Significant progress has been made recently on challenging tasks in automatic sign language understanding, such as sign language recognition, translation and production. However, these works have focused on datasets with relatively few samples, short recordings and limited vocabulary and signing space. In this work, we introduce the novel task of sign language topic detection. We base our experiments on How2Sign, a large-scale video dataset spanning multiple semantic domains. We provide strong baselines for the task of topic detection and present a comparison between different visual features commonly used in the domain of sign language.
@article{arxiv.2209.02402,
title = {Topic Detection in Continuous Sign Language Videos},
author = {Alvaro Budria and Laia Tarres and Gerard I. Gallego and Francesc Moreno-Noguer and Jordi Torres and Xavier Giro-i-Nieto},
journal= {arXiv preprint arXiv:2209.02402},
year = {2022}
}
Comments
Presented as an extended abstract in the "AVA: Accessibility, Vision, and Autonomy Meet" CVPR 2022 Workshop