@inproceedings{khan:24043:sign-lang:lrec,
  author    = {Khan, Sarmad and Murtagh, Irene and McLoughlin, Simon D.},
  title     = {Investigating Motion History Images and Convolutional Neural Networks for Isolated {Irish} {Sign} {Language} Fingerspelling Recognition},
  pages     = {140--146},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Mesch, Johanna and Schulder, Marc},
  booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources},
  maintitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)},
  publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}},
  address   = {Torino, Italy},
  day       = {25},
  month     = may,
  year      = {2024},
  isbn      = {978-2-493814-30-2},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/24043.html},
  abstract  = {The limited global competency in sign language makes the objective of improving communication for the deaf and hard-of-hearing community through computational processing both vital and necessary. In an effort to address this problem, our research leverages the Irish Sign Language hand shape (ISL-HS) dataset and state-of-the-art deep learning architectures to recognize the Irish Sign Language alphabet. We streamline the feature extraction methodology and pave the way for the efficient use of Convolutional Neural Networks (CNNs) by using Motion History Images (MHIs) for monitoring the sign language motions. The effectiveness of numerous powerful CNN architectures in deciphering the intricate patterns of motion captured in MHIs is investigated in this research. The process includes generating MHIs from the ISL dataset and then using these images to train several CNN neural network models and evaluate their ability to recognize the Irish Sign Language alphabet. The results demonstrate the possibility of investigating MHIs with advanced CNNs to enhance sign language recognition, with a noteworthy accuracy percentage. By contributing to the development of language processing tools and technologies for Irish Sign Language, this research has the potential to address the lack of technological communicative accessibility and inclusion for the deaf and hard-of-hearing community in Ireland.}
}

@inproceedings{holmes:70025:sltat:lrec,
  author    = {Holmes, Ruth and Rushe, Ellen and Fowley, Frank and Ventresque, Anthony},
  title     = {Improving Signer Independent Sign Language Recognition for Low Resource Languages},
  pages     = {45--52},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and McDonald, John C. and Shterionov, Dimitar and Wolfe, Rosalee},
  booktitle = {Proceedings of the 7th International Workshop on Sign Language Translation and Avatar Technology: The Junction of the Visual and the Textual: Challenges and Perspectives},
  maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Marseille, France},
  day       = {24},
  month     = jun,
  year      = {2022},
  isbn      = {979-10-95546-82-5},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/2022.sltat-1.7.html},
  abstract  = {The reliance of deep learning algorithms on large scale datasets represents a significant challenge when learning from low resource sign language datasets. This challenge is compounded when we consider that, for a model to be effective in the real world, it must not only learn the variations of a given sign, but also learn to be invariant to the person signing. In this paper, we first illustrate the performance gap between signer-independent and signer-dependent models on Irish Sign Language manual hand shape data. We then evaluate the effect of transfer learning, with different levels of fine-tuning, on the generalisation of signer independent models, and show the effects of different input representations, namely variations in image data and pose estimation. We go on to investigate the sensitivity of current pose estimation models in order to establish their limitations and areas in need of improvement. The results show that accurate pose estimation outperforms raw RGB image data, even when relying on pre-trained image models. Following on from this, we investigate image texture as a potential contributing factor to the gap in performance between signer-dependent and signer-independent models using counterfactual testing images and discuss potential ramifications for low-resource sign languages. Keywords: Sign language recognition, Transfer learning, Irish Sign Language, Low-resource languages}
}