ANONYSIGN: Novel Human Appearance Synthesis for Sign Language Video Anonymisation

Sign languages are rich visual languages, and the main mode of communication for Deaf communities. As with the computational study of spoken languages, sign language research requires large-scale datasets to effectively tackle the tasks of Sign Language Translation (SLT) and Sign Language Production (SLP). However, due to privacy concerns regarding the visual nature of sign language datasets, there is a hesitancy to contribute to data collection [3].