@techreport{oai:ipsj.ixsq.nii.ac.jp:00241043,
 author = {Ren, Wang and He, Li and Ren, Wang and He, Li},
 issue = {27},
 month = {Nov},
 note = {This research focuses on developing a model to recognize Japanese Sign Language (JSL) gestures using pose-based data processed through a transformer module. The dataset includes 401 JSL words from single signer videos, with hand gesture landmarks extracted via Mediapipe. These landmarks are transformed into an 18-dimensional vector, normalized, and tokenized for input into a BERT-based model. The architecture supports hands-to-gloss recognition, utilizing masked unit modeling for pre-training. Training is divided into isolated word-level recognition and continuous hands-to-gloss recognition. The model's performance was evaluated using accuracy, precision, recall, and F-measure. It achieved 0.746 accuracy in single-word recognition and improved to 0.808 in continuous sign recognition using cosine similarity and fine-tuning techniques., This research focuses on developing a model to recognize Japanese Sign Language (JSL) gestures using pose-based data processed through a transformer module. The dataset includes 401 JSL words from single signer videos, with hand gesture landmarks extracted via Mediapipe. These landmarks are transformed into an 18-dimensional vector, normalized, and tokenized for input into a BERT-based model. The architecture supports hands-to-gloss recognition, utilizing masked unit modeling for pre-training. Training is divided into isolated word-level recognition and continuous hands-to-gloss recognition. The model's performance was evaluated using accuracy, precision, recall, and F-measure. It achieved 0.746 accuracy in single-word recognition and improved to 0.808 in continuous sign recognition using cosine similarity and fine-tuning techniques.},
 title = {Pose-based Model for Continuous Japanese Sign Language Recognition with Transformer},
 year = {2024}
}