@inproceedings{bassomadjoukeng:26037:sign-lang:lrec,
  author    = {Basso Madjoukeng, Ariel and Poitier, Pierre and Kenmogne, Belise Edith and Couplet, Adelaide and Leleu, Margaux and Benoit, Frenay},
  title     = {Leveraging Unannotated Sign Language Data via a Robust Data Augmentation Method for Contrastive Representation Learning},
  pages     = {10--16},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc},
  booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion},
  maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Palma, Mallorca, Spain},
  day       = {16},
  month     = may,
  year      = {2026},
  isbn      = {978-2-493814-82-1},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26037.html},
  abstract  = {Contrastive learning is a deep learning paradigm that allows the learning of useful representations without annotations. In many fields, including sign language recognition (SLR), contrastive approaches have proven to be very effective for developing pretrained models. To learn representations, they generate augmented variants of an instance through augmentation techniques and then maximize their similarities. The quality of the learned representations is strongly correlated with the augmentations used during training. In several fields, specialized augmentations have been developed and adopted. However, in SLR, we observed two trends: contrastive-based SLR approaches often rely on augmentations that are not realistic for the application (e.g., vertical flip, excessive rotations); specialized augmentation methods lack robustness. Hence, when they are used as a starting point for contrastive algorithms, the learned representations are often irrelevant, and sometimes sensitive. These issues considerably affect the accuracy of SLR models on downstream tasks. In response, this paper proposes a robust augmentation method specially designed for contrastive approaches applied to SLR. The results show an improvement in accuracy during linear evaluation and semi-supervised learning with only 30{\%} of annotations.}
}

@inproceedings{poitier:26022:sign-lang:lrec,
  author    = {Poitier, Pierre and Fink, J{\'e}r{\^o}me and Basso Madjoukeng, Ariel and Couplet, Adelaide and Leleu, Margaux and Fr{\'e}nay, Beno{\^i}t},
  title     = {Long-Term Sign Language Data Crowdsourcing Through Collaborative Lexicons},
  pages     = {419--428},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc},
  booktitle = {Proceedings of the {LREC2026} 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion},
  maintitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Palma, Mallorca, Spain},
  day       = {16},
  month     = may,
  year      = {2026},
  isbn      = {978-2-493814-82-1},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/26022.html},
  abstract  = {While there exists a multitude of different sign languages (SLs) across the world, Deaf communities often lack the digital tools required to document and process their languages. In this work, we introduce Mot-Signe (MOSI), an application designed in close collaboration with actors from the French Belgian Deaf community. Our tool enables users to search for French Belgian Sign Language (LSFB) translations or to propose new ones by recording signs themselves. This crowdsourcing approach facilitates the collection of SL data in the wild, enriching the available documentation on LSFB and proposing an innovative response to the data scarcity issue inherent to sign language processing. To evaluate the sustainability of this community-driven data collection, a longitudinal user study was conducted. Following its public release, MOSI demonstrated significant real-world adoption, enabling the collection of over 3,000 distinct LSFB signs. Notably, MOSI captures highly valuable linguistic variations and specialized vocabulary often absent from traditional corpora.}
}