<ul><li>Researchers have developed a large-scale, multi-view, word-level Bangla Sign Language (BdSL) dataset called BdSLW401, which consists of 401 signs and 102,176 video samples.</li><li>To improve transformer-based Sign Language Recognition (SLR), they have introduced a method called Relative Quantization Encoding (RQE) that quantizes motion trajectories and anchors landmarks to physiological reference points.</li><li>The application of RQE has shown a reduction of 44.3% Word Error Rate (WER) in the WLASL100 dataset and 21.0% in the SignBD-200 dataset, along with significant gains in BdSLW60 and SignBD-90.</li><li>The researchers also introduced an extended variant of RQE called RQE-SF, which improves pose consistency in lateral view recognition.</li></ul>

BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)

Discover more