POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation

📝 Original Info

• Title: POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
• ArXiv ID: 2511.00270
• Date: 2025-10-31
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. **

📝 Abstract

Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.

💡 Deep Analysis

📄 Full Content

Reference