A Cross-Dataset Study on the Brazilian Sign Language Translation

Abstract

Signed communication is an important form of natural language, often less studied, but still relevant. The main question we address in this paper is how to translate Brazilian Sign Language (LIBRAS) implementing Deep Learning networks with limited data availability. Previous studies often use a single dataset, in most cases collected by the authors themselves. We claim a cross-dataset approach would be more adequate to evaluate real-world scenarios. We investigate two methods based on spatial feature extraction. The first one uses pre-trained Convolutional Neural Networks (CNN) and the second one Body Landmark Estimation (skeleton information). A Long Short-Term Memory (LSTM) network is responsible for the sign classification. Our contribution encompasses data curation, alongside providing general guidelines for enhanced generalization.

Cite

Text

de Avellar Sarmento and Ponti. "A Cross-Dataset Study on the Brazilian Sign Language Translation." IEEE/CVF International Conference on Computer Vision Workshops, 2023. doi:10.1109/ICCVW60793.2023.00300

Markdown

[de Avellar Sarmento and Ponti. "A Cross-Dataset Study on the Brazilian Sign Language Translation." IEEE/CVF International Conference on Computer Vision Workshops, 2023.](https://mlanthology.org/iccvw/2023/deavellarsarmento2023iccvw-crossdataset/) doi:10.1109/ICCVW60793.2023.00300

BibTeX

@inproceedings{deavellarsarmento2023iccvw-crossdataset,
  title     = {{A Cross-Dataset Study on the Brazilian Sign Language Translation}},
  author    = {de Avellar Sarmento, Amanda Hellen and Ponti, Moacir Antonelli},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2023},
  pages     = {2808-2812},
  doi       = {10.1109/ICCVW60793.2023.00300},
  url       = {https://mlanthology.org/iccvw/2023/deavellarsarmento2023iccvw-crossdataset/}
}