Unsupervised Discovery of Sign Terms by K-Nearest Neighbours Approach

Unsupervised Discovery of Sign Terms by K-Nearest Neighbours Approach
复制标题

通过 K 最近邻方法无监督地发现符号项

DOI:
10.1007/978-3-030-66096-3_22
复制
发表时间:
2020
期刊:
影响因子:
3.9
通讯作者:
M. Saraçlar
M. Saraçlar
中科院分区:
计算机科学3区
文献类型:
--
作者:
Korhan Polat;M. Saraçlar

文献摘要

参考文献

被引文献

相似文献

。为了充分利用大量的未标注手语资源,需要采用无监督的学习方法。受口语中无监督术语发现(UTD)的成功结果的启发,我们探索如何将类似的方法应用于手语术语发现。我们的目标是在没有任何监督的情况下从连续的签名视频中fi和重复的条款。利用从RGB视频中提取的视觉特征,我们证明了一种基于k近邻的语音发现算法也可以发现符号项。我们还使用基线UTD算法进行了实验,并对它们的差异进行了评论。
. In order to utilize the large amount of unlabeled sign language resources, unsupervised learning methods are needed. Motivated by the successful results of unsupervised term discovery (UTD) in spoken languages, here we explore how to apply similar methods for sign terms discovery. Our goal is to find the repeating terms from continuous sign videos without any supervision. Using visual features extracted from RGB videos, we show that a k-nearest neighbours based discovery algorithm designed for speech can also discover sign terms. We also run experiments using a baseline UTD algorithm and comment on their differences.
DOI: 10.5244/c.27.20
发表时间: 2013
期刊: --
影响因子: --
作者:
Tomas Pfister;James Charles;Andrew Zisserman
通讯作者: Tomas Pfister;James Charles;Andrew Zisserman
DOI: 10.1109/taslp.2016.2517567
发表时间: 2016-03
期刊: IEEE/ACM Transactions on Audio, Speech, and Language Processing
影响因子: --
作者:
H. Kamper;A. Jansen;S. Goldwater
通讯作者: H. Kamper;A. Jansen;S. Goldwater