3D-LEX v1.0: 3D Lexicons for American Sign Language and Sign Language of the Netherlands
This work provides a new 3D dataset and annotation tool for sign language processing, enabling more detailed analysis and improved recognition, though it is incremental in building on existing linguistic resources.
The authors tackled the problem of capturing sign language in 3D by introducing the 3D-LEX v1.0 dataset with 2,000 signs from American and Dutch sign languages, and a semi-automatic annotation method that improved gloss recognition accuracy by 5% over no annotations and 1% over expert annotations.
In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, and attains an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5% over using no handshape annotations, and by 1% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.