Sign Segmentation with Changepoint-Modulated Pseudo-Labelling

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021)(2021)

引用 13|浏览22
暂无评分
摘要
The objective of this work is to find temporal boundaries between signs in continuous sign language. Motivated by the paucity of annotation available for this task, we propose a simple yet effective algorithm to improve segmentation performance on unlabelled signing footage from a domain of interest. We make the following contributions: (1) We motivate and introduce the task of source-free domain adaptation for sign language segmentation, in which labelled source data is available for an initial training phase, but is not available during adaptation. (2) We propose the Changepoint-Modulated Pseudo-Labelling (CMPL) algorithm to leverage cues from abrupt changes in motion-sensitive feature space to improve pseudo-labelling quality for adaptation. (3) We showcase the effectiveness of our approach for category-agnostic sign segmentation, transferring from the BSLCORPUS to the BSL-1K and RWTH-PHOENIX-Weather 2014 datasets, where we outperform the prior state of the art.
更多
查看译文
关键词
segmentation,changepoint-modulated,pseudo-labelling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要