WLASL
PulseAugur coverage of WLASL — every cluster mentioning WLASL across labs, papers, and developer communities, ranked by signal.
-
New AI models advance sign language recognition and production
Researchers have developed novel methods for sign language recognition and production, moving beyond traditional closed-set classification. One approach uses video captioning and description retrieval to create a revers…
-
New Transformer Model Achieves SOTA in Sign Language Recognition
Researchers have developed a novel Transformer-based architecture called the Sequential Spatio-Temporal Attention Network (SSTAN) for dynamic sign language and fingerspelling recognition. This model utilizes hierarchica…
-
New lightweight Transformer model boosts sign language recognition accuracy
Researchers have developed TransSLR, a lightweight Transformer model designed for sign language recognition, particularly for under-represented languages like Central African Sign Language (CASL). This model operates on…
-
SIGNET framework enables cross-language sign language translation via motion knowledge transfer
Researchers have developed SIGNET, a new framework designed to improve cross-language sign language translation by transferring motion-level knowledge between different sign languages. This approach leverages pretrained…
-
SignMAE uses segmentation to improve sign language recognition accuracy
Researchers have developed SignMAE, a novel self-supervised learning method for sign language recognition that leverages segmentation to better capture the nuances of hand and body movements. Unlike previous approaches …