Multimodal 3D Hand Pose Enhancement for Sign Language
The application of recent deep learning breakthroughs to the domain of sign language has yielded very promising results. However, sign language processing systems depend on large amounts of labeled high-quality data to work properly. Current hand pose estimation methods are often unreliable and do not always produce estimations with enough quality. To mitigate this issue, we explore the applicability of the novel Body2Hands method for the obtainment of high-quality hand pose estimations.
This repo contains the main results produced as part of my research on the task of hand pose enhancement for sign language data. I worked on this topic at University within the context of a course called "Introduction To Research".
Code
The code used for preprocessing data, training models and evaluating them can all be found here.
Article
An article presenting the work can be downloaded from this repository.
Presentation Slides
You can also check out a visual summary of the article in the form of slides.
