论文标题
连续手语视频中的主题检测
Topic Detection in Continuous Sign Language Videos
论文作者
论文摘要
最近在自动手语理解中的具有挑战性的任务（例如手语识别，翻译和生产）方面取得了重大进展。但是，这些作品集中在相对较少的样本，简短记录以及有限的词汇和签名空间的数据集上。在这项工作中，我们介绍了手语主题检测的新任务。我们基于跨越多个语义域的大规模视频数据集的2sign的实验。我们为主题检测任务提供了强大的基准，并在手语领域常用的不同视觉特征之间进行了比较。
Significant progress has been made recently on challenging tasks in automatic sign language understanding, such as sign language recognition, translation and production. However, these works have focused on datasets with relatively few samples, short recordings and limited vocabulary and signing space. In this work, we introduce the novel task of sign language topic detection. We base our experiments on How2Sign, a large-scale video dataset spanning multiple semantic domains. We provide strong baselines for the task of topic detection and present a comparison between different visual features commonly used in the domain of sign language.
