Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison

TL;DR

This paper introduces the largest publicly available large-scale sign language dataset for word-level recognition, compares deep learning models on it, and proposes a novel pose-based graph convolutional network to improve recognition accuracy.

Contribution

The paper provides a new extensive dataset for sign language recognition, benchmarks existing models, and introduces a novel pose-based graph convolutional network for improved performance.

Findings

Pose-based and appearance-based models achieve up to 66% top-10 accuracy.

The new dataset contains over 2000 words performed by 100 signers.

The Pose-TGCN model enhances pose-based recognition performance.

Abstract

Vision-based sign language recognition aims at helping deaf people to communicate with others. However, most existing sign language datasets are limited to a small number of words. Due to the limited vocabulary size, models learned from those datasets cannot be applied in practice. In this paper, we introduce a new large-scale Word-Level American Sign Language (WLASL) video dataset, containing more than 2000 words performed by over 100 signers. This dataset will be made publicly available to the research community. To our knowledge, it is by far the largest public ASL dataset to facilitate word-level sign recognition research. Based on this new large-scale dataset, we are able to experiment with several deep learning methods for word-level sign recognition and evaluate their performances in large scale scenarios. Specifically we implement and compare two different models,i.e., (i) holistic visual appearance-based approach, and (ii) 2D human pose based approach. Both models are valuable baselines that will benefit the community for method benchmarking. Moreover, we also propose a novel pose-based temporal graph convolution networks (Pose-TGCN) that models spatial and temporal dependencies in human pose trajectories simultaneously, which has further boosted the performance of the pose-based method. Our results show that pose-based and appearance-based models achieve comparable performances up to 66% at top-10 accuracy on 2,000 words/glosses, demonstrating the validity and challenges of our dataset. Our dataset and baseline deep models are available at \url{https://dxli94.github.io/WLASL/}.