Publications - Computer vision

LSA-T: The First Continuous Argentinian Sign Language Dataset for Sign Language Translation
Conference paper

LSA-T is the first continuous Argentinian Sign Language (LSA) dataset. It contains ~22 hs of video extracted from the CN Sordos YouTube channel with Spanish subtitles, joints for each signer, and the inferred signer if there is more than one person in a clip. Videos are in 30 FPS full HD (1920x1080). Full specifications at https://midusi.github.io/LSA-T/.

Computer vision Dataset Deep learning LSA-T Sign language translation

A Comparison of Neural Networks for Sign Language Recognition with LSA64
Conference paper

We evaluate three models built on standard recurrent and convolutional neural network layers on LSA64. Coupled with carefully chosen hyperparameters and preprocessing techniques, these models are all able to achieve near perfect accuracy on LSA64, surpassing all previous models, many specifically designed for this task.

Sign language recognition Neural networks LSA64 Convolutional neural networks Recurrent neural networks Computer vision

LSA-T: The First Continuous Argentinian Sign Language Dataset for Sign Language TranslationConference paper

A Comparison of Neural Networks for Sign Language Recognition with LSA64Conference paper

LSA-T: The First Continuous Argentinian Sign Language Dataset for Sign Language Translation
Conference paper

A Comparison of Neural Networks for Sign Language Recognition with LSA64
Conference paper