This paper proposes an attentional network for the task of Continuous SignLanguage Recognition . The proposed approach exploits co-independent streams of data to model the sign language modalities . We found that by doing so the model isable to identify the essential Sign Language components that revolve around thedominant hand and the face areas . We test our model on the benchmark dataset RWTH-PHOENIX-Weather 2014, yielding competitive results. We tested the model on a benchmark dataset, which yielded competitive results, and found that the model was able to identify essential sign language components that are centered around the dominant hand and face areas. We utilize the attention mechanism to aggregate the hand features with their appropriate spatio

Author(s) : Fares Ben Slimane, Mohamed Bouguessa

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : model - language - sign - hand - results -

Leave a Reply

Your email address will not be published. Required fields are marked *