Gloss-Free Representation Learning for Cross-Dataset Sign Spotting
无 gloss( gloss 指手语 gloss,即手语的书面转写)的跨数据集手语定位表征学习
机构 * Hacettepe University(哈杰泰佩大学)
专题命中 评测与基准 :LLM(abstract,abstract_cn);pretraining(abstract);分类 cs.CL
AI总结 本研究针对资源受限语言的手语研究,用土耳其广播语料库 TSL-News 基于转录文本的伪 gloss 标签预训练手语编码器,在跨数据集手语定位任务中显著提升性能,证明松散对齐的广播数据可提供有效弱监督学习手语表征。
Comments Accepted at the 4th LIMIT Workshop (Representation Learning with Very Limited Resources), ECCV 2026. The abstract was shortened to comply with arXiv's 1,920-character limit