冰岛手语的孤立手语识别：低资源环境下的实验
Isolated Sign Language Recognition for Icelandic Sign Language: Experiments in a Low-resource Setting
- University of Zurich（苏黎世大学）
- Communication Centre for the Deaf and Hard of Hearing in Iceland（冰岛聋人与听力障碍者交流中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对冰岛手语这一极低资源场景，本文首次实验了孤立手语识别，比较OpenHands与SPOTER框架，发现跨语言迁移能显著提升准确率，最高达28.86%。
AI中文摘要：
我们首次开展了针对冰岛手语（ÍTM）的孤立手语识别（ISLR）实验。我们使用了ÍTM SignWiki，这是一个源自冰岛语-冰岛手语双语在线词典的数据集。该数据集真正属于低资源：1,845个视频覆盖849个类别，其中86%的类别仅有两个示例，使得完整任务实际上成为跨手语者的一次性识别。我们在词汇量递增的三个任务（22、117和849个类别）上比较了两种开源ISLR框架OpenHands和SPOTER，并评估了三种姿态估计器和两种跨语言迁移形式。仅使用ÍTM数据时，SPOTER在所有三个任务上均优于OpenHands，且MediaPipe姿态比AlphaPose或SDPose产生更好的结果。跨语言迁移带来了最大的收益：在ÍTM上微调之前，使用美国手语数据预训练SPOTER，在三个任务上的准确率提高了14至24个百分点，分别达到72.7%、47.9%和22.6%；而使用来自其他六种手语的数据进行多语言训练，将OpenHands在完整任务上的准确率从1.41%提升至28.86%。尽管距离实际应用还很远，但结果表明，从资源更丰富的手语进行迁移对于极低资源的手语是有前景的。我们发布了这两个框架的改编版本。
英文摘要：
We present the first experiments on isolated sign language recognition (ISLR) for Icelandic Sign Language (ÍTM). We use ÍTM SignWiki, a dataset derived from a bilingual Icelandic--ÍTM online dictionary. It is genuinely low-resource: 1,845 videos cover 849 classes, 86% of which have only two examples, making the full task effectively one-shot recognition across signers. We compare two open-source ISLR frameworks, OpenHands and SPOTER, on three tasks of increasing vocabulary size (22, 117 and 849 classes), and evaluate three pose estimators and two forms of cross-lingual transfer. With ÍTM data alone, SPOTER outperforms OpenHands on all three tasks, and MediaPipe poses give better results than AlphaPose or SDPose. Cross-lingual transfer brings the largest gains: pretraining SPOTER on American Sign Language data before finetuning on ÍTM raises accuracy by 14--24 percentage points, to 72.7%, 47.9% and 22.6% on the three tasks, and multilingual training with data from six other sign languages lifts OpenHands from 1.41% to 28.86% on the full task. Although far from practical use, the results suggest that transfer from better-resourced sign languages is promising for very low-resource ones. We release our adapted versions of both frameworks.
