of distinct modalities, into the same space.
1 code implementation • 21 Oct 2023 • Amit Moryossef, Zifan Jiang, Mathias Müller, Sarah Ebling, Yoav Goldberg
We find that introducing BIO tagging is necessary to model sign boundaries.
2 code implementations • 20 Sep 2023 • Amit Moryossef, Zifan Jiang
We introduce SignBank+, a clean version of the SignBank dataset, optimized for machine translation between spoken language text and SignWriting, a phonetic sign language writing system.
2 code implementations • 28 May 2023 • Amit Moryossef, Mathias Müller, Anne Göhring, Zifan Jiang, Yoav Goldberg, Sarah Ebling
Sign language translation systems are complex and require many components.
1 code implementation • 5 Jan 2023 • Zifan Jiang, Adrian Soldati, Isaac Schamberg, Adriano R. Lameira, Steven Moran
We present a novel approach to automatically detect and classify great ape calls from continuous raw audio recordings collected during field research.
no code implementations • 28 Nov 2022 • Mathias Müller, Zifan Jiang, Amit Moryossef, Annette Rios, Sarah Ebling
Automatic sign language processing is gaining popularity in Natural Language Processing (NLP) research (Yin et al., 2021).
1 code implementation • 11 Oct 2022 • Zifan Jiang, Amit Moryossef, Mathias Müller, Sarah Ebling
This paper presents work on novel machine translation (MT) systems between spoken and signed languages, where signed languages are represented in SignWriting, a sign language writing system.
no code implementations • 17 Jun 2021 • Salman Seyedi, Zifan Jiang, Allan Levey, Gari D. Clifford
The expanding usage of complex machine learning methods like deep learning has led to an explosion in human activity recognition, particularly applied to health.